Bridget M. Kuehn

Even mundane tasks such as making a meal can be exhausting for Louise Salant.

“I’m totally wiped out,” said the 71-year-old former private music instructor with asthma who lives in New York City and has been coping with debilitating symptoms of fatigue, shortness of breath, and gastrointestinal symptoms since recovering from a severe bout of COVID-19 2 years ago. “I just don’t have the energy.”

Ms. Salant is not alone. Many older people who contract COVID-19 experience prolonged symptoms of the disease. An analysis of Medicare Advantage claims data published in the BMJ found that about one-third of roughly 87,000 adults aged 65 in the database with a COVID-19 diagnosis sought care for persistent or new symptoms 21 or more days later.

That figure is about twice the rate of persistent COVID-19 related symptoms seen in a cohort of adults younger than age 65 with commercial insurance analyzed by the same group of researchers in a separate BMJ study. Compared with a 2020 comparator group of patients in this age cohort, these patients had a greater likelihood of respiratory failure, fatigue, hypertension, memory problems, kidney injury, mental health conditions, hypercoagulability, and cardiac rhythm disorders. When they compared post–COVID-19 symptoms to lasting symptoms of another serious viral disease – influenza – the researchers found that only respiratory failure, dementia, and post-viral fatigue were more common in the COVID-19 group.

“It became clear early in the pandemic that there is going to be a second pandemic related to all of the complications that we’ve seen related to COVID-19 infections,” said Ken Cohen, MD, executive director of translational research and national senior medical director for Optum Labs in Minnetonka, Minn., who coauthored the BMJ studies.

The results are among a growing body of evidence suggesting that older adults are at high risk of persistent post-COVID-19 symptoms.

Researchers in Rome, for example, found that 83% of 165 patients aged 65 or older who had been hospitalized for COVID-19 reported at least one lasting symptom – problems like fatigue, shortness of breath, joint pain, and coughing – in the months after hospitalization. One-third of those had two symptoms, and 46% had three or more.

A similar study in Norway found that two-thirds of patients aged 60 or older reported reduced health-related quality of life during follow-up visits 6 months after hospitalization for COVID-19. The most-reported impairments among those patients were the inability to perform the tasks of daily life, reduced mobility, and increased pain and discomfort.
 

Cognitive concerns

Mounting evidence indicates that COVID-19 may contribute to chronic cognitive impairment in older adults. A multisite U.S. study found that 28% of 817 adults presenting to emergency departments with COVID-19 had delirium and poorer outcomes. A Chinese case-control study that enrolled 1,438 individuals hospitalized in Wuhan for COVID-19, along with 438 of their uninfected spouses, found that 12% of COVID-19 survivors experienced cognitive impairment a year after discharge. Matteo Tosato, MD, PhD, head of the outpatient clinic for patients with long COVID symptoms at Gemelli Hospital in Rome, called those findings “very concerning.”

Jin Ho Han, MD, associate professor of emergency medicine at Vanderbilt University, Nashville, Tenn., said cognitive impairment is common after an acute illness, particularly in frail or vulnerable patients.

“Hospitalization and the acute illness itself accelerate cognitive decline,” said Dr. Han, and previous evidence links delirium with worsening cognition. He and his colleagues are studying the potential role of delirium in longer-term cognitive decline in older patients after COVID-19.

Dr. Han emphasized the importance of preventing COVID-19-related delirium through vaccines and other strategies to reduce exposure of older patients to the virus. “Once you have cognitive decline, there are no interventions to reverse it,” he said.
 

Alarm bells for long-term care

Experts expressed concern that the situation might be even worse for people living in long-term care facilities. Many already need assistance with tasks of daily living and could be particularly vulnerable to lasting effects of COVID-19, said Karl Steinberg, MD, president of the Society for Post-Acute and Long-Term Care Medicine. He estimated that roughly half of his patients who have had COVID-19, regardless of the severity of their symptoms, have endured some degree of functional decline.

“It’s common for long-term care facility residents to experience functional and cognitive decline, even after seemingly minor things, like a cold or a trip to the hospital,” Dr. Steinberg, who has been a medical director of long-term care facilities in San Diego County for more than 2 decades, told this news organization. “It makes it a little harder to determine whether the declines we’ve been seeing post COVID in these residents are attributable to post COVID versus just an accelerated step in their overall expected decline.”

The pandemic may have contributed to worse outcomes for people in long-term care facilities in several ways: the disease itself, its effects on health care delivery, and necessary preventive measures to protect long-term care residents from exposure to the virus.

“During the many months where family visits were prohibited, we saw people – whether they had COVID-19 or not – suffer major clinical, functional, cognitive declines or severe psychological symptoms,” Dr. Steinberg said.

He emphasized the importance of preventive measures such as vaccines and boosters in patients in long-term care facilities. He said the benefit of preventing lasting symptoms is often a strong motivator for family caregivers of people with dementia to get them vaccinated or boosted.

