Latest News

Can exercise “therapy” and diet improve survival in patients with colon cancer? It appears so, according to two pivotal studies presented at American Society of Clinical Oncology (ASCO) 2025 annual meeting.

In the CHALLENGE trial, a structured exercise program after surgery and adjuvant chemotherapy cut the risk for colon cancer recurrence in patients with stage III and high-risk stage II disease by more than one quarter and the risk for death by more than one third.

“The magnitude of benefit with exercise is substantial. In fact, it is comparable, and in some cases exceeds the magnitude of benefit of many of our very good standard medical therapies in oncology,” study presenter Christopher Booth, MD, with Queen’s University, Kingston, Ontario, Canada, told attendees.

Results of the study were published online in The New England Journal of Medicine to coincide with the presentation at the meeting.

The findings are “nothing short of a major milestone,” said study discussant Peter Campbell, PhD, with Montefiore Einstein Comprehensive Cancer Center, Bronx, New York.

The other study showed that eating a less inflammatory diet may reduce the risk for death in patients with colon cancer, with the greatest benefits seen in those who embraced anti-inflammatory foods and exercised regularly.

“Putting these two abstracts into perspective, we as physicians need to be essentially prescribing healthy diet and exercise. The combination of the two are synergistic,” Julie Gralow, MD, ASCO chief medical officer and executive vice president, told attendees.

Despite the benefits of these lifestyle changes, exercise and diet are meant to supplement, not replace, established colon cancer treatments.

It would be a false binary to frame this as lifestyle vs cancer treatment, explained Mark Lewis, MD, director of Gastrointestinal Oncology at Intermountain Healthcare in Salt Lake City, Utah. With exercise, for instance, “the key is giving enough chemo to protect against recurrence and eliminate micrometastases but not so much that we cause neuropathy and reduce function and ability to follow the CHALLENGE structured program,” Lewis said.

Exercise and Survival

Colon cancer remains the second-leading cause of cancer death worldwide. Even with surgery and chemotherapy, roughly 30% of patients with stage III and high-risk stage II colon cancer will experience disease recurrence.

“As oncologists, one of the most common questions we get asked by patients is — what else can I do to improve my outcome?” Booth said.

Observational studies published nearly two decades ago hinted that physically active cancer survivors fare better, but no randomized trial has definitively tested whether exercise could alter disease course. That knowledge gap prompted the Canadian Cancer Trials Group to launch the CHALLENGE trial.

Between 2009 and 2023, the phase 3 study enrolled 889 adults (median age, 61 years; 51% women) who had completed surgery and adjuvant chemotherapy for stage III (90%) or high-risk stage II (10%) colon cancer. Most patients were from Canada and Australia and were enrolled 2-6 months after completing chemotherapy.

Half of study participants were randomly allocated to a structured exercise program (n = 445) and half to receive standard health education materials promoting physical activity and healthy eating (control individuals, n = 444).

As part of the structured exercise intervention, patients met with a physical activity consultant twice a month for the first 6 months. These sessions included exercise coaching and supervised exercise. Patients could choose their preferred aerobic exercise and most picked brisk walking.

The consultants gave each patient an “exercise prescription” to hit a specific amount of exercise. The target was an additional 10 metabolic equivalent (MET)–hours of aerobic activity per week — about three to four brisk walks each lasting 45-60 minutes. After 6 months, patients met with their consultants once a month, with additional sessions available for extra support if needed.

Structured exercise led to “substantial and sustained” increases in the amount of exercise participants did, as well as physiologic measures of their fitness, with “highly relevant” improvements in VO₂ max, 6-minute walk test, and patient-reported physical function, underscoring that participants were not only exercising more but also getting fitter, Booth said.

Exercise was associated with a clinically meaningful and statistically significant 28% reduction in the risk for recurrent or new cancer (hazard ratio [HR], 0.72; P = .017), with a 5-year disease free survival rate of 80% in the exercise group and 74% in the control group.

In other words, “for every 16 patients that went on the exercise program, exercise prevented 1 person from recurrent or new cancer” at 5 years, Booth reported.

Overall survival results were “even more impressive,” he said.

At 8 years, 90% of patients in the exercise program were alive vs 83% of those in the control group, which translated to a 37% lower risk for death (HR, 0.63; P = .022).

“For every 14 patients who went on the exercise program, exercise prevented 1 person from dying” at the 8-year mark, Booth noted.

“Notably, this difference in survival was not driven by difference in cardiovascular deaths but by a reduction in the risk of death from colon cancer,” he said.

Besides a slight uptick in musculoskeletal aches, no major safety signals emerged in the exercise group.

It’s important to note that the survival benefit associated with exercise came after patients had received surgery followed by chemotherapy — in other words, exercise did not replace established cancer treatments. It’s also unclear whether initiating an exercise intervention earlier in the treatment trajectory — before surgery or during chemotherapy, instead of after chemotherapy — could further improve cancer outcomes, the authors noted.

Still, “exercise as an intervention is a no brainer and should be implemented broadly,” said ASCO expert Pamela Kunz, MD, with Yale School of Medicine, New Haven, Connecticut.

Marco Gerlinger, MD, with Barts Cancer Institute, London, England, agreed.

“Oncologists can now make a very clear evidence-based recommendation for patients who just completed their chemotherapy for bowel cancer and are fit enough for such an exercise program,” Gerlinger said in a statement from the nonprofit UK Science Media Centre.

Booth noted that knowledge alone will not be sufficient to allow most patients to change their lifestyle and realize the health benefits.

“The policy implementation piece of this is really key, and we need health systems, hospitals, and payers to invest in these behavior support programs so that patients have access to a physical activity consultant and can realize the health benefits,” he said.

“This intervention is empowering and achievable for patients and with much, much lower cost than many of our therapies. It is also sustainable for health systems,” he concluded.

Diet and Survival

Diet can also affect outcomes in patients with colon cancer.

In the same session describing the CHALLENGE results, Sara Char, MD, with Dana-Farber Cancer Institute in Boston, reported findings showing that consuming a diet high in proinflammatory foods was associated with worse overall survival in patients with stage III colon cancer. A proinflammatory diet includes red and processed meats, sugary drinks, and refined grains, while an anti-inflammatory diet focuses on fruits, vegetables, whole grains, fish, and olive oil.

Chronic systemic inflammation has been implicated in both colon cancer development and in its progression, and elevated levels of inflammatory markers in the blood have previously been associated with worse survival outcomes in patients with stage III colon cancer.

Char and colleagues analyzed dietary patterns of a subset of 1625 patients (mean age, 61 years) with resected stage III colon cancer enrolled in the phase 3 CALGB/SWOG 80702 (Alliance) clinical trial, which compared 3 months of adjuvant chemotherapy with 6 months of adjuvant chemotherapy, with or without the anti-inflammatory medication celecoxib.

As part of the trial, participants reported their diet and exercise habits at various timepoints. Their diets were scored using the validated empirical dietary inflammatory pattern (EDIP) tool, which is a weighted sum of 18 food groups — nine proinflammatory and nine anti-inflammatory. A high EDIP score marks a proinflammatory diet, and a low EDIP score indicates a less inflammatory diet.

During median follow-up of nearly 4 years, researchers noted a trend toward worse disease-free survival in patients with high proinflammatory diets (HR, 1.46), but this association was not significant in the multivariable adjusted model (HR, 1.36; P = .22), Char reported.

However, higher intake of proinflammatory foods was associated with significantly worse overall survival.

Patients who consumed the most proinflammatory foods (top 20%) had an 87% higher risk for death compared with those who consumed the least (bottom 20%; HR, 1.87). The median overall survival in the highest quintile was 7.7 years and was not reached in the lowest quintile.

Combine Exercise and Diet for Best Results

To examine the joint effect of physical activity and diet on overall survival, patients were divided into higher and lower levels of physical activity using a cut-off of 9 MET hours per week, which roughly correlates to 30 minutes of vigorous walking five days a week with a little bit of light yoga, Char explained.

In this analysis, patients with less proinflammatory diets and higher physical activity levels had the best overall survival outcomes, with a 63% lower risk for death compared with peers who consumed more pro-inflammatory diets and exercised less (HR, 0.37; P < .0001).

Daily celecoxib use and low-dose aspirin use (< 100 mg/d) did not affect the association between inflammatory diet and survival.

Char cautioned, that while the EDIP tool is useful to measure the inflammatory potential of a diet, “this is not a dietary recommendation, and we need further studies to be able to tailor our findings into dietary recommendations that can be provided to patients at the bedside.”

Gralow said this “early but promising observational study suggests a powerful synergy: Patients with stage III colon cancer who embraced anti-inflammatory foods and exercised regularly showed the best overall survival compared to those with inflammatory diets and limited exercise.”

The CHALLENGE trial was funded by the Canadian Cancer Society, the National Health and Medical Research Council, Cancer Research UK, and the University of Sydney Cancer Research Fund. Booth had no disclosures. The diet study was funded by the National Institutes of Health, Pfizer, and the Project P Fund. Char disclosed an advisory/consultant role with Goodpath. Kunz, Gralow and Campbell had no relevant disclosures.

A version of this article first appeared on Medscape.com.

Can exercise “therapy” and diet improve survival in patients with colon cancer? It appears so, according to two pivotal studies presented at American Society of Clinical Oncology (ASCO) 2025 annual meeting.

In the CHALLENGE trial, a structured exercise program after surgery and adjuvant chemotherapy cut the risk for colon cancer recurrence in patients with stage III and high-risk stage II disease by more than one quarter and the risk for death by more than one third.

“The magnitude of benefit with exercise is substantial. In fact, it is comparable, and in some cases exceeds the magnitude of benefit of many of our very good standard medical therapies in oncology,” study presenter Christopher Booth, MD, with Queen’s University, Kingston, Ontario, Canada, told attendees.

Results of the study were published online in The New England Journal of Medicine to coincide with the presentation at the meeting.

The findings are “nothing short of a major milestone,” said study discussant Peter Campbell, PhD, with Montefiore Einstein Comprehensive Cancer Center, Bronx, New York.

The other study showed that eating a less inflammatory diet may reduce the risk for death in patients with colon cancer, with the greatest benefits seen in those who embraced anti-inflammatory foods and exercised regularly.

“Putting these two abstracts into perspective, we as physicians need to be essentially prescribing healthy diet and exercise. The combination of the two are synergistic,” Julie Gralow, MD, ASCO chief medical officer and executive vice president, told attendees.

Despite the benefits of these lifestyle changes, exercise and diet are meant to supplement, not replace, established colon cancer treatments.

It would be a false binary to frame this as lifestyle vs cancer treatment, explained Mark Lewis, MD, director of Gastrointestinal Oncology at Intermountain Healthcare in Salt Lake City, Utah. With exercise, for instance, “the key is giving enough chemo to protect against recurrence and eliminate micrometastases but not so much that we cause neuropathy and reduce function and ability to follow the CHALLENGE structured program,” Lewis said.

Exercise and Survival

Colon cancer remains the second-leading cause of cancer death worldwide. Even with surgery and chemotherapy, roughly 30% of patients with stage III and high-risk stage II colon cancer will experience disease recurrence.

“As oncologists, one of the most common questions we get asked by patients is — what else can I do to improve my outcome?” Booth said.

Observational studies published nearly two decades ago hinted that physically active cancer survivors fare better, but no randomized trial has definitively tested whether exercise could alter disease course. That knowledge gap prompted the Canadian Cancer Trials Group to launch the CHALLENGE trial.

Between 2009 and 2023, the phase 3 study enrolled 889 adults (median age, 61 years; 51% women) who had completed surgery and adjuvant chemotherapy for stage III (90%) or high-risk stage II (10%) colon cancer. Most patients were from Canada and Australia and were enrolled 2-6 months after completing chemotherapy.

Half of study participants were randomly allocated to a structured exercise program (n = 445) and half to receive standard health education materials promoting physical activity and healthy eating (control individuals, n = 444).

As part of the structured exercise intervention, patients met with a physical activity consultant twice a month for the first 6 months. These sessions included exercise coaching and supervised exercise. Patients could choose their preferred aerobic exercise and most picked brisk walking.

The consultants gave each patient an “exercise prescription” to hit a specific amount of exercise. The target was an additional 10 metabolic equivalent (MET)–hours of aerobic activity per week — about three to four brisk walks each lasting 45-60 minutes. After 6 months, patients met with their consultants once a month, with additional sessions available for extra support if needed.

Structured exercise led to “substantial and sustained” increases in the amount of exercise participants did, as well as physiologic measures of their fitness, with “highly relevant” improvements in VO₂ max, 6-minute walk test, and patient-reported physical function, underscoring that participants were not only exercising more but also getting fitter, Booth said.

Exercise was associated with a clinically meaningful and statistically significant 28% reduction in the risk for recurrent or new cancer (hazard ratio [HR], 0.72; P = .017), with a 5-year disease free survival rate of 80% in the exercise group and 74% in the control group.

In other words, “for every 16 patients that went on the exercise program, exercise prevented 1 person from recurrent or new cancer” at 5 years, Booth reported.

Overall survival results were “even more impressive,” he said.

At 8 years, 90% of patients in the exercise program were alive vs 83% of those in the control group, which translated to a 37% lower risk for death (HR, 0.63; P = .022).

“For every 14 patients who went on the exercise program, exercise prevented 1 person from dying” at the 8-year mark, Booth noted.

“Notably, this difference in survival was not driven by difference in cardiovascular deaths but by a reduction in the risk of death from colon cancer,” he said.

Besides a slight uptick in musculoskeletal aches, no major safety signals emerged in the exercise group.

It’s important to note that the survival benefit associated with exercise came after patients had received surgery followed by chemotherapy — in other words, exercise did not replace established cancer treatments. It’s also unclear whether initiating an exercise intervention earlier in the treatment trajectory — before surgery or during chemotherapy, instead of after chemotherapy — could further improve cancer outcomes, the authors noted.

Still, “exercise as an intervention is a no brainer and should be implemented broadly,” said ASCO expert Pamela Kunz, MD, with Yale School of Medicine, New Haven, Connecticut.

Marco Gerlinger, MD, with Barts Cancer Institute, London, England, agreed.

“Oncologists can now make a very clear evidence-based recommendation for patients who just completed their chemotherapy for bowel cancer and are fit enough for such an exercise program,” Gerlinger said in a statement from the nonprofit UK Science Media Centre.

Booth noted that knowledge alone will not be sufficient to allow most patients to change their lifestyle and realize the health benefits.

“The policy implementation piece of this is really key, and we need health systems, hospitals, and payers to invest in these behavior support programs so that patients have access to a physical activity consultant and can realize the health benefits,” he said.

“This intervention is empowering and achievable for patients and with much, much lower cost than many of our therapies. It is also sustainable for health systems,” he concluded.

Diet and Survival

Diet can also affect outcomes in patients with colon cancer.

In the same session describing the CHALLENGE results, Sara Char, MD, with Dana-Farber Cancer Institute in Boston, reported findings showing that consuming a diet high in proinflammatory foods was associated with worse overall survival in patients with stage III colon cancer. A proinflammatory diet includes red and processed meats, sugary drinks, and refined grains, while an anti-inflammatory diet focuses on fruits, vegetables, whole grains, fish, and olive oil.

Chronic systemic inflammation has been implicated in both colon cancer development and in its progression, and elevated levels of inflammatory markers in the blood have previously been associated with worse survival outcomes in patients with stage III colon cancer.

Char and colleagues analyzed dietary patterns of a subset of 1625 patients (mean age, 61 years) with resected stage III colon cancer enrolled in the phase 3 CALGB/SWOG 80702 (Alliance) clinical trial, which compared 3 months of adjuvant chemotherapy with 6 months of adjuvant chemotherapy, with or without the anti-inflammatory medication celecoxib.

As part of the trial, participants reported their diet and exercise habits at various timepoints. Their diets were scored using the validated empirical dietary inflammatory pattern (EDIP) tool, which is a weighted sum of 18 food groups — nine proinflammatory and nine anti-inflammatory. A high EDIP score marks a proinflammatory diet, and a low EDIP score indicates a less inflammatory diet.

During median follow-up of nearly 4 years, researchers noted a trend toward worse disease-free survival in patients with high proinflammatory diets (HR, 1.46), but this association was not significant in the multivariable adjusted model (HR, 1.36; P = .22), Char reported.

However, higher intake of proinflammatory foods was associated with significantly worse overall survival.

Patients who consumed the most proinflammatory foods (top 20%) had an 87% higher risk for death compared with those who consumed the least (bottom 20%; HR, 1.87). The median overall survival in the highest quintile was 7.7 years and was not reached in the lowest quintile.

Combine Exercise and Diet for Best Results

To examine the joint effect of physical activity and diet on overall survival, patients were divided into higher and lower levels of physical activity using a cut-off of 9 MET hours per week, which roughly correlates to 30 minutes of vigorous walking five days a week with a little bit of light yoga, Char explained.

In this analysis, patients with less proinflammatory diets and higher physical activity levels had the best overall survival outcomes, with a 63% lower risk for death compared with peers who consumed more pro-inflammatory diets and exercised less (HR, 0.37; P < .0001).

Daily celecoxib use and low-dose aspirin use (< 100 mg/d) did not affect the association between inflammatory diet and survival.

Char cautioned, that while the EDIP tool is useful to measure the inflammatory potential of a diet, “this is not a dietary recommendation, and we need further studies to be able to tailor our findings into dietary recommendations that can be provided to patients at the bedside.”

Gralow said this “early but promising observational study suggests a powerful synergy: Patients with stage III colon cancer who embraced anti-inflammatory foods and exercised regularly showed the best overall survival compared to those with inflammatory diets and limited exercise.”

The CHALLENGE trial was funded by the Canadian Cancer Society, the National Health and Medical Research Council, Cancer Research UK, and the University of Sydney Cancer Research Fund. Booth had no disclosures. The diet study was funded by the National Institutes of Health, Pfizer, and the Project P Fund. Char disclosed an advisory/consultant role with Goodpath. Kunz, Gralow and Campbell had no relevant disclosures.

A version of this article first appeared on Medscape.com.

Can exercise “therapy” and diet improve survival in patients with colon cancer? It appears so, according to two pivotal studies presented at American Society of Clinical Oncology (ASCO) 2025 annual meeting.

In the CHALLENGE trial, a structured exercise program after surgery and adjuvant chemotherapy cut the risk for colon cancer recurrence in patients with stage III and high-risk stage II disease by more than one quarter and the risk for death by more than one third.

“The magnitude of benefit with exercise is substantial. In fact, it is comparable, and in some cases exceeds the magnitude of benefit of many of our very good standard medical therapies in oncology,” study presenter Christopher Booth, MD, with Queen’s University, Kingston, Ontario, Canada, told attendees.

Results of the study were published online in The New England Journal of Medicine to coincide with the presentation at the meeting.

The findings are “nothing short of a major milestone,” said study discussant Peter Campbell, PhD, with Montefiore Einstein Comprehensive Cancer Center, Bronx, New York.

The other study showed that eating a less inflammatory diet may reduce the risk for death in patients with colon cancer, with the greatest benefits seen in those who embraced anti-inflammatory foods and exercised regularly.

“Putting these two abstracts into perspective, we as physicians need to be essentially prescribing healthy diet and exercise. The combination of the two are synergistic,” Julie Gralow, MD, ASCO chief medical officer and executive vice president, told attendees.

Despite the benefits of these lifestyle changes, exercise and diet are meant to supplement, not replace, established colon cancer treatments.

It would be a false binary to frame this as lifestyle vs cancer treatment, explained Mark Lewis, MD, director of Gastrointestinal Oncology at Intermountain Healthcare in Salt Lake City, Utah. With exercise, for instance, “the key is giving enough chemo to protect against recurrence and eliminate micrometastases but not so much that we cause neuropathy and reduce function and ability to follow the CHALLENGE structured program,” Lewis said.

Exercise and Survival

Colon cancer remains the second-leading cause of cancer death worldwide. Even with surgery and chemotherapy, roughly 30% of patients with stage III and high-risk stage II colon cancer will experience disease recurrence.

“As oncologists, one of the most common questions we get asked by patients is — what else can I do to improve my outcome?” Booth said.

Observational studies published nearly two decades ago hinted that physically active cancer survivors fare better, but no randomized trial has definitively tested whether exercise could alter disease course. That knowledge gap prompted the Canadian Cancer Trials Group to launch the CHALLENGE trial.

Between 2009 and 2023, the phase 3 study enrolled 889 adults (median age, 61 years; 51% women) who had completed surgery and adjuvant chemotherapy for stage III (90%) or high-risk stage II (10%) colon cancer. Most patients were from Canada and Australia and were enrolled 2-6 months after completing chemotherapy.

Half of study participants were randomly allocated to a structured exercise program (n = 445) and half to receive standard health education materials promoting physical activity and healthy eating (control individuals, n = 444).

As part of the structured exercise intervention, patients met with a physical activity consultant twice a month for the first 6 months. These sessions included exercise coaching and supervised exercise. Patients could choose their preferred aerobic exercise and most picked brisk walking.

The consultants gave each patient an “exercise prescription” to hit a specific amount of exercise. The target was an additional 10 metabolic equivalent (MET)–hours of aerobic activity per week — about three to four brisk walks each lasting 45-60 minutes. After 6 months, patients met with their consultants once a month, with additional sessions available for extra support if needed.

Structured exercise led to “substantial and sustained” increases in the amount of exercise participants did, as well as physiologic measures of their fitness, with “highly relevant” improvements in VO₂ max, 6-minute walk test, and patient-reported physical function, underscoring that participants were not only exercising more but also getting fitter, Booth said.

Exercise was associated with a clinically meaningful and statistically significant 28% reduction in the risk for recurrent or new cancer (hazard ratio [HR], 0.72; P = .017), with a 5-year disease free survival rate of 80% in the exercise group and 74% in the control group.

In other words, “for every 16 patients that went on the exercise program, exercise prevented 1 person from recurrent or new cancer” at 5 years, Booth reported.

Overall survival results were “even more impressive,” he said.

At 8 years, 90% of patients in the exercise program were alive vs 83% of those in the control group, which translated to a 37% lower risk for death (HR, 0.63; P = .022).

“For every 14 patients who went on the exercise program, exercise prevented 1 person from dying” at the 8-year mark, Booth noted.

“Notably, this difference in survival was not driven by difference in cardiovascular deaths but by a reduction in the risk of death from colon cancer,” he said.

Besides a slight uptick in musculoskeletal aches, no major safety signals emerged in the exercise group.

It’s important to note that the survival benefit associated with exercise came after patients had received surgery followed by chemotherapy — in other words, exercise did not replace established cancer treatments. It’s also unclear whether initiating an exercise intervention earlier in the treatment trajectory — before surgery or during chemotherapy, instead of after chemotherapy — could further improve cancer outcomes, the authors noted.

Still, “exercise as an intervention is a no brainer and should be implemented broadly,” said ASCO expert Pamela Kunz, MD, with Yale School of Medicine, New Haven, Connecticut.

Marco Gerlinger, MD, with Barts Cancer Institute, London, England, agreed.

“Oncologists can now make a very clear evidence-based recommendation for patients who just completed their chemotherapy for bowel cancer and are fit enough for such an exercise program,” Gerlinger said in a statement from the nonprofit UK Science Media Centre.

Booth noted that knowledge alone will not be sufficient to allow most patients to change their lifestyle and realize the health benefits.

“The policy implementation piece of this is really key, and we need health systems, hospitals, and payers to invest in these behavior support programs so that patients have access to a physical activity consultant and can realize the health benefits,” he said.

“This intervention is empowering and achievable for patients and with much, much lower cost than many of our therapies. It is also sustainable for health systems,” he concluded.