“It’s clear that vaccination and booster reduce the incidence of post-COVID symptoms,” he said. Almost all studies have been in younger cohorts, but he expects the benefits would also apply to older patients.
 

Easing symptoms and offering support

As with long COVID generally, many questions remain about the causes of lasting symptoms of COVID-19 in older patients, and how best to treat them. Dr. Tosato, who led the study of long-COVID patients in Rome, is focusing on inflammation as a critical factor in the condition. He and colleagues across Europe hope to answer some of them by launching a multicenter study of lasting COVID-19 symptoms. 

In the meantime, Dr. Steinberg and Dr. Tosato said they are doing their best to evaluate and treat patients empirically.

“We pull from our armamentarium to treat system-specific symptoms,” Dr. Steinberg said. “We want to improve the quality of life and help each day be the best it can.”

Physicians in long-term care facilities might use medications such as antidepressants or nonpharmacologic approaches for patients experiencing depression symptoms. Families are also crucial in helping patients by bringing in home-cooked meals and encouraging loved ones who may be experiencing loss of taste or smell to eat, Dr. Steinberg said.

“We’ve seen with the return of families and loved ones visiting to some extent has alleviated some people’s symptoms, especially psychological ones,” he said.

Dr. Tosato said he and his colleagues start with an individualized, multidisciplinary assessment to determine what types of care may help. He noted that physicians might recommend medications or rehabilitative therapies depending on the patient’s needs.

“A personalized approach is key,” Dr. Tosato said. His study also found that the proportion of older patients experiencing symptoms declined over time – a glimmer of hope that many will recover. 

Dr. Cohen emphasized the need for a multimodal rehabilitation, an evidence-based approach used to care for patients who survived hospitalization with severe COVID-19 – a group that has substantially higher rates of persistent symptoms. This approach includes cognitive rehabilitation, physical therapy, occupational therapy, and a graded exercise program.

Dr. Han and colleagues are studying potential therapies such as cognitive rehabilitation in adults who’ve experienced delirium. But until evidence-based treatments are available, they stress the role of support for patients with cognitive decline and their families.   

“A lot of the work we do is teach patients and their families to compensate for newly acquired cognitive deficits from any illness, including COVID-19,” Dr. Han said.

Ms. Salant said she has experienced some improvement in her energy since her pulmonologist recommended a new inhaler based on her symptoms. Her sense of smell and taste, lost to the infection, returned after she received her first dose of a vaccine against COVID-19. She takes comfort in participating in Survivor Corps, a group of more than 170,000 COVID-19 survivors and their families who advocate for more scientific research on the disease.

She also expressed gratitude for the support she receives from her primary care physician, who she said has taken the time to learn more about the symptoms of long COVID, listens to her, and respects what she has to say.

“I have hope that I will keep getting better by baby steps,” Ms. Salant said. 

Dr. Tosato, Dr. Steinberg, and Dr. Han have disclosed no relevant financial relationships.

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

Even mundane tasks such as making a meal can be exhausting for Louise Salant.

“I’m totally wiped out,” said the 71-year-old former private music instructor with asthma who lives in New York City and has been coping with debilitating symptoms of fatigue, shortness of breath, and gastrointestinal symptoms since recovering from a severe bout of COVID-19 2 years ago. “I just don’t have the energy.”

Ms. Salant is not alone. Many older people who contract COVID-19 experience prolonged symptoms of the disease. An analysis of Medicare Advantage claims data published in the BMJ found that about one-third of roughly 87,000 adults aged 65 in the database with a COVID-19 diagnosis sought care for persistent or new symptoms 21 or more days later.

That figure is about twice the rate of persistent COVID-19 related symptoms seen in a cohort of adults younger than age 65 with commercial insurance analyzed by the same group of researchers in a separate BMJ study. Compared with a 2020 comparator group of patients in this age cohort, these patients had a greater likelihood of respiratory failure, fatigue, hypertension, memory problems, kidney injury, mental health conditions, hypercoagulability, and cardiac rhythm disorders. When they compared post–COVID-19 symptoms to lasting symptoms of another serious viral disease – influenza – the researchers found that only respiratory failure, dementia, and post-viral fatigue were more common in the COVID-19 group.

“It became clear early in the pandemic that there is going to be a second pandemic related to all of the complications that we’ve seen related to COVID-19 infections,” said Ken Cohen, MD, executive director of translational research and national senior medical director for Optum Labs in Minnetonka, Minn., who coauthored the BMJ studies.

The results are among a growing body of evidence suggesting that older adults are at high risk of persistent post-COVID-19 symptoms.

Researchers in Rome, for example, found that 83% of 165 patients aged 65 or older who had been hospitalized for COVID-19 reported at least one lasting symptom – problems like fatigue, shortness of breath, joint pain, and coughing – in the months after hospitalization. One-third of those had two symptoms, and 46% had three or more.

A similar study in Norway found that two-thirds of patients aged 60 or older reported reduced health-related quality of life during follow-up visits 6 months after hospitalization for COVID-19. The most-reported impairments among those patients were the inability to perform the tasks of daily life, reduced mobility, and increased pain and discomfort.
 

Cognitive concerns

Mounting evidence indicates that COVID-19 may contribute to chronic cognitive impairment in older adults. A multisite U.S. study found that 28% of 817 adults presenting to emergency departments with COVID-19 had delirium and poorer outcomes. A Chinese case-control study that enrolled 1,438 individuals hospitalized in Wuhan for COVID-19, along with 438 of their uninfected spouses, found that 12% of COVID-19 survivors experienced cognitive impairment a year after discharge. Matteo Tosato, MD, PhD, head of the outpatient clinic for patients with long COVID symptoms at Gemelli Hospital in Rome, called those findings “very concerning.”

Jin Ho Han, MD, associate professor of emergency medicine at Vanderbilt University, Nashville, Tenn., said cognitive impairment is common after an acute illness, particularly in frail or vulnerable patients.

“Hospitalization and the acute illness itself accelerate cognitive decline,” said Dr. Han, and previous evidence links delirium with worsening cognition. He and his colleagues are studying the potential role of delirium in longer-term cognitive decline in older patients after COVID-19.

Dr. Han emphasized the importance of preventing COVID-19-related delirium through vaccines and other strategies to reduce exposure of older patients to the virus. “Once you have cognitive decline, there are no interventions to reverse it,” he said.
 

Alarm bells for long-term care

Experts expressed concern that the situation might be even worse for people living in long-term care facilities. Many already need assistance with tasks of daily living and could be particularly vulnerable to lasting effects of COVID-19, said Karl Steinberg, MD, president of the Society for Post-Acute and Long-Term Care Medicine. He estimated that roughly half of his patients who have had COVID-19, regardless of the severity of their symptoms, have endured some degree of functional decline.

“It’s common for long-term care facility residents to experience functional and cognitive decline, even after seemingly minor things, like a cold or a trip to the hospital,” Dr. Steinberg, who has been a medical director of long-term care facilities in San Diego County for more than 2 decades, told this news organization. “It makes it a little harder to determine whether the declines we’ve been seeing post COVID in these residents are attributable to post COVID versus just an accelerated step in their overall expected decline.”

The pandemic may have contributed to worse outcomes for people in long-term care facilities in several ways: the disease itself, its effects on health care delivery, and necessary preventive measures to protect long-term care residents from exposure to the virus.

“During the many months where family visits were prohibited, we saw people – whether they had COVID-19 or not – suffer major clinical, functional, cognitive declines or severe psychological symptoms,” Dr. Steinberg said.

He emphasized the importance of preventive measures such as vaccines and boosters in patients in long-term care facilities. He said the benefit of preventing lasting symptoms is often a strong motivator for family caregivers of people with dementia to get them vaccinated or boosted.

“It’s clear that vaccination and booster reduce the incidence of post-COVID symptoms,” he said. Almost all studies have been in younger cohorts, but he expects the benefits would also apply to older patients.
 

Easing symptoms and offering support

As with long COVID generally, many questions remain about the causes of lasting symptoms of COVID-19 in older patients, and how best to treat them. Dr. Tosato, who led the study of long-COVID patients in Rome, is focusing on inflammation as a critical factor in the condition. He and colleagues across Europe hope to answer some of them by launching a multicenter study of lasting COVID-19 symptoms. 

In the meantime, Dr. Steinberg and Dr. Tosato said they are doing their best to evaluate and treat patients empirically.

“We pull from our armamentarium to treat system-specific symptoms,” Dr. Steinberg said. “We want to improve the quality of life and help each day be the best it can.”

Physicians in long-term care facilities might use medications such as antidepressants or nonpharmacologic approaches for patients experiencing depression symptoms. Families are also crucial in helping patients by bringing in home-cooked meals and encouraging loved ones who may be experiencing loss of taste or smell to eat, Dr. Steinberg said.

“We’ve seen with the return of families and loved ones visiting to some extent has alleviated some people’s symptoms, especially psychological ones,” he said.

Dr. Tosato said he and his colleagues start with an individualized, multidisciplinary assessment to determine what types of care may help. He noted that physicians might recommend medications or rehabilitative therapies depending on the patient’s needs.

“A personalized approach is key,” Dr. Tosato said. His study also found that the proportion of older patients experiencing symptoms declined over time – a glimmer of hope that many will recover. 

Dr. Cohen emphasized the need for a multimodal rehabilitation, an evidence-based approach used to care for patients who survived hospitalization with severe COVID-19 – a group that has substantially higher rates of persistent symptoms. This approach includes cognitive rehabilitation, physical therapy, occupational therapy, and a graded exercise program.