Diet and Survival

Diet can also affect outcomes in patients with colon cancer.

In the same session describing the CHALLENGE results, Sara Char, MD, with Dana-Farber Cancer Institute in Boston, reported findings showing that consuming a diet high in proinflammatory foods was associated with worse overall survival in patients with stage III colon cancer. A proinflammatory diet includes red and processed meats, sugary drinks, and refined grains, while an anti-inflammatory diet focuses on fruits, vegetables, whole grains, fish, and olive oil.

Chronic systemic inflammation has been implicated in both colon cancer development and in its progression, and elevated levels of inflammatory markers in the blood have previously been associated with worse survival outcomes in patients with stage III colon cancer.

Char and colleagues analyzed dietary patterns of a subset of 1625 patients (mean age, 61 years) with resected stage III colon cancer enrolled in the phase 3 CALGB/SWOG 80702 (Alliance) clinical trial, which compared 3 months of adjuvant chemotherapy with 6 months of adjuvant chemotherapy, with or without the anti-inflammatory medication celecoxib.

As part of the trial, participants reported their diet and exercise habits at various timepoints. Their diets were scored using the validated empirical dietary inflammatory pattern (EDIP) tool, which is a weighted sum of 18 food groups — nine proinflammatory and nine anti-inflammatory. A high EDIP score marks a proinflammatory diet, and a low EDIP score indicates a less inflammatory diet.

During median follow-up of nearly 4 years, researchers noted a trend toward worse disease-free survival in patients with high proinflammatory diets (HR, 1.46), but this association was not significant in the multivariable adjusted model (HR, 1.36; P = .22), Char reported.

However, higher intake of proinflammatory foods was associated with significantly worse overall survival.

Patients who consumed the most proinflammatory foods (top 20%) had an 87% higher risk for death compared with those who consumed the least (bottom 20%; HR, 1.87). The median overall survival in the highest quintile was 7.7 years and was not reached in the lowest quintile.

Combine Exercise and Diet for Best Results

To examine the joint effect of physical activity and diet on overall survival, patients were divided into higher and lower levels of physical activity using a cut-off of 9 MET hours per week, which roughly correlates to 30 minutes of vigorous walking five days a week with a little bit of light yoga, Char explained.

In this analysis, patients with less proinflammatory diets and higher physical activity levels had the best overall survival outcomes, with a 63% lower risk for death compared with peers who consumed more pro-inflammatory diets and exercised less (HR, 0.37; P < .0001).

Daily celecoxib use and low-dose aspirin use (< 100 mg/d) did not affect the association between inflammatory diet and survival.

Char cautioned, that while the EDIP tool is useful to measure the inflammatory potential of a diet, “this is not a dietary recommendation, and we need further studies to be able to tailor our findings into dietary recommendations that can be provided to patients at the bedside.”

Gralow said this “early but promising observational study suggests a powerful synergy: Patients with stage III colon cancer who embraced anti-inflammatory foods and exercised regularly showed the best overall survival compared to those with inflammatory diets and limited exercise.”

The CHALLENGE trial was funded by the Canadian Cancer Society, the National Health and Medical Research Council, Cancer Research UK, and the University of Sydney Cancer Research Fund. Booth had no disclosures. The diet study was funded by the National Institutes of Health, Pfizer, and the Project P Fund. Char disclosed an advisory/consultant role with Goodpath. Kunz, Gralow and Campbell had no relevant disclosures.

A version of this article first appeared on Medscape.com.

The prevalence of eosinophilic esophagitis (EoE) has increased fivefold in the United States since 2009, now affecting about 1 in 700 people and totaling $1.32 billion in annual healthcare costs, according to recent research.

Although EoE has been considered a rare disease, the chronic condition is becoming more common, and healthcare providers should expect to encounter EoE in clinical settings, the study authors wrote.

“Our last assessment of the prevalence and burden of EoE was more than 10 years ago, and we had a strong suspicion we would continue to see increased numbers of patients with EoE and an increasing cost burden related to the condition in the United States,” said senior author Evan S. Dellon, MD, MPH, AGAF, professor of gastroenterology and hepatology and director of the Center for Esophageal Diseases and Swallowing at the University of North Carolina School of Medicine, Chapel Hill, North Carolina.

“EoE is becoming more common,” Dellon said. “Healthcare providers should expect to see EoE in their practices, including in the primary care setting, emergency departments, allergy practices, GI [gastrointestinal] practices, ENT clinics, and endoscopy suites.”

The study was published in Clinical Gastroenterology and Hepatology.

Estimating EoE Prevalence

Dellon and colleagues analyzed the Merative MarketScan Commercial Claims and Encounters and Medicare Fee-for-Service databases to calculate the annual prevalence of EoE, as well as age- and sex-stratified estimates standardized to the US population. They also calculated healthcare utilization, including medications and endoscopic procedures, to estimate annual EoE-associated costs. Since the EoE billing code was introduced in 2008, the analysis included 2009-2022 MarketScan and 2009-2017 Medicare data.

In the MarketScan database, the research team identified 20,435 EoE cases in 2022, with a mean age of 38 years, 16% younger than 18 years, 62% men, and 41% with a comorbid allergic disease code. The most common symptoms and diagnoses were dysphagia (39%), abdominal pain or dyspepsia (24%), and esophageal stricture (19%). Over time, patients also had previous codes for comorbid allergic diseases (64%), dysphagia (62%), or esophageal stricture (32%).

In the Medicare database, the research team identified 1913 EoE cases in 2017, with a mean age of 73 years, 47% men, 90% non-Hispanic White, and 36% with a comorbid allergic disease. The most common symptoms and diagnoses were dysphagia (49%), abdominal pain or dyspepsia (35%), and esophageal stricture (30%). Over time, patients also had codes for comorbid allergic diseases (64%), dysphagia (65%), or esophageal stricture (42%).

The database numbers translated to EoE prevalences of about 163 cases per 100,000 people in MarketScan in 2022 and 64 cases per 100,000 people in Medicare in 2017. Since 2009, there has been a fivefold increase in prevalence in both databases.

In MarketScan, the prevalence was higher among men than among women, at 204 vs 122 cases per 100,000 people. For both sexes, peak prevalence occurred between ages 40 and 44.

In Medicare, prevalence was also higher among men than among women, at 79 vs 55 cases per 100,000 people. Peak prevalence occurred between ages 65 and 69.

Standardized to the US population, EoE prevalence was 142.5 cases per 100,000 people, extrapolating to 472,380 cases. The overall prevalence was approximately 1 in 700, with rates of 1 in 617 for those younger than 65 years and 1 in 1562 for those aged ≥ 65 years.

“The rapidly increasing prevalence year over year for the entire timeframe of the study was surprising, as were our estimates of the total number of EoE patients in the US, which suggests that EoE is no longer a rare disease and is now seen in about 1 in 700 people,” Dellon said. “This almost triples our prior estimates of 1 in 2000 from 10 years ago, with all trends suggesting that the prevalence will continue to increase.”

 

Calculating EoE Costs

In terms of procedures, endoscopy with dilation or biopsy was used in about 60%-70% of patients with EoE in both MarketScan and Medicare during the years analyzed. In addition, upper endoscopy with biopsy was coded in 80%-90% of patients, guidewire-based dilation in 11%-17% of patients, and balloon-based dilation in 13%-20% of patients.

In terms of prescription medications, proton pump inhibitors (41%) and topical steroids (26%) were the most common in MarketScan in 2022, as well as in Medicare in 2017, at 32% and 9%, respectively.

When looking at costs by age and sex, the male cohort with the highest costs was aged 10-14 years, estimated at $106.7 million. Among the female cohort, the highest costs were associated with ages 15-19, estimated at $46.5 million.

Overall, total EoE-associated healthcare costs were estimated to be $1.04 billion in 2017, and when adjusted for inflation, the costs were estimated at $1.32 billion in 2024. This is likely an underestimate, the authors wrote, given that EoE prevalence has likely increased for ages 65 or older since 2017 and for all ages since 2022.

“Researching the prevalence and costs is essential to improving patient care by highlighting the growing burden of this recently recognized and growing chronic disease, guiding policy and insurer decisions, and advocating for better access to effective treatments and support for patients,” said Joy Chang, MD, assistant professor of medicine in the Division of Gastroenterology, University of Michigan, Ann Arbor, Michigan.Chang, who wasn’t involved with this study, specializes in eosinophilic GI diseases and researches patient-physician preferences and decision-making in EoE care.

“Clinicians should remain vigilant for symptoms, utilize guideline-based diagnostic approaches, and consider both medical and dietary treatment strategies to optimize patient outcomes and reduce long-term costs,” she said. “Increased awareness and timely intervention can help mitigate the growing impact of this chronic condition.”

The study was supported by a National Institutes of Health grant and used resources from the University of North Carolina Center for Gastrointestinal Biology and Disease. Dellon reported receiving research funding from and having consultant roles with numerous pharmaceutical companies and organizations. Chang reported having no relevant disclosures.

A version of this article appeared on Medscape.com.

The prevalence of eosinophilic esophagitis (EoE) has increased fivefold in the United States since 2009, now affecting about 1 in 700 people and totaling $1.32 billion in annual healthcare costs, according to recent research.

Although EoE has been considered a rare disease, the chronic condition is becoming more common, and healthcare providers should expect to encounter EoE in clinical settings, the study authors wrote.

“Our last assessment of the prevalence and burden of EoE was more than 10 years ago, and we had a strong suspicion we would continue to see increased numbers of patients with EoE and an increasing cost burden related to the condition in the United States,” said senior author Evan S. Dellon, MD, MPH, AGAF, professor of gastroenterology and hepatology and director of the Center for Esophageal Diseases and Swallowing at the University of North Carolina School of Medicine, Chapel Hill, North Carolina.

“EoE is becoming more common,” Dellon said. “Healthcare providers should expect to see EoE in their practices, including in the primary care setting, emergency departments, allergy practices, GI [gastrointestinal] practices, ENT clinics, and endoscopy suites.”

The study was published in Clinical Gastroenterology and Hepatology.

Estimating EoE Prevalence

Dellon and colleagues analyzed the Merative MarketScan Commercial Claims and Encounters and Medicare Fee-for-Service databases to calculate the annual prevalence of EoE, as well as age- and sex-stratified estimates standardized to the US population. They also calculated healthcare utilization, including medications and endoscopic procedures, to estimate annual EoE-associated costs. Since the EoE billing code was introduced in 2008, the analysis included 2009-2022 MarketScan and 2009-2017 Medicare data.

In the MarketScan database, the research team identified 20,435 EoE cases in 2022, with a mean age of 38 years, 16% younger than 18 years, 62% men, and 41% with a comorbid allergic disease code. The most common symptoms and diagnoses were dysphagia (39%), abdominal pain or dyspepsia (24%), and esophageal stricture (19%). Over time, patients also had previous codes for comorbid allergic diseases (64%), dysphagia (62%), or esophageal stricture (32%).

In the Medicare database, the research team identified 1913 EoE cases in 2017, with a mean age of 73 years, 47% men, 90% non-Hispanic White, and 36% with a comorbid allergic disease. The most common symptoms and diagnoses were dysphagia (49%), abdominal pain or dyspepsia (35%), and esophageal stricture (30%). Over time, patients also had codes for comorbid allergic diseases (64%), dysphagia (65%), or esophageal stricture (42%).

The database numbers translated to EoE prevalences of about 163 cases per 100,000 people in MarketScan in 2022 and 64 cases per 100,000 people in Medicare in 2017. Since 2009, there has been a fivefold increase in prevalence in both databases.

In MarketScan, the prevalence was higher among men than among women, at 204 vs 122 cases per 100,000 people. For both sexes, peak prevalence occurred between ages 40 and 44.

In Medicare, prevalence was also higher among men than among women, at 79 vs 55 cases per 100,000 people. Peak prevalence occurred between ages 65 and 69.