Dr. Han and colleagues are studying potential therapies such as cognitive rehabilitation in adults who’ve experienced delirium. But until evidence-based treatments are available, they stress the role of support for patients with cognitive decline and their families.   

“A lot of the work we do is teach patients and their families to compensate for newly acquired cognitive deficits from any illness, including COVID-19,” Dr. Han said.

Ms. Salant said she has experienced some improvement in her energy since her pulmonologist recommended a new inhaler based on her symptoms. Her sense of smell and taste, lost to the infection, returned after she received her first dose of a vaccine against COVID-19. She takes comfort in participating in Survivor Corps, a group of more than 170,000 COVID-19 survivors and their families who advocate for more scientific research on the disease.

She also expressed gratitude for the support she receives from her primary care physician, who she said has taken the time to learn more about the symptoms of long COVID, listens to her, and respects what she has to say.

“I have hope that I will keep getting better by baby steps,” Ms. Salant said. 

Dr. Tosato, Dr. Steinberg, and Dr. Han have disclosed no relevant financial relationships.

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

Even mundane tasks such as making a meal can be exhausting for Louise Salant.

“I’m totally wiped out,” said the 71-year-old former private music instructor with asthma who lives in New York City and has been coping with debilitating symptoms of fatigue, shortness of breath, and gastrointestinal symptoms since recovering from a severe bout of COVID-19 2 years ago. “I just don’t have the energy.”

Ms. Salant is not alone. Many older people who contract COVID-19 experience prolonged symptoms of the disease. An analysis of Medicare Advantage claims data published in the BMJ found that about one-third of roughly 87,000 adults aged 65 in the database with a COVID-19 diagnosis sought care for persistent or new symptoms 21 or more days later.

That figure is about twice the rate of persistent COVID-19 related symptoms seen in a cohort of adults younger than age 65 with commercial insurance analyzed by the same group of researchers in a separate BMJ study. Compared with a 2020 comparator group of patients in this age cohort, these patients had a greater likelihood of respiratory failure, fatigue, hypertension, memory problems, kidney injury, mental health conditions, hypercoagulability, and cardiac rhythm disorders. When they compared post–COVID-19 symptoms to lasting symptoms of another serious viral disease – influenza – the researchers found that only respiratory failure, dementia, and post-viral fatigue were more common in the COVID-19 group.

“It became clear early in the pandemic that there is going to be a second pandemic related to all of the complications that we’ve seen related to COVID-19 infections,” said Ken Cohen, MD, executive director of translational research and national senior medical director for Optum Labs in Minnetonka, Minn., who coauthored the BMJ studies.

The results are among a growing body of evidence suggesting that older adults are at high risk of persistent post-COVID-19 symptoms.

Researchers in Rome, for example, found that 83% of 165 patients aged 65 or older who had been hospitalized for COVID-19 reported at least one lasting symptom – problems like fatigue, shortness of breath, joint pain, and coughing – in the months after hospitalization. One-third of those had two symptoms, and 46% had three or more.

A similar study in Norway found that two-thirds of patients aged 60 or older reported reduced health-related quality of life during follow-up visits 6 months after hospitalization for COVID-19. The most-reported impairments among those patients were the inability to perform the tasks of daily life, reduced mobility, and increased pain and discomfort.
 

Cognitive concerns

Mounting evidence indicates that COVID-19 may contribute to chronic cognitive impairment in older adults. A multisite U.S. study found that 28% of 817 adults presenting to emergency departments with COVID-19 had delirium and poorer outcomes. A Chinese case-control study that enrolled 1,438 individuals hospitalized in Wuhan for COVID-19, along with 438 of their uninfected spouses, found that 12% of COVID-19 survivors experienced cognitive impairment a year after discharge. Matteo Tosato, MD, PhD, head of the outpatient clinic for patients with long COVID symptoms at Gemelli Hospital in Rome, called those findings “very concerning.”

Jin Ho Han, MD, associate professor of emergency medicine at Vanderbilt University, Nashville, Tenn., said cognitive impairment is common after an acute illness, particularly in frail or vulnerable patients.

“Hospitalization and the acute illness itself accelerate cognitive decline,” said Dr. Han, and previous evidence links delirium with worsening cognition. He and his colleagues are studying the potential role of delirium in longer-term cognitive decline in older patients after COVID-19.

Dr. Han emphasized the importance of preventing COVID-19-related delirium through vaccines and other strategies to reduce exposure of older patients to the virus. “Once you have cognitive decline, there are no interventions to reverse it,” he said.
 