Standardized to the US population, EoE prevalence was 142.5 cases per 100,000 people, extrapolating to 472,380 cases. The overall prevalence was approximately 1 in 700, with rates of 1 in 617 for those younger than 65 years and 1 in 1562 for those aged ≥ 65 years.

“The rapidly increasing prevalence year over year for the entire timeframe of the study was surprising, as were our estimates of the total number of EoE patients in the US, which suggests that EoE is no longer a rare disease and is now seen in about 1 in 700 people,” Dellon said. “This almost triples our prior estimates of 1 in 2000 from 10 years ago, with all trends suggesting that the prevalence will continue to increase.”

 

Calculating EoE Costs

In terms of procedures, endoscopy with dilation or biopsy was used in about 60%-70% of patients with EoE in both MarketScan and Medicare during the years analyzed. In addition, upper endoscopy with biopsy was coded in 80%-90% of patients, guidewire-based dilation in 11%-17% of patients, and balloon-based dilation in 13%-20% of patients.

In terms of prescription medications, proton pump inhibitors (41%) and topical steroids (26%) were the most common in MarketScan in 2022, as well as in Medicare in 2017, at 32% and 9%, respectively.

When looking at costs by age and sex, the male cohort with the highest costs was aged 10-14 years, estimated at $106.7 million. Among the female cohort, the highest costs were associated with ages 15-19, estimated at $46.5 million.

Overall, total EoE-associated healthcare costs were estimated to be $1.04 billion in 2017, and when adjusted for inflation, the costs were estimated at $1.32 billion in 2024. This is likely an underestimate, the authors wrote, given that EoE prevalence has likely increased for ages 65 or older since 2017 and for all ages since 2022.

“Researching the prevalence and costs is essential to improving patient care by highlighting the growing burden of this recently recognized and growing chronic disease, guiding policy and insurer decisions, and advocating for better access to effective treatments and support for patients,” said Joy Chang, MD, assistant professor of medicine in the Division of Gastroenterology, University of Michigan, Ann Arbor, Michigan.Chang, who wasn’t involved with this study, specializes in eosinophilic GI diseases and researches patient-physician preferences and decision-making in EoE care.

“Clinicians should remain vigilant for symptoms, utilize guideline-based diagnostic approaches, and consider both medical and dietary treatment strategies to optimize patient outcomes and reduce long-term costs,” she said. “Increased awareness and timely intervention can help mitigate the growing impact of this chronic condition.”

The study was supported by a National Institutes of Health grant and used resources from the University of North Carolina Center for Gastrointestinal Biology and Disease. Dellon reported receiving research funding from and having consultant roles with numerous pharmaceutical companies and organizations. Chang reported having no relevant disclosures.

A version of this article appeared on Medscape.com.

The prevalence of eosinophilic esophagitis (EoE) has increased fivefold in the United States since 2009, now affecting about 1 in 700 people and totaling $1.32 billion in annual healthcare costs, according to recent research.

Although EoE has been considered a rare disease, the chronic condition is becoming more common, and healthcare providers should expect to encounter EoE in clinical settings, the study authors wrote.

“Our last assessment of the prevalence and burden of EoE was more than 10 years ago, and we had a strong suspicion we would continue to see increased numbers of patients with EoE and an increasing cost burden related to the condition in the United States,” said senior author Evan S. Dellon, MD, MPH, AGAF, professor of gastroenterology and hepatology and director of the Center for Esophageal Diseases and Swallowing at the University of North Carolina School of Medicine, Chapel Hill, North Carolina.

“EoE is becoming more common,” Dellon said. “Healthcare providers should expect to see EoE in their practices, including in the primary care setting, emergency departments, allergy practices, GI [gastrointestinal] practices, ENT clinics, and endoscopy suites.”

The study was published in Clinical Gastroenterology and Hepatology.

Estimating EoE Prevalence

Dellon and colleagues analyzed the Merative MarketScan Commercial Claims and Encounters and Medicare Fee-for-Service databases to calculate the annual prevalence of EoE, as well as age- and sex-stratified estimates standardized to the US population. They also calculated healthcare utilization, including medications and endoscopic procedures, to estimate annual EoE-associated costs. Since the EoE billing code was introduced in 2008, the analysis included 2009-2022 MarketScan and 2009-2017 Medicare data.

In the MarketScan database, the research team identified 20,435 EoE cases in 2022, with a mean age of 38 years, 16% younger than 18 years, 62% men, and 41% with a comorbid allergic disease code. The most common symptoms and diagnoses were dysphagia (39%), abdominal pain or dyspepsia (24%), and esophageal stricture (19%). Over time, patients also had previous codes for comorbid allergic diseases (64%), dysphagia (62%), or esophageal stricture (32%).

In the Medicare database, the research team identified 1913 EoE cases in 2017, with a mean age of 73 years, 47% men, 90% non-Hispanic White, and 36% with a comorbid allergic disease. The most common symptoms and diagnoses were dysphagia (49%), abdominal pain or dyspepsia (35%), and esophageal stricture (30%). Over time, patients also had codes for comorbid allergic diseases (64%), dysphagia (65%), or esophageal stricture (42%).

The database numbers translated to EoE prevalences of about 163 cases per 100,000 people in MarketScan in 2022 and 64 cases per 100,000 people in Medicare in 2017. Since 2009, there has been a fivefold increase in prevalence in both databases.

In MarketScan, the prevalence was higher among men than among women, at 204 vs 122 cases per 100,000 people. For both sexes, peak prevalence occurred between ages 40 and 44.

In Medicare, prevalence was also higher among men than among women, at 79 vs 55 cases per 100,000 people. Peak prevalence occurred between ages 65 and 69.

Standardized to the US population, EoE prevalence was 142.5 cases per 100,000 people, extrapolating to 472,380 cases. The overall prevalence was approximately 1 in 700, with rates of 1 in 617 for those younger than 65 years and 1 in 1562 for those aged ≥ 65 years.

“The rapidly increasing prevalence year over year for the entire timeframe of the study was surprising, as were our estimates of the total number of EoE patients in the US, which suggests that EoE is no longer a rare disease and is now seen in about 1 in 700 people,” Dellon said. “This almost triples our prior estimates of 1 in 2000 from 10 years ago, with all trends suggesting that the prevalence will continue to increase.”

 

Calculating EoE Costs

In terms of procedures, endoscopy with dilation or biopsy was used in about 60%-70% of patients with EoE in both MarketScan and Medicare during the years analyzed. In addition, upper endoscopy with biopsy was coded in 80%-90% of patients, guidewire-based dilation in 11%-17% of patients, and balloon-based dilation in 13%-20% of patients.

In terms of prescription medications, proton pump inhibitors (41%) and topical steroids (26%) were the most common in MarketScan in 2022, as well as in Medicare in 2017, at 32% and 9%, respectively.

When looking at costs by age and sex, the male cohort with the highest costs was aged 10-14 years, estimated at $106.7 million. Among the female cohort, the highest costs were associated with ages 15-19, estimated at $46.5 million.

Overall, total EoE-associated healthcare costs were estimated to be $1.04 billion in 2017, and when adjusted for inflation, the costs were estimated at $1.32 billion in 2024. This is likely an underestimate, the authors wrote, given that EoE prevalence has likely increased for ages 65 or older since 2017 and for all ages since 2022.

“Researching the prevalence and costs is essential to improving patient care by highlighting the growing burden of this recently recognized and growing chronic disease, guiding policy and insurer decisions, and advocating for better access to effective treatments and support for patients,” said Joy Chang, MD, assistant professor of medicine in the Division of Gastroenterology, University of Michigan, Ann Arbor, Michigan.Chang, who wasn’t involved with this study, specializes in eosinophilic GI diseases and researches patient-physician preferences and decision-making in EoE care.

“Clinicians should remain vigilant for symptoms, utilize guideline-based diagnostic approaches, and consider both medical and dietary treatment strategies to optimize patient outcomes and reduce long-term costs,” she said. “Increased awareness and timely intervention can help mitigate the growing impact of this chronic condition.”

The study was supported by a National Institutes of Health grant and used resources from the University of North Carolina Center for Gastrointestinal Biology and Disease. Dellon reported receiving research funding from and having consultant roles with numerous pharmaceutical companies and organizations. Chang reported having no relevant disclosures.

A version of this article appeared on Medscape.com.

SAN DIEGO — A novel generative artificial intelligence (AI) framework known as trajectory flow matching (TFM) can predict the need for red blood cell transfusion and mortality risk in intensive care unit (ICU) patients with acute gastrointestinal (GI) bleeding, researchers reported at Digestive Disease Week^® (DDW) 2025.

Acute GI bleeding is the most common cause of digestive disease–related hospitalization, with an estimated 500,000 hospital admissions annually. It’s known that predicting the need for red blood cell transfusion in the first 24 hours may improve resuscitation and decrease both morbidity and mortality.

However, an existing clinical score known as the Rockall Score does not perform well for predicting mortality, Xi (Nicole) Zhang, an MD-PhD student at McGill University, Montreal, Quebec, Canada, told attendees at DDW. With an area under the curve of 0.65-0.75, better prediction is needed, said Zhang, whose coresearchers included Dennis Shung, MD, MHS, PhD, director of Applied Artificial Intelligence at Yale University School of Medicine, New Haven, Connecticut.

“We’d like to predict multiple outcomes in addition to mortality,” said Zhang, who is also a student at the Mila-Quebec Artificial Intelligence Institute.

As a result, the researchers turned to the TFM approach, applying it to ICU patients with acute GI bleeding to predict both the need for transfusion and in-hospital mortality risk. The all-cause mortality rate is up to 11%, according to a 2020 study by James Y. W. Lau, MD, and colleagues. The rebleeding rate of nonvariceal upper GI bleeds is up to 10.4%. Zhang said the rebleeding rate for variceal upper gastrointestinal bleeding is up to 65%.

The AI method the researchers used outperformed a standard deep learning model at predicting the need for transfusion and estimating mortality risk.

 

Defining the AI Framework

“Probabilistic flow matching is a class of generative artificial intelligence that learns how a simple distribution becomes a more complex distribution with ordinary differential equations,” Zhang told GI & Hepatology News. “For example, if you had a few lines and shapes you could learn how it could become a detailed portrait of a face. In our case, we start with a few blood pressure and heart rate measurements and learn the pattern of blood pressures and heart rates over time, particularly if they reflect clinical deterioration with hemodynamic instability.”

Another way to think about the underlying algorithm, Zhang said, is to think about a river with boats where the river flow determines where the boats end up. “We are trying to direct the boat to the correct dock by adjusting the flow of water in the canal. In this case we are mapping the distribution with the first few data points to the distribution with the entire patient trajectory.”

The information gained, she said, could be helpful in timing endoscopic evaluation or allocating red blood cell products for emergent transfusion.

 

Study Details

The researchers evaluated a cohort of 2602 patients admitted to the ICU, identified from the publicly available MIMIC-III database. They divided the patients into a training set of 2342 patients and an internal validation set of 260 patients. Input variables were severe liver disease comorbidity, administration of vasopressor medications, mean arterial blood pressure, and heart rate over the first 24 hours.

Excluded was hemoglobin, since the point was to test the trajectory of hemodynamic parameters independent of hemoglobin thresholds used to guide red blood cell transfusion.

The outcome measures were administration of packed red blood cell transfusion within 24 hours and all-cause hospital mortality.

The TFM was more accurate than a standard deep learning model in predicting red blood cell transfusion, with an accuracy of 93.6% vs 43.2%; P ≤ .001. It was also more accurate at predicting all-cause in-hospital mortality, with an accuracy of 89.5% vs 42.5%, P = .01.

The researchers concluded that the TFM approach was able to predict the hemodynamic trajectories of patients with acute GI bleeding defined as deviation and outperformed the baseline from the measured mean arterial pressure and heart rate.

 

Expert Perspective

“This is an exciting proof-of-concept study that shows generative AI methods may be applied to complex datasets in order to improve on our current predictive models and improve patient care,” said Jeremy Glissen Brown, MD, MSc, an assistant professor of medicine and a practicing gastroenterologist at Duke University who has published research on the use of AI in clinical practice. He reviewed the study for GI & Hepatology News but was not involved in the research.

“Future work will likely look into the implementation of a version of this model on real-time data.” he said. “We are at an exciting inflection point in predictive models within GI and clinical medicine. Predictive models based on deep learning and generative AI hold the promise of improving how we predict and treat disease states, but the excitement being generated with studies such as this needs to be balanced with the trade-offs inherent to the current paradigm of deep learning and generative models compared to more traditional regression-based models. These include many of the same ‘black box’ explainability questions that have risen in the age of convolutional neural networks as well as some method-specific questions due to the continuous and implicit nature of TFM.”

Elaborating on that, Glissen Brown said: “TFM, like many deep learning techniques, raises concerns about explainability that we’ve long seen with convolutional neural networks — the ‘black box’ problem, where it’s difficult to interpret exactly how and why the model arrives at a particular decision. But TFM also introduces unique challenges due to its continuous and implicit formulation. Since it often learns flows without explicitly defining intermediate representations or steps, it can be harder to trace the logic or pathways it uses to connect inputs to outputs. This makes standard interpretability tools less effective and calls for new techniques tailored to these continuous architectures.”

“This approach could have a real clinical impact,” said Robert Hirten, MD, associate professor of medicine and artificial intelligence, Icahn School of Medicine at Mount Sinai, New York City, who also reviewed the study. “Accurately predicting transfusion needs and mortality risk in real time could support earlier, more targeted interventions for high-risk patients. While these findings still need to be validated in prospective studies, it could enhance ICU decision-making and resource allocation.”

“For the practicing gastroenterologist, we envision this system could help them figure out when to perform endoscopy in a patient admitted with acute gastrointestinal bleeding in the ICU at very high risk of exsanguination,” Zhang told GI & Hepatology News.

The approach, the researchers said, will be useful in identifying unique patient characteristics, make possible the identification of high-risk patients and lead to more personalized medicine.

Hirten, Zhang, and Shung had no disclosures. Glissen Brown reported consulting relationships with Medtronic, OdinVision, Doximity, and Olympus. The National Institutes of Health funded this study.

A version of this article appeared on Medscape.com.

SAN DIEGO — A novel generative artificial intelligence (AI) framework known as trajectory flow matching (TFM) can predict the need for red blood cell transfusion and mortality risk in intensive care unit (ICU) patients with acute gastrointestinal (GI) bleeding, researchers reported at Digestive Disease Week^® (DDW) 2025.

Acute GI bleeding is the most common cause of digestive disease–related hospitalization, with an estimated 500,000 hospital admissions annually. It’s known that predicting the need for red blood cell transfusion in the first 24 hours may improve resuscitation and decrease both morbidity and mortality.

However, an existing clinical score known as the Rockall Score does not perform well for predicting mortality, Xi (Nicole) Zhang, an MD-PhD student at McGill University, Montreal, Quebec, Canada, told attendees at DDW. With an area under the curve of 0.65-0.75, better prediction is needed, said Zhang, whose coresearchers included Dennis Shung, MD, MHS, PhD, director of Applied Artificial Intelligence at Yale University School of Medicine, New Haven, Connecticut.

“We’d like to predict multiple outcomes in addition to mortality,” said Zhang, who is also a student at the Mila-Quebec Artificial Intelligence Institute.

As a result, the researchers turned to the TFM approach, applying it to ICU patients with acute GI bleeding to predict both the need for transfusion and in-hospital mortality risk. The all-cause mortality rate is up to 11%, according to a 2020 study by James Y. W. Lau, MD, and colleagues. The rebleeding rate of nonvariceal upper GI bleeds is up to 10.4%. Zhang said the rebleeding rate for variceal upper gastrointestinal bleeding is up to 65%.

The AI method the researchers used outperformed a standard deep learning model at predicting the need for transfusion and estimating mortality risk.

 

Defining the AI Framework

“Probabilistic flow matching is a class of generative artificial intelligence that learns how a simple distribution becomes a more complex distribution with ordinary differential equations,” Zhang told GI & Hepatology News. “For example, if you had a few lines and shapes you could learn how it could become a detailed portrait of a face. In our case, we start with a few blood pressure and heart rate measurements and learn the pattern of blood pressures and heart rates over time, particularly if they reflect clinical deterioration with hemodynamic instability.”

Another way to think about the underlying algorithm, Zhang said, is to think about a river with boats where the river flow determines where the boats end up. “We are trying to direct the boat to the correct dock by adjusting the flow of water in the canal. In this case we are mapping the distribution with the first few data points to the distribution with the entire patient trajectory.”

The information gained, she said, could be helpful in timing endoscopic evaluation or allocating red blood cell products for emergent transfusion.

 

Study Details

The researchers evaluated a cohort of 2602 patients admitted to the ICU, identified from the publicly available MIMIC-III database. They divided the patients into a training set of 2342 patients and an internal validation set of 260 patients. Input variables were severe liver disease comorbidity, administration of vasopressor medications, mean arterial blood pressure, and heart rate over the first 24 hours.

Excluded was hemoglobin, since the point was to test the trajectory of hemodynamic parameters independent of hemoglobin thresholds used to guide red blood cell transfusion.

The outcome measures were administration of packed red blood cell transfusion within 24 hours and all-cause hospital mortality.

The TFM was more accurate than a standard deep learning model in predicting red blood cell transfusion, with an accuracy of 93.6% vs 43.2%; P ≤ .001. It was also more accurate at predicting all-cause in-hospital mortality, with an accuracy of 89.5% vs 42.5%, P = .01.

The researchers concluded that the TFM approach was able to predict the hemodynamic trajectories of patients with acute GI bleeding defined as deviation and outperformed the baseline from the measured mean arterial pressure and heart rate.

 

Expert Perspective

“This is an exciting proof-of-concept study that shows generative AI methods may be applied to complex datasets in order to improve on our current predictive models and improve patient care,” said Jeremy Glissen Brown, MD, MSc, an assistant professor of medicine and a practicing gastroenterologist at Duke University who has published research on the use of AI in clinical practice. He reviewed the study for GI & Hepatology News but was not involved in the research.

“Future work will likely look into the implementation of a version of this model on real-time data.” he said. “We are at an exciting inflection point in predictive models within GI and clinical medicine. Predictive models based on deep learning and generative AI hold the promise of improving how we predict and treat disease states, but the excitement being generated with studies such as this needs to be balanced with the trade-offs inherent to the current paradigm of deep learning and generative models compared to more traditional regression-based models. These include many of the same ‘black box’ explainability questions that have risen in the age of convolutional neural networks as well as some method-specific questions due to the continuous and implicit nature of TFM.”

Elaborating on that, Glissen Brown said: “TFM, like many deep learning techniques, raises concerns about explainability that we’ve long seen with convolutional neural networks — the ‘black box’ problem, where it’s difficult to interpret exactly how and why the model arrives at a particular decision. But TFM also introduces unique challenges due to its continuous and implicit formulation. Since it often learns flows without explicitly defining intermediate representations or steps, it can be harder to trace the logic or pathways it uses to connect inputs to outputs. This makes standard interpretability tools less effective and calls for new techniques tailored to these continuous architectures.”

“This approach could have a real clinical impact,” said Robert Hirten, MD, associate professor of medicine and artificial intelligence, Icahn School of Medicine at Mount Sinai, New York City, who also reviewed the study. “Accurately predicting transfusion needs and mortality risk in real time could support earlier, more targeted interventions for high-risk patients. While these findings still need to be validated in prospective studies, it could enhance ICU decision-making and resource allocation.”

“For the practicing gastroenterologist, we envision this system could help them figure out when to perform endoscopy in a patient admitted with acute gastrointestinal bleeding in the ICU at very high risk of exsanguination,” Zhang told GI & Hepatology News.

The approach, the researchers said, will be useful in identifying unique patient characteristics, make possible the identification of high-risk patients and lead to more personalized medicine.

Hirten, Zhang, and Shung had no disclosures. Glissen Brown reported consulting relationships with Medtronic, OdinVision, Doximity, and Olympus. The National Institutes of Health funded this study.

A version of this article appeared on Medscape.com.

SAN DIEGO — A novel generative artificial intelligence (AI) framework known as trajectory flow matching (TFM) can predict the need for red blood cell transfusion and mortality risk in intensive care unit (ICU) patients with acute gastrointestinal (GI) bleeding, researchers reported at Digestive Disease Week^® (DDW) 2025.

Acute GI bleeding is the most common cause of digestive disease–related hospitalization, with an estimated 500,000 hospital admissions annually. It’s known that predicting the need for red blood cell transfusion in the first 24 hours may improve resuscitation and decrease both morbidity and mortality.

However, an existing clinical score known as the Rockall Score does not perform well for predicting mortality, Xi (Nicole) Zhang, an MD-PhD student at McGill University, Montreal, Quebec, Canada, told attendees at DDW. With an area under the curve of 0.65-0.75, better prediction is needed, said Zhang, whose coresearchers included Dennis Shung, MD, MHS, PhD, director of Applied Artificial Intelligence at Yale University School of Medicine, New Haven, Connecticut.

“We’d like to predict multiple outcomes in addition to mortality,” said Zhang, who is also a student at the Mila-Quebec Artificial Intelligence Institute.

As a result, the researchers turned to the TFM approach, applying it to ICU patients with acute GI bleeding to predict both the need for transfusion and in-hospital mortality risk. The all-cause mortality rate is up to 11%, according to a 2020 study by James Y. W. Lau, MD, and colleagues. The rebleeding rate of nonvariceal upper GI bleeds is up to 10.4%. Zhang said the rebleeding rate for variceal upper gastrointestinal bleeding is up to 65%.

The AI method the researchers used outperformed a standard deep learning model at predicting the need for transfusion and estimating mortality risk.

 

Defining the AI Framework

“Probabilistic flow matching is a class of generative artificial intelligence that learns how a simple distribution becomes a more complex distribution with ordinary differential equations,” Zhang told GI & Hepatology News. “For example, if you had a few lines and shapes you could learn how it could become a detailed portrait of a face. In our case, we start with a few blood pressure and heart rate measurements and learn the pattern of blood pressures and heart rates over time, particularly if they reflect clinical deterioration with hemodynamic instability.”

Another way to think about the underlying algorithm, Zhang said, is to think about a river with boats where the river flow determines where the boats end up. “We are trying to direct the boat to the correct dock by adjusting the flow of water in the canal. In this case we are mapping the distribution with the first few data points to the distribution with the entire patient trajectory.”

The information gained, she said, could be helpful in timing endoscopic evaluation or allocating red blood cell products for emergent transfusion.

 

Study Details

The researchers evaluated a cohort of 2602 patients admitted to the ICU, identified from the publicly available MIMIC-III database. They divided the patients into a training set of 2342 patients and an internal validation set of 260 patients. Input variables were severe liver disease comorbidity, administration of vasopressor medications, mean arterial blood pressure, and heart rate over the first 24 hours.

Excluded was hemoglobin, since the point was to test the trajectory of hemodynamic parameters independent of hemoglobin thresholds used to guide red blood cell transfusion.

The outcome measures were administration of packed red blood cell transfusion within 24 hours and all-cause hospital mortality.

The TFM was more accurate than a standard deep learning model in predicting red blood cell transfusion, with an accuracy of 93.6% vs 43.2%; P ≤ .001. It was also more accurate at predicting all-cause in-hospital mortality, with an accuracy of 89.5% vs 42.5%, P = .01.

The researchers concluded that the TFM approach was able to predict the hemodynamic trajectories of patients with acute GI bleeding defined as deviation and outperformed the baseline from the measured mean arterial pressure and heart rate.