Alarm bells for long-term care

Experts expressed concern that the situation might be even worse for people living in long-term care facilities. Many already need assistance with tasks of daily living and could be particularly vulnerable to lasting effects of COVID-19, said Karl Steinberg, MD, president of the Society for Post-Acute and Long-Term Care Medicine. He estimated that roughly half of his patients who have had COVID-19, regardless of the severity of their symptoms, have endured some degree of functional decline.

“It’s common for long-term care facility residents to experience functional and cognitive decline, even after seemingly minor things, like a cold or a trip to the hospital,” Dr. Steinberg, who has been a medical director of long-term care facilities in San Diego County for more than 2 decades, told this news organization. “It makes it a little harder to determine whether the declines we’ve been seeing post COVID in these residents are attributable to post COVID versus just an accelerated step in their overall expected decline.”

The pandemic may have contributed to worse outcomes for people in long-term care facilities in several ways: the disease itself, its effects on health care delivery, and necessary preventive measures to protect long-term care residents from exposure to the virus.

“During the many months where family visits were prohibited, we saw people – whether they had COVID-19 or not – suffer major clinical, functional, cognitive declines or severe psychological symptoms,” Dr. Steinberg said.

He emphasized the importance of preventive measures such as vaccines and boosters in patients in long-term care facilities. He said the benefit of preventing lasting symptoms is often a strong motivator for family caregivers of people with dementia to get them vaccinated or boosted.

“It’s clear that vaccination and booster reduce the incidence of post-COVID symptoms,” he said. Almost all studies have been in younger cohorts, but he expects the benefits would also apply to older patients.
 

Easing symptoms and offering support

As with long COVID generally, many questions remain about the causes of lasting symptoms of COVID-19 in older patients, and how best to treat them. Dr. Tosato, who led the study of long-COVID patients in Rome, is focusing on inflammation as a critical factor in the condition. He and colleagues across Europe hope to answer some of them by launching a multicenter study of lasting COVID-19 symptoms. 

In the meantime, Dr. Steinberg and Dr. Tosato said they are doing their best to evaluate and treat patients empirically.

“We pull from our armamentarium to treat system-specific symptoms,” Dr. Steinberg said. “We want to improve the quality of life and help each day be the best it can.”

Physicians in long-term care facilities might use medications such as antidepressants or nonpharmacologic approaches for patients experiencing depression symptoms. Families are also crucial in helping patients by bringing in home-cooked meals and encouraging loved ones who may be experiencing loss of taste or smell to eat, Dr. Steinberg said.

“We’ve seen with the return of families and loved ones visiting to some extent has alleviated some people’s symptoms, especially psychological ones,” he said.

Dr. Tosato said he and his colleagues start with an individualized, multidisciplinary assessment to determine what types of care may help. He noted that physicians might recommend medications or rehabilitative therapies depending on the patient’s needs.

“A personalized approach is key,” Dr. Tosato said. His study also found that the proportion of older patients experiencing symptoms declined over time – a glimmer of hope that many will recover. 

Dr. Cohen emphasized the need for a multimodal rehabilitation, an evidence-based approach used to care for patients who survived hospitalization with severe COVID-19 – a group that has substantially higher rates of persistent symptoms. This approach includes cognitive rehabilitation, physical therapy, occupational therapy, and a graded exercise program.

Dr. Han and colleagues are studying potential therapies such as cognitive rehabilitation in adults who’ve experienced delirium. But until evidence-based treatments are available, they stress the role of support for patients with cognitive decline and their families.   

“A lot of the work we do is teach patients and their families to compensate for newly acquired cognitive deficits from any illness, including COVID-19,” Dr. Han said.

Ms. Salant said she has experienced some improvement in her energy since her pulmonologist recommended a new inhaler based on her symptoms. Her sense of smell and taste, lost to the infection, returned after she received her first dose of a vaccine against COVID-19. She takes comfort in participating in Survivor Corps, a group of more than 170,000 COVID-19 survivors and their families who advocate for more scientific research on the disease.

She also expressed gratitude for the support she receives from her primary care physician, who she said has taken the time to learn more about the symptoms of long COVID, listens to her, and respects what she has to say.

“I have hope that I will keep getting better by baby steps,” Ms. Salant said. 

Dr. Tosato, Dr. Steinberg, and Dr. Han have disclosed no relevant financial relationships.

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

A digital algorithm using 24 patient characteristics identifies far more women who are likely to develop a postpartum hemorrhage than currently used tools to predict the risk for bleeding after delivery, according to a study published in the Journal of the American Medical Informatics Association.

About 1 in 10 of the roughly 700 pregnancy-related deaths in the United States are caused by postpartum hemorrhage, according to the U.S. Centers for Disease Control and Prevention. These deaths disproportionately occur among Black women, for whom studies show the risk of dying from a postpartum hemorrhage is fivefold greater than that of White women.