 

Expert Perspective

“This is an exciting proof-of-concept study that shows generative AI methods may be applied to complex datasets in order to improve on our current predictive models and improve patient care,” said Jeremy Glissen Brown, MD, MSc, an assistant professor of medicine and a practicing gastroenterologist at Duke University who has published research on the use of AI in clinical practice. He reviewed the study for GI & Hepatology News but was not involved in the research.

“Future work will likely look into the implementation of a version of this model on real-time data.” he said. “We are at an exciting inflection point in predictive models within GI and clinical medicine. Predictive models based on deep learning and generative AI hold the promise of improving how we predict and treat disease states, but the excitement being generated with studies such as this needs to be balanced with the trade-offs inherent to the current paradigm of deep learning and generative models compared to more traditional regression-based models. These include many of the same ‘black box’ explainability questions that have risen in the age of convolutional neural networks as well as some method-specific questions due to the continuous and implicit nature of TFM.”

Elaborating on that, Glissen Brown said: “TFM, like many deep learning techniques, raises concerns about explainability that we’ve long seen with convolutional neural networks — the ‘black box’ problem, where it’s difficult to interpret exactly how and why the model arrives at a particular decision. But TFM also introduces unique challenges due to its continuous and implicit formulation. Since it often learns flows without explicitly defining intermediate representations or steps, it can be harder to trace the logic or pathways it uses to connect inputs to outputs. This makes standard interpretability tools less effective and calls for new techniques tailored to these continuous architectures.”

“This approach could have a real clinical impact,” said Robert Hirten, MD, associate professor of medicine and artificial intelligence, Icahn School of Medicine at Mount Sinai, New York City, who also reviewed the study. “Accurately predicting transfusion needs and mortality risk in real time could support earlier, more targeted interventions for high-risk patients. While these findings still need to be validated in prospective studies, it could enhance ICU decision-making and resource allocation.”

“For the practicing gastroenterologist, we envision this system could help them figure out when to perform endoscopy in a patient admitted with acute gastrointestinal bleeding in the ICU at very high risk of exsanguination,” Zhang told GI & Hepatology News.

The approach, the researchers said, will be useful in identifying unique patient characteristics, make possible the identification of high-risk patients and lead to more personalized medicine.

Hirten, Zhang, and Shung had no disclosures. Glissen Brown reported consulting relationships with Medtronic, OdinVision, Doximity, and Olympus. The National Institutes of Health funded this study.

A version of this article appeared on Medscape.com.

The “Shark Tank” winning innovation at the American Gastroenterological Association (AGA) Tech Summit in Chicago this April has “life-altering” potential for ostomy patients, according to one of the judges, and eliminates the need for constant pouch wear.

The innovation is called Twistomy and it is designed to replace current ostomy-pouch systems that can cause leaks, odor, skin irritation, embarrassment, and social and emotional distress. The AGA Committee for GI Innovation and Technology (CGIT) organizes the annual Tech Summit.

 

Twistomy’s winning design includes a flexible ring and sleeve, which are inserted into the stoma and secured on the outside with a set of rings that make up the housing unit attached to a standard wafer. The housing unit twists the sleeve closed, allowing the user to control fecal output. For evacuation, the user attaches a pouch, untwists the sleeve, evacuates cleanly and effectively, and then discards the pouch.

Twistomy cofounders Devon Horton, BS, senior bioengineer, and Lily Williams, BS, biomedical researcher and engineer, both work for the department of surgery at University of Colorado, Denver.

 

Horton said in an interview that when he was approached with the idea to create a better ostomy solution for a senior-year capstone project he was intrigued because the traditional ostomy system “has not changed in more than 70 years. It was crazy that no one had done anything to change that.” 

The Twistomy team also won the Grand Prize this spring at the Emerging Medical Innovation Valuation Competition at the Design of Medical Devices Conference held at the University of Minnesota, Minneapolis.

 

Witnessing the Struggle as a CNA

Horton also works as a certified nursing assistant at an inpatient unit at University of Colorado Hospital and the ostomy patients he sees there every shift help drive his passion to find a better solution.

He hears the emotional stories of people who manage their ostomy daily.

“Many express feelings of depression and anxiety, feeling isolated with their severe inability to go out and do things because of the fear of the noise the stoma makes, or the crinkling of the plastic bag in a yoga class,” he said. “We want to help them regain that control of quality of life.”

They also hope to cut down on the ostomy management time. “Initial user testing [for Twistomy] was less than 75 seconds to insert and assemble,” he said. “I did an interview with a patient yesterday who said they probably spend an hour a day managing their ostomy,” including cleaning and replacing.

Horton and Williams have a patent on the device and currently use three-dimensional printing for the prototypes.

 

Williams said they are now conducting consumer discovery studies through the National Science Foundation and are interviewing 30 stakeholders — “anyone who has a relationship with an ostomy,” whether a colorectal surgeon, a gastrointestinal nurse, ostomy patients, or insurers. 

Those interviews will help in refining the device so they can start consulting with manufacturers and work toward approval as a Class II medical device from the US Food and Drug Administration (FDA), Williams said.

 

Saving Healthcare Costs

Another potential benefit for Twistomy is its ability to cut healthcare costs, Horton said. Traditional ostomies are prone to leakage, which can lead to peristomal skin complications.

He pointed to a National Institutes of Health analysis that found that on average peristomal skin complications caused upwards of $80,000 more per ostomy patient in increased healthcare costs over a 3-month period than for those without the complications. 

“With Twistomy, we are reducing leakage most likely to zero,” Horton said. “We set out to say if we could reduce [infections] by half or a little less than half, we can cut out those tens of thousands of dollars that insurance companies and payers are spending.”

 

Permanent and Temporary Ostomy Markets

He pointed out that not all ostomies are permanent ostomies, adding that the reversal rate “is about 65%.” Often those reversal surgeries cannot take place until peristomal skin complications have been healed.

“We’re not only hoping to market to the permanent stoma patients, but the patients with temporary stomas as well,” he said.

The team estimates it will need $4 million–$6 million in funding for manufacturing and consultation costs as well as costs involved in seeking FDA approval. 

Horton and Williams project the housing unit cost will be $399 based on known out-of-pocket expenses for patients with ostomy care products and the unit would be replaced annually. Disposable elements would be an additional cost.

Assuming insurance acceptance of the product, he said, “With about an 80/20 insurance coverage, typical for many patients, it would be about $100 in out-of-pocket expenses per month to use our device, which is around the lower end of what a lot of patients are spending out of pocket.”

One of the Tech Summit judges, Somaya Albhaisi, MD, a gastroenterology/hepatology fellow at University of Southern California, Los Angeles, said in an interview that the Shark Tank results were unanimous among the five judges and Twistomy also took the fan favorite vote.

She said the teams were judged on quality of pitch, potential clinical impact, and feasibility of business plan. Teams got 5-7 minutes to pitch and answered questions afterward.

 

“Deep Understanding” of Patient Need

“They combined smart engineering with deep understanding of patient need, which is restoring control, dignity, and quality of life for ostomy users while also reducing healthcare costs. It is rare to see a solution this scalable and impactful. It was a deeply empathetic solution overall.” She noted that nearly 1 million people in the United States currently use an ostomy.

Ostomy users’ quality of life is compromised, and they often have mental health challenges, Albhaisi said. This innovation appears to offer easy use, more dignity and control. 

The other four Shark Tank finalists were:

• AI Lumen, which developed a retroview camera system, which attaches to the colonoscope and enhances imaging to detect hidden polyps that may evade conventional endoscopes.
• Amplified Sciences, which developed an ultrasensitive diagnostic platform that detects biomarker activities in minute volumes of fluid from pancreatic cystic lesions, helping to stratify patients into low risk or potential malignancy, reducing unneeded surgeries, costs, and comorbidities.
• KITE Endoscopic Innovations, which designed the Dynaflex TruCut needle to offer a simpler endoscopic ultrasound (EUS)–guided biopsy procedure with fewer needle passes, deeper insights into tumor pathology, and more tissue for geonomic analysis.
• MicroSteer, which designed a device to facilitate semiautomated endoscopic submucosal dissection (ESD) by decoupling the dissecting knife from the endoscope, enhancing safety and effectiveness during the procedure.

The Twistomy Team “Surprised Everyone”

The competitors’ scores were “very close,” one of the judges, Kevin Berliner, said in an interview. “The Twistomy team surprised everyone — the judges and the crowd — with their succinct, informative, and impactful pitch. That presentation disparity was the tiebreaker for me,” said Berliner, who works for Medtronic, a sponsor of the competition, in Chicago.

He said Horton and Williams were the youngest presenters and had the earliest stage pitch they judged, but they “outpresented other competitors in clarity, simplification, and storytelling.”

Also impressive was their description of their “commercially viable path to success” and their plan for the challenges ahead, he said.

Those challenges to get Twistomy to market center “on the ongoing changing climate we have with research funds lately,” Horton said. “We’re giving it an estimate of 3-5 years.” 

Horton, Williams, Albhaisi, and Berliner reported no relevant financial relationships.
 

The “Shark Tank” winning innovation at the American Gastroenterological Association (AGA) Tech Summit in Chicago this April has “life-altering” potential for ostomy patients, according to one of the judges, and eliminates the need for constant pouch wear.

The innovation is called Twistomy and it is designed to replace current ostomy-pouch systems that can cause leaks, odor, skin irritation, embarrassment, and social and emotional distress. The AGA Committee for GI Innovation and Technology (CGIT) organizes the annual Tech Summit.

 

Twistomy’s winning design includes a flexible ring and sleeve, which are inserted into the stoma and secured on the outside with a set of rings that make up the housing unit attached to a standard wafer. The housing unit twists the sleeve closed, allowing the user to control fecal output. For evacuation, the user attaches a pouch, untwists the sleeve, evacuates cleanly and effectively, and then discards the pouch.

Twistomy cofounders Devon Horton, BS, senior bioengineer, and Lily Williams, BS, biomedical researcher and engineer, both work for the department of surgery at University of Colorado, Denver.

 

Horton said in an interview that when he was approached with the idea to create a better ostomy solution for a senior-year capstone project he was intrigued because the traditional ostomy system “has not changed in more than 70 years. It was crazy that no one had done anything to change that.” 

The Twistomy team also won the Grand Prize this spring at the Emerging Medical Innovation Valuation Competition at the Design of Medical Devices Conference held at the University of Minnesota, Minneapolis.

 

Witnessing the Struggle as a CNA

Horton also works as a certified nursing assistant at an inpatient unit at University of Colorado Hospital and the ostomy patients he sees there every shift help drive his passion to find a better solution.

He hears the emotional stories of people who manage their ostomy daily.

“Many express feelings of depression and anxiety, feeling isolated with their severe inability to go out and do things because of the fear of the noise the stoma makes, or the crinkling of the plastic bag in a yoga class,” he said. “We want to help them regain that control of quality of life.”

They also hope to cut down on the ostomy management time. “Initial user testing [for Twistomy] was less than 75 seconds to insert and assemble,” he said. “I did an interview with a patient yesterday who said they probably spend an hour a day managing their ostomy,” including cleaning and replacing.

Horton and Williams have a patent on the device and currently use three-dimensional printing for the prototypes.

 

Williams said they are now conducting consumer discovery studies through the National Science Foundation and are interviewing 30 stakeholders — “anyone who has a relationship with an ostomy,” whether a colorectal surgeon, a gastrointestinal nurse, ostomy patients, or insurers. 

Those interviews will help in refining the device so they can start consulting with manufacturers and work toward approval as a Class II medical device from the US Food and Drug Administration (FDA), Williams said.

 

Saving Healthcare Costs

Another potential benefit for Twistomy is its ability to cut healthcare costs, Horton said. Traditional ostomies are prone to leakage, which can lead to peristomal skin complications.

He pointed to a National Institutes of Health analysis that found that on average peristomal skin complications caused upwards of $80,000 more per ostomy patient in increased healthcare costs over a 3-month period than for those without the complications. 

“With Twistomy, we are reducing leakage most likely to zero,” Horton said. “We set out to say if we could reduce [infections] by half or a little less than half, we can cut out those tens of thousands of dollars that insurance companies and payers are spending.”

 

Permanent and Temporary Ostomy Markets

He pointed out that not all ostomies are permanent ostomies, adding that the reversal rate “is about 65%.” Often those reversal surgeries cannot take place until peristomal skin complications have been healed.

“We’re not only hoping to market to the permanent stoma patients, but the patients with temporary stomas as well,” he said.

The team estimates it will need $4 million–$6 million in funding for manufacturing and consultation costs as well as costs involved in seeking FDA approval. 

Horton and Williams project the housing unit cost will be $399 based on known out-of-pocket expenses for patients with ostomy care products and the unit would be replaced annually. Disposable elements would be an additional cost.

Assuming insurance acceptance of the product, he said, “With about an 80/20 insurance coverage, typical for many patients, it would be about $100 in out-of-pocket expenses per month to use our device, which is around the lower end of what a lot of patients are spending out of pocket.”

One of the Tech Summit judges, Somaya Albhaisi, MD, a gastroenterology/hepatology fellow at University of Southern California, Los Angeles, said in an interview that the Shark Tank results were unanimous among the five judges and Twistomy also took the fan favorite vote.

She said the teams were judged on quality of pitch, potential clinical impact, and feasibility of business plan. Teams got 5-7 minutes to pitch and answered questions afterward.

 

“Deep Understanding” of Patient Need

“They combined smart engineering with deep understanding of patient need, which is restoring control, dignity, and quality of life for ostomy users while also reducing healthcare costs. It is rare to see a solution this scalable and impactful. It was a deeply empathetic solution overall.” She noted that nearly 1 million people in the United States currently use an ostomy.

Ostomy users’ quality of life is compromised, and they often have mental health challenges, Albhaisi said. This innovation appears to offer easy use, more dignity and control. 

The other four Shark Tank finalists were:

• AI Lumen, which developed a retroview camera system, which attaches to the colonoscope and enhances imaging to detect hidden polyps that may evade conventional endoscopes.
• Amplified Sciences, which developed an ultrasensitive diagnostic platform that detects biomarker activities in minute volumes of fluid from pancreatic cystic lesions, helping to stratify patients into low risk or potential malignancy, reducing unneeded surgeries, costs, and comorbidities.
• KITE Endoscopic Innovations, which designed the Dynaflex TruCut needle to offer a simpler endoscopic ultrasound (EUS)–guided biopsy procedure with fewer needle passes, deeper insights into tumor pathology, and more tissue for geonomic analysis.
• MicroSteer, which designed a device to facilitate semiautomated endoscopic submucosal dissection (ESD) by decoupling the dissecting knife from the endoscope, enhancing safety and effectiveness during the procedure.

The Twistomy Team “Surprised Everyone”

The competitors’ scores were “very close,” one of the judges, Kevin Berliner, said in an interview. “The Twistomy team surprised everyone — the judges and the crowd — with their succinct, informative, and impactful pitch. That presentation disparity was the tiebreaker for me,” said Berliner, who works for Medtronic, a sponsor of the competition, in Chicago.

He said Horton and Williams were the youngest presenters and had the earliest stage pitch they judged, but they “outpresented other competitors in clarity, simplification, and storytelling.”

Also impressive was their description of their “commercially viable path to success” and their plan for the challenges ahead, he said.

Those challenges to get Twistomy to market center “on the ongoing changing climate we have with research funds lately,” Horton said. “We’re giving it an estimate of 3-5 years.” 

Horton, Williams, Albhaisi, and Berliner reported no relevant financial relationships.
 

The “Shark Tank” winning innovation at the American Gastroenterological Association (AGA) Tech Summit in Chicago this April has “life-altering” potential for ostomy patients, according to one of the judges, and eliminates the need for constant pouch wear.

The innovation is called Twistomy and it is designed to replace current ostomy-pouch systems that can cause leaks, odor, skin irritation, embarrassment, and social and emotional distress. The AGA Committee for GI Innovation and Technology (CGIT) organizes the annual Tech Summit.

 

Twistomy’s winning design includes a flexible ring and sleeve, which are inserted into the stoma and secured on the outside with a set of rings that make up the housing unit attached to a standard wafer. The housing unit twists the sleeve closed, allowing the user to control fecal output. For evacuation, the user attaches a pouch, untwists the sleeve, evacuates cleanly and effectively, and then discards the pouch.

Twistomy cofounders Devon Horton, BS, senior bioengineer, and Lily Williams, BS, biomedical researcher and engineer, both work for the department of surgery at University of Colorado, Denver.

 

Horton said in an interview that when he was approached with the idea to create a better ostomy solution for a senior-year capstone project he was intrigued because the traditional ostomy system “has not changed in more than 70 years. It was crazy that no one had done anything to change that.” 

The Twistomy team also won the Grand Prize this spring at the Emerging Medical Innovation Valuation Competition at the Design of Medical Devices Conference held at the University of Minnesota, Minneapolis.

 

Witnessing the Struggle as a CNA

Horton also works as a certified nursing assistant at an inpatient unit at University of Colorado Hospital and the ostomy patients he sees there every shift help drive his passion to find a better solution.

He hears the emotional stories of people who manage their ostomy daily.

“Many express feelings of depression and anxiety, feeling isolated with their severe inability to go out and do things because of the fear of the noise the stoma makes, or the crinkling of the plastic bag in a yoga class,” he said. “We want to help them regain that control of quality of life.”

They also hope to cut down on the ostomy management time. “Initial user testing [for Twistomy] was less than 75 seconds to insert and assemble,” he said. “I did an interview with a patient yesterday who said they probably spend an hour a day managing their ostomy,” including cleaning and replacing.

Horton and Williams have a patent on the device and currently use three-dimensional printing for the prototypes.

 

Williams said they are now conducting consumer discovery studies through the National Science Foundation and are interviewing 30 stakeholders — “anyone who has a relationship with an ostomy,” whether a colorectal surgeon, a gastrointestinal nurse, ostomy patients, or insurers. 

Those interviews will help in refining the device so they can start consulting with manufacturers and work toward approval as a Class II medical device from the US Food and Drug Administration (FDA), Williams said.

 

Saving Healthcare Costs

Another potential benefit for Twistomy is its ability to cut healthcare costs, Horton said. Traditional ostomies are prone to leakage, which can lead to peristomal skin complications.

He pointed to a National Institutes of Health analysis that found that on average peristomal skin complications caused upwards of $80,000 more per ostomy patient in increased healthcare costs over a 3-month period than for those without the complications. 

“With Twistomy, we are reducing leakage most likely to zero,” Horton said. “We set out to say if we could reduce [infections] by half or a little less than half, we can cut out those tens of thousands of dollars that insurance companies and payers are spending.”

 

Permanent and Temporary Ostomy Markets

He pointed out that not all ostomies are permanent ostomies, adding that the reversal rate “is about 65%.” Often those reversal surgeries cannot take place until peristomal skin complications have been healed.

“We’re not only hoping to market to the permanent stoma patients, but the patients with temporary stomas as well,” he said.

The team estimates it will need $4 million–$6 million in funding for manufacturing and consultation costs as well as costs involved in seeking FDA approval. 

Horton and Williams project the housing unit cost will be $399 based on known out-of-pocket expenses for patients with ostomy care products and the unit would be replaced annually. Disposable elements would be an additional cost.

Assuming insurance acceptance of the product, he said, “With about an 80/20 insurance coverage, typical for many patients, it would be about $100 in out-of-pocket expenses per month to use our device, which is around the lower end of what a lot of patients are spending out of pocket.”

One of the Tech Summit judges, Somaya Albhaisi, MD, a gastroenterology/hepatology fellow at University of Southern California, Los Angeles, said in an interview that the Shark Tank results were unanimous among the five judges and Twistomy also took the fan favorite vote.

She said the teams were judged on quality of pitch, potential clinical impact, and feasibility of business plan. Teams got 5-7 minutes to pitch and answered questions afterward.

 

“Deep Understanding” of Patient Need

“They combined smart engineering with deep understanding of patient need, which is restoring control, dignity, and quality of life for ostomy users while also reducing healthcare costs. It is rare to see a solution this scalable and impactful. It was a deeply empathetic solution overall.” She noted that nearly 1 million people in the United States currently use an ostomy.

Ostomy users’ quality of life is compromised, and they often have mental health challenges, Albhaisi said. This innovation appears to offer easy use, more dignity and control. 

The other four Shark Tank finalists were:

• AI Lumen, which developed a retroview camera system, which attaches to the colonoscope and enhances imaging to detect hidden polyps that may evade conventional endoscopes.
• Amplified Sciences, which developed an ultrasensitive diagnostic platform that detects biomarker activities in minute volumes of fluid from pancreatic cystic lesions, helping to stratify patients into low risk or potential malignancy, reducing unneeded surgeries, costs, and comorbidities.
• KITE Endoscopic Innovations, which designed the Dynaflex TruCut needle to offer a simpler endoscopic ultrasound (EUS)–guided biopsy procedure with fewer needle passes, deeper insights into tumor pathology, and more tissue for geonomic analysis.
• MicroSteer, which designed a device to facilitate semiautomated endoscopic submucosal dissection (ESD) by decoupling the dissecting knife from the endoscope, enhancing safety and effectiveness during the procedure.

The Twistomy Team “Surprised Everyone”

The competitors’ scores were “very close,” one of the judges, Kevin Berliner, said in an interview. “The Twistomy team surprised everyone — the judges and the crowd — with their succinct, informative, and impactful pitch. That presentation disparity was the tiebreaker for me,” said Berliner, who works for Medtronic, a sponsor of the competition, in Chicago.

He said Horton and Williams were the youngest presenters and had the earliest stage pitch they judged, but they “outpresented other competitors in clarity, simplification, and storytelling.”

Also impressive was their description of their “commercially viable path to success” and their plan for the challenges ahead, he said.

Those challenges to get Twistomy to market center “on the ongoing changing climate we have with research funds lately,” Horton said. “We’re giving it an estimate of 3-5 years.” 

Horton, Williams, Albhaisi, and Berliner reported no relevant financial relationships.
 

SAN DIEGO — Crohn’s disease (CD) has become more common in the United States, and an estimated 1 million Americans have the condition. Still, much is unknown about how to evaluate the individual risk for the disease.

“It’s pretty much accepted that Crohn’s disease does not begin at diagnosis,” said Ryan Ungaro, MD, associate professor of medicine at the Icahn School of Medicine at Mount Sinai, New York City, speaking at Digestive Disease Week (DDW)^® 2025.

Although individual blood markers have been associated with the future risk for CD, what’s needed, he said, is to understand which combination of biomarkers are most predictive.

Now, Ungaro and his team have developed a risk score they found accurate in predicting CD onset within 2 years before its onset.

It’s an early version that will likely be further improved and needs additional validation, Ungaro told GI & Hepatology News.

“Once we can accurately identify individuals at risk for developing Crohn’s disease, we can then imagine a number of potential interventions,” Ungaro said.

Approaches would vary depending on how far away the onset is estimated to be. For people who likely wouldn’t develop disease for many years, one intervention might be close monitoring to enable diagnosis in the earliest stages, when treatment works best, he said. Someone at a high risk of developing CD in the next 2 or 3 years, on the other hand, might be offered a pharmaceutical intervention.

 

Developing and Testing the Risk Score

To develop the risk score, Ungaro and colleagues analyzed data of 200 patients with CD and 100 healthy control participants from PREDICTS, a nested case-controlled study of active US military service members. The study is within the larger Department of Defense Serum Repository, which began in 1985 and has more than 62.5 million samples, all stored at −30 °C.

The researchers collected serum samples at four timepoints up to 6 or more years before the diagnosis. They assayed antimicrobial antibodies using the Prometheus Laboratories platform, proteomic markers using the Olink inflammation panel, and anti–granulocyte macrophage colony-stimulating factor autoantibodies using enzyme-linked immunosorbent assay.