“Postpartum hemorrhage is a preventable medical emergency but remains the leading cause of maternal mortality globally,” the study’s senior author Li Li, MD, senior vice president of clinical informatics at Sema4, a company that uses artificial intelligence and machine learning to develop data-based clinical tools, told this news organization. “Early intervention is critical for reducing postpartum hemorrhage morbidity and mortality.”
 

Porous predictors

Existing tools for risk prediction are not particularly effective, Dr. Li said. For example, the American College of Obstetricians and Gynecologists’ (ACOG) Safe Motherhood Initiative offers checklists of clinical characteristics to classify women as low, medium, or high risk. However, 40% of the women classified as low risk based on this type of tool experience a hemorrhage.

ACOG also recommends quantifying blood loss during delivery or immediately after to identify women who are hemorrhaging, because imprecise estimates from clinicians may delay urgently needed care. Yet many hospitals have not implemented methods for measuring bleeding, said Dr. Li, who also is an assistant professor of genetics and genomic sciences at the Icahn School of Medicine at Mount Sinai, New York.

To develop a more precise way of identifying women at risk, Dr. Li and colleagues turned to artificial intelligence technology to create a “digital phenotype” based on approximately 72,000 births in the Mount Sinai Health System.

The digital tool retrospectively identified about 6,600 cases of postpartum hemorrhage, about 3.8 times the roughly 1,700 cases that would have been predicted based on methods that estimate blood loss. A blinded physician review of a subset of 45 patient charts – including 26 patients who experienced a hemorrhage, 11 who didn’t, and 6 with unclear outcomes – found that the digital approach was 89% percent accurate at identifying cases, whereas blood loss–based methods were accurate 67% of the time.

Several of the 24 characteristics included in the model appear in other risk predictors, including whether a woman has had a previous cesarean delivery or prior postdelivery bleeding and whether she has anemia or related blood disorders. Among the rest were risk factors that have been identified in the literature, including maternal blood pressure, time from admission to delivery, and average pulse during hospitalization. Five more features were new: red blood cell count and distribution width, mean corpuscular hemoglobin, absolute neutrophil count, and white blood cell count.

“These [new] values are easily obtainable from standard blood draws in the hospital but are not currently used in clinical practice to estimate postpartum hemorrhage risk,” Dr. Li said.

In a related retrospective study, Dr. Li and her colleagues used the new tool to classify women into high, low, or medium risk categories. They found that 28% of the women the algorithm classified as high risk experienced a postpartum hemorrhage compared with 15% to 19% of the women classified as high risk by standard predictive tools. They also identified potential “inflection points” where changes in vital signs may suggest a substantial increase in risk. For example, women whose median blood pressure during labor and delivery was above 132 mm Hg had an 11% average increase in their risk for bleeding. 

By more precisely identifying women at risk, the new method “could be used to pre-emptively allocate resources that can ultimately reduce postpartum hemorrhage morbidity and mortality,” Dr. Li said. Sema4 is launching a prospective clinical trial to further assess the algorithm, she added.  
 

Finding the continuum of risk

Holly Ende, MD, an obstetric anesthesiologist at Vanderbilt University Medical Center, Nashville, Tenn., said approaches that leverage electronic health records to identify women at risk for hemorrhage have many advantages over currently used tools.

“Machine learning models or statistical models are able to take into account many more risk factors and weigh each of those risk factors based on how much they contribute to risk,” Dr. Ende, who was not involved in the new studies, told this news organization. “We can stratify women more on a continuum.”

But digital approaches have potential downsides.

“Machine learning algorithms can be developed in such a way that perpetuates racial bias, and it’s important to be aware of potential biases in coded algorithms,” Dr. Li said. To help reduce such bias, they used a database that included a racially and ethnically diverse patient population, but she acknowledged that additional research is needed.

Dr. Ende, the coauthor of a commentary in Obstetrics & Gynecology on risk assessment for postpartum hemorrhage, said algorithm developers must be sensitive to pre-existing disparities in health care that may affect the data they use to build the software.

She pointed to uterine atony – a known risk factor for hemorrhage – as an example. In her own research, she and her colleagues identified women with atony by searching their medical records for medications used to treat the condition. But when they ran their model, Black women were less likely to develop uterine atony, which the team knew wasn’t true in the real world. They traced the problem to an existing disparity in obstetric care: Black women with uterine atony were less likely than women of other races to receive medications for the condition.

“People need to be cognizant as they are developing these types of prediction models and be extremely careful to avoid perpetuating any disparities in care,” Dr. Ende cautioned. On the other hand, if carefully developed, these tools might also help reduce disparities in health care by standardizing risk stratification and clinical practices, she said.

In addition to independent validation of data-based risk prediction tools, Dr. Ende said ensuring that clinicians are properly trained to use these tools is crucial.

“Implementation may be the biggest limitation,” she said.

Dr. Ende and Dr. Li have disclosed no relevant financial relationships.