Participants (median age, 33 years for both groups) were randomly divided into equally sized training and testing sets. In both the group, 83% of patients were White and about 90% were men.

Time-varying trajectories of marker abundance were estimated for each biomarker. Then, logistic regression modeled disease status as a function of each marker for different timepoints and multivariate modeling was performed via logistic LASSO regression.

A risk score to predict CD onset within 2 years was developed. Prediction models were fit on the testing set and predictive performance evaluated using receiver operating characteristic curves and area under the curve (AUC).

Blood proteins and antibodies have differing associations with CD depending on the time before diagnosis, the researchers found.

The integrative model to predict CD onset within 2 years incorporated 10 biomarkers associated significantly with CD onset.

The AUC for the model was 0.87 (considered good, with 1 indicating perfect discrimination). It produced a specificity of 99% and a positive predictive value of 84%.

The researchers stratified the model scores into quartiles and found the CD incidence within 2 years increased from 2% in the first quartile to 57.7% in the fourth. The relative risk of developing CD in the top quartile individuals vs lower quartile individuals was 10.4.

The serologic and proteomic markers show dynamic changes years before the diagnosis, Ungaro said.

 

A Strong Start

The research represents “an ambitious and exciting frontier for the future of IBD [inflammatory bowel disease] care,” said Victor G. Chedid, MD, MS, consultant and assistant professor of medicine at Mayo Clinic, Rochester, Minnesota, who reviewed the findings but was not involved in the study.

Currently, physicians treat IBD once it manifests, and it’s difficult to predict who will get CD, he said.

The integrative model’s AUC of 0.87 is impressive, and its specificity and positive predictive value levels show it is highly accurate in predicting the onset of CD within 2 years, Chedid added.

Further validation in larger and more diverse population is needed, Chedid said, but he sees the potential for the model to be practical in clinical practice.

“Additionally, the use of blood-based biomarkers makes the model relatively noninvasive and easy to implement in a clinical setting,” he said.

Now, the research goal is to understand the best biomarkers for characterizing the different preclinical phases of CD and to test different interventions in prevention trials, Ungaro told GI & Hepatology News.

A few trials are planned or ongoing, he noted. The trial PIONIR trial will look at the impact of a specific diet on the risk of developing CD, and the INTERCEPT trial aims to develop a blood-based risk score that can identify individuals with a high risk of developing CD within 5 years after initial evaluation.

Ungaro reported being on the advisory board of and/or receiving speaker or consulting fees from AbbVie, Bristol Myer Squibb, Celltrion, ECM Therapeutics, Genentech, Jansen, Eli Lilly, Pfizer, Roivant, Sanofi, and Takeda. Chedid reported having no relevant disclosures.

The PROMISE Consortium is funded by the Helmsley Charitable Trust.

A version of this article appeared on Medscape.com.

SAN DIEGO — Crohn’s disease (CD) has become more common in the United States, and an estimated 1 million Americans have the condition. Still, much is unknown about how to evaluate the individual risk for the disease.

“It’s pretty much accepted that Crohn’s disease does not begin at diagnosis,” said Ryan Ungaro, MD, associate professor of medicine at the Icahn School of Medicine at Mount Sinai, New York City, speaking at Digestive Disease Week (DDW)^® 2025.

Although individual blood markers have been associated with the future risk for CD, what’s needed, he said, is to understand which combination of biomarkers are most predictive.

Now, Ungaro and his team have developed a risk score they found accurate in predicting CD onset within 2 years before its onset.

It’s an early version that will likely be further improved and needs additional validation, Ungaro told GI & Hepatology News.

“Once we can accurately identify individuals at risk for developing Crohn’s disease, we can then imagine a number of potential interventions,” Ungaro said.

Approaches would vary depending on how far away the onset is estimated to be. For people who likely wouldn’t develop disease for many years, one intervention might be close monitoring to enable diagnosis in the earliest stages, when treatment works best, he said. Someone at a high risk of developing CD in the next 2 or 3 years, on the other hand, might be offered a pharmaceutical intervention.

 

Developing and Testing the Risk Score

To develop the risk score, Ungaro and colleagues analyzed data of 200 patients with CD and 100 healthy control participants from PREDICTS, a nested case-controlled study of active US military service members. The study is within the larger Department of Defense Serum Repository, which began in 1985 and has more than 62.5 million samples, all stored at −30 °C.

The researchers collected serum samples at four timepoints up to 6 or more years before the diagnosis. They assayed antimicrobial antibodies using the Prometheus Laboratories platform, proteomic markers using the Olink inflammation panel, and anti–granulocyte macrophage colony-stimulating factor autoantibodies using enzyme-linked immunosorbent assay.

Participants (median age, 33 years for both groups) were randomly divided into equally sized training and testing sets. In both the group, 83% of patients were White and about 90% were men.

Time-varying trajectories of marker abundance were estimated for each biomarker. Then, logistic regression modeled disease status as a function of each marker for different timepoints and multivariate modeling was performed via logistic LASSO regression.

A risk score to predict CD onset within 2 years was developed. Prediction models were fit on the testing set and predictive performance evaluated using receiver operating characteristic curves and area under the curve (AUC).

Blood proteins and antibodies have differing associations with CD depending on the time before diagnosis, the researchers found.

The integrative model to predict CD onset within 2 years incorporated 10 biomarkers associated significantly with CD onset.

The AUC for the model was 0.87 (considered good, with 1 indicating perfect discrimination). It produced a specificity of 99% and a positive predictive value of 84%.

The researchers stratified the model scores into quartiles and found the CD incidence within 2 years increased from 2% in the first quartile to 57.7% in the fourth. The relative risk of developing CD in the top quartile individuals vs lower quartile individuals was 10.4.

The serologic and proteomic markers show dynamic changes years before the diagnosis, Ungaro said.

 

A Strong Start

The research represents “an ambitious and exciting frontier for the future of IBD [inflammatory bowel disease] care,” said Victor G. Chedid, MD, MS, consultant and assistant professor of medicine at Mayo Clinic, Rochester, Minnesota, who reviewed the findings but was not involved in the study.

Currently, physicians treat IBD once it manifests, and it’s difficult to predict who will get CD, he said.

The integrative model’s AUC of 0.87 is impressive, and its specificity and positive predictive value levels show it is highly accurate in predicting the onset of CD within 2 years, Chedid added.

Further validation in larger and more diverse population is needed, Chedid said, but he sees the potential for the model to be practical in clinical practice.

“Additionally, the use of blood-based biomarkers makes the model relatively noninvasive and easy to implement in a clinical setting,” he said.

Now, the research goal is to understand the best biomarkers for characterizing the different preclinical phases of CD and to test different interventions in prevention trials, Ungaro told GI & Hepatology News.

A few trials are planned or ongoing, he noted. The trial PIONIR trial will look at the impact of a specific diet on the risk of developing CD, and the INTERCEPT trial aims to develop a blood-based risk score that can identify individuals with a high risk of developing CD within 5 years after initial evaluation.

Ungaro reported being on the advisory board of and/or receiving speaker or consulting fees from AbbVie, Bristol Myer Squibb, Celltrion, ECM Therapeutics, Genentech, Jansen, Eli Lilly, Pfizer, Roivant, Sanofi, and Takeda. Chedid reported having no relevant disclosures.

The PROMISE Consortium is funded by the Helmsley Charitable Trust.

A version of this article appeared on Medscape.com.

SAN DIEGO — Crohn’s disease (CD) has become more common in the United States, and an estimated 1 million Americans have the condition. Still, much is unknown about how to evaluate the individual risk for the disease.

“It’s pretty much accepted that Crohn’s disease does not begin at diagnosis,” said Ryan Ungaro, MD, associate professor of medicine at the Icahn School of Medicine at Mount Sinai, New York City, speaking at Digestive Disease Week (DDW)^® 2025.

Although individual blood markers have been associated with the future risk for CD, what’s needed, he said, is to understand which combination of biomarkers are most predictive.

Now, Ungaro and his team have developed a risk score they found accurate in predicting CD onset within 2 years before its onset.

It’s an early version that will likely be further improved and needs additional validation, Ungaro told GI & Hepatology News.

“Once we can accurately identify individuals at risk for developing Crohn’s disease, we can then imagine a number of potential interventions,” Ungaro said.

Approaches would vary depending on how far away the onset is estimated to be. For people who likely wouldn’t develop disease for many years, one intervention might be close monitoring to enable diagnosis in the earliest stages, when treatment works best, he said. Someone at a high risk of developing CD in the next 2 or 3 years, on the other hand, might be offered a pharmaceutical intervention.

 

Developing and Testing the Risk Score

To develop the risk score, Ungaro and colleagues analyzed data of 200 patients with CD and 100 healthy control participants from PREDICTS, a nested case-controlled study of active US military service members. The study is within the larger Department of Defense Serum Repository, which began in 1985 and has more than 62.5 million samples, all stored at −30 °C.

The researchers collected serum samples at four timepoints up to 6 or more years before the diagnosis. They assayed antimicrobial antibodies using the Prometheus Laboratories platform, proteomic markers using the Olink inflammation panel, and anti–granulocyte macrophage colony-stimulating factor autoantibodies using enzyme-linked immunosorbent assay.

Participants (median age, 33 years for both groups) were randomly divided into equally sized training and testing sets. In both the group, 83% of patients were White and about 90% were men.

Time-varying trajectories of marker abundance were estimated for each biomarker. Then, logistic regression modeled disease status as a function of each marker for different timepoints and multivariate modeling was performed via logistic LASSO regression.

A risk score to predict CD onset within 2 years was developed. Prediction models were fit on the testing set and predictive performance evaluated using receiver operating characteristic curves and area under the curve (AUC).

Blood proteins and antibodies have differing associations with CD depending on the time before diagnosis, the researchers found.

The integrative model to predict CD onset within 2 years incorporated 10 biomarkers associated significantly with CD onset.

The AUC for the model was 0.87 (considered good, with 1 indicating perfect discrimination). It produced a specificity of 99% and a positive predictive value of 84%.

The researchers stratified the model scores into quartiles and found the CD incidence within 2 years increased from 2% in the first quartile to 57.7% in the fourth. The relative risk of developing CD in the top quartile individuals vs lower quartile individuals was 10.4.

The serologic and proteomic markers show dynamic changes years before the diagnosis, Ungaro said.

 

A Strong Start

The research represents “an ambitious and exciting frontier for the future of IBD [inflammatory bowel disease] care,” said Victor G. Chedid, MD, MS, consultant and assistant professor of medicine at Mayo Clinic, Rochester, Minnesota, who reviewed the findings but was not involved in the study.

Currently, physicians treat IBD once it manifests, and it’s difficult to predict who will get CD, he said.

The integrative model’s AUC of 0.87 is impressive, and its specificity and positive predictive value levels show it is highly accurate in predicting the onset of CD within 2 years, Chedid added.

Further validation in larger and more diverse population is needed, Chedid said, but he sees the potential for the model to be practical in clinical practice.

“Additionally, the use of blood-based biomarkers makes the model relatively noninvasive and easy to implement in a clinical setting,” he said.

Now, the research goal is to understand the best biomarkers for characterizing the different preclinical phases of CD and to test different interventions in prevention trials, Ungaro told GI & Hepatology News.

A few trials are planned or ongoing, he noted. The trial PIONIR trial will look at the impact of a specific diet on the risk of developing CD, and the INTERCEPT trial aims to develop a blood-based risk score that can identify individuals with a high risk of developing CD within 5 years after initial evaluation.

Ungaro reported being on the advisory board of and/or receiving speaker or consulting fees from AbbVie, Bristol Myer Squibb, Celltrion, ECM Therapeutics, Genentech, Jansen, Eli Lilly, Pfizer, Roivant, Sanofi, and Takeda. Chedid reported having no relevant disclosures.

The PROMISE Consortium is funded by the Helmsley Charitable Trust.

A version of this article appeared on Medscape.com.