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

A digital algorithm using 24 patient characteristics identifies far more women who are likely to develop a postpartum hemorrhage than currently used tools to predict the risk for bleeding after delivery, according to a study published in the Journal of the American Medical Informatics Association.

About 1 in 10 of the roughly 700 pregnancy-related deaths in the United States are caused by postpartum hemorrhage, according to the U.S. Centers for Disease Control and Prevention. These deaths disproportionately occur among Black women, for whom studies show the risk of dying from a postpartum hemorrhage is fivefold greater than that of White women.

“Postpartum hemorrhage is a preventable medical emergency but remains the leading cause of maternal mortality globally,” the study’s senior author Li Li, MD, senior vice president of clinical informatics at Sema4, a company that uses artificial intelligence and machine learning to develop data-based clinical tools, told this news organization. “Early intervention is critical for reducing postpartum hemorrhage morbidity and mortality.”
 

Porous predictors

Existing tools for risk prediction are not particularly effective, Dr. Li said. For example, the American College of Obstetricians and Gynecologists’ (ACOG) Safe Motherhood Initiative offers checklists of clinical characteristics to classify women as low, medium, or high risk. However, 40% of the women classified as low risk based on this type of tool experience a hemorrhage.

ACOG also recommends quantifying blood loss during delivery or immediately after to identify women who are hemorrhaging, because imprecise estimates from clinicians may delay urgently needed care. Yet many hospitals have not implemented methods for measuring bleeding, said Dr. Li, who also is an assistant professor of genetics and genomic sciences at the Icahn School of Medicine at Mount Sinai, New York.

To develop a more precise way of identifying women at risk, Dr. Li and colleagues turned to artificial intelligence technology to create a “digital phenotype” based on approximately 72,000 births in the Mount Sinai Health System.

The digital tool retrospectively identified about 6,600 cases of postpartum hemorrhage, about 3.8 times the roughly 1,700 cases that would have been predicted based on methods that estimate blood loss. A blinded physician review of a subset of 45 patient charts – including 26 patients who experienced a hemorrhage, 11 who didn’t, and 6 with unclear outcomes – found that the digital approach was 89% percent accurate at identifying cases, whereas blood loss–based methods were accurate 67% of the time.

Several of the 24 characteristics included in the model appear in other risk predictors, including whether a woman has had a previous cesarean delivery or prior postdelivery bleeding and whether she has anemia or related blood disorders. Among the rest were risk factors that have been identified in the literature, including maternal blood pressure, time from admission to delivery, and average pulse during hospitalization. Five more features were new: red blood cell count and distribution width, mean corpuscular hemoglobin, absolute neutrophil count, and white blood cell count.

“These [new] values are easily obtainable from standard blood draws in the hospital but are not currently used in clinical practice to estimate postpartum hemorrhage risk,” Dr. Li said.

In a related retrospective study, Dr. Li and her colleagues used the new tool to classify women into high, low, or medium risk categories. They found that 28% of the women the algorithm classified as high risk experienced a postpartum hemorrhage compared with 15% to 19% of the women classified as high risk by standard predictive tools. They also identified potential “inflection points” where changes in vital signs may suggest a substantial increase in risk. For example, women whose median blood pressure during labor and delivery was above 132 mm Hg had an 11% average increase in their risk for bleeding. 

By more precisely identifying women at risk, the new method “could be used to pre-emptively allocate resources that can ultimately reduce postpartum hemorrhage morbidity and mortality,” Dr. Li said. Sema4 is launching a prospective clinical trial to further assess the algorithm, she added.  
 

Finding the continuum of risk

Holly Ende, MD, an obstetric anesthesiologist at Vanderbilt University Medical Center, Nashville, Tenn., said approaches that leverage electronic health records to identify women at risk for hemorrhage have many advantages over currently used tools.

“Machine learning models or statistical models are able to take into account many more risk factors and weigh each of those risk factors based on how much they contribute to risk,” Dr. Ende, who was not involved in the new studies, told this news organization. “We can stratify women more on a continuum.”

But digital approaches have potential downsides.

“Machine learning algorithms can be developed in such a way that perpetuates racial bias, and it’s important to be aware of potential biases in coded algorithms,” Dr. Li said. To help reduce such bias, they used a database that included a racially and ethnically diverse patient population, but she acknowledged that additional research is needed.

Dr. Ende, the coauthor of a commentary in Obstetrics & Gynecology on risk assessment for postpartum hemorrhage, said algorithm developers must be sensitive to pre-existing disparities in health care that may affect the data they use to build the software.

She pointed to uterine atony – a known risk factor for hemorrhage – as an example. In her own research, she and her colleagues identified women with atony by searching their medical records for medications used to treat the condition. But when they ran their model, Black women were less likely to develop uterine atony, which the team knew wasn’t true in the real world. They traced the problem to an existing disparity in obstetric care: Black women with uterine atony were less likely than women of other races to receive medications for the condition.

“People need to be cognizant as they are developing these types of prediction models and be extremely careful to avoid perpetuating any disparities in care,” Dr. Ende cautioned. On the other hand, if carefully developed, these tools might also help reduce disparities in health care by standardizing risk stratification and clinical practices, she said.

In addition to independent validation of data-based risk prediction tools, Dr. Ende said ensuring that clinicians are properly trained to use these tools is crucial.

“Implementation may be the biggest limitation,” she said.

Dr. Ende and Dr. Li have disclosed no relevant financial relationships.

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

A digital algorithm using 24 patient characteristics identifies far more women who are likely to develop a postpartum hemorrhage than currently used tools to predict the risk for bleeding after delivery, according to a study published in the Journal of the American Medical Informatics Association.

About 1 in 10 of the roughly 700 pregnancy-related deaths in the United States are caused by postpartum hemorrhage, according to the U.S. Centers for Disease Control and Prevention. These deaths disproportionately occur among Black women, for whom studies show the risk of dying from a postpartum hemorrhage is fivefold greater than that of White women.

“Postpartum hemorrhage is a preventable medical emergency but remains the leading cause of maternal mortality globally,” the study’s senior author Li Li, MD, senior vice president of clinical informatics at Sema4, a company that uses artificial intelligence and machine learning to develop data-based clinical tools, told this news organization. “Early intervention is critical for reducing postpartum hemorrhage morbidity and mortality.”
 

Porous predictors

Existing tools for risk prediction are not particularly effective, Dr. Li said. For example, the American College of Obstetricians and Gynecologists’ (ACOG) Safe Motherhood Initiative offers checklists of clinical characteristics to classify women as low, medium, or high risk. However, 40% of the women classified as low risk based on this type of tool experience a hemorrhage.

ACOG also recommends quantifying blood loss during delivery or immediately after to identify women who are hemorrhaging, because imprecise estimates from clinicians may delay urgently needed care. Yet many hospitals have not implemented methods for measuring bleeding, said Dr. Li, who also is an assistant professor of genetics and genomic sciences at the Icahn School of Medicine at Mount Sinai, New York.

To develop a more precise way of identifying women at risk, Dr. Li and colleagues turned to artificial intelligence technology to create a “digital phenotype” based on approximately 72,000 births in the Mount Sinai Health System.

The digital tool retrospectively identified about 6,600 cases of postpartum hemorrhage, about 3.8 times the roughly 1,700 cases that would have been predicted based on methods that estimate blood loss. A blinded physician review of a subset of 45 patient charts – including 26 patients who experienced a hemorrhage, 11 who didn’t, and 6 with unclear outcomes – found that the digital approach was 89% percent accurate at identifying cases, whereas blood loss–based methods were accurate 67% of the time.

Several of the 24 characteristics included in the model appear in other risk predictors, including whether a woman has had a previous cesarean delivery or prior postdelivery bleeding and whether she has anemia or related blood disorders. Among the rest were risk factors that have been identified in the literature, including maternal blood pressure, time from admission to delivery, and average pulse during hospitalization. Five more features were new: red blood cell count and distribution width, mean corpuscular hemoglobin, absolute neutrophil count, and white blood cell count.

“These [new] values are easily obtainable from standard blood draws in the hospital but are not currently used in clinical practice to estimate postpartum hemorrhage risk,” Dr. Li said.

In a related retrospective study, Dr. Li and her colleagues used the new tool to classify women into high, low, or medium risk categories. They found that 28% of the women the algorithm classified as high risk experienced a postpartum hemorrhage compared with 15% to 19% of the women classified as high risk by standard predictive tools. They also identified potential “inflection points” where changes in vital signs may suggest a substantial increase in risk. For example, women whose median blood pressure during labor and delivery was above 132 mm Hg had an 11% average increase in their risk for bleeding. 

By more precisely identifying women at risk, the new method “could be used to pre-emptively allocate resources that can ultimately reduce postpartum hemorrhage morbidity and mortality,” Dr. Li said. Sema4 is launching a prospective clinical trial to further assess the algorithm, she added.  
 

Finding the continuum of risk

Holly Ende, MD, an obstetric anesthesiologist at Vanderbilt University Medical Center, Nashville, Tenn., said approaches that leverage electronic health records to identify women at risk for hemorrhage have many advantages over currently used tools.

“Machine learning models or statistical models are able to take into account many more risk factors and weigh each of those risk factors based on how much they contribute to risk,” Dr. Ende, who was not involved in the new studies, told this news organization. “We can stratify women more on a continuum.”

But digital approaches have potential downsides.

“Machine learning algorithms can be developed in such a way that perpetuates racial bias, and it’s important to be aware of potential biases in coded algorithms,” Dr. Li said. To help reduce such bias, they used a database that included a racially and ethnically diverse patient population, but she acknowledged that additional research is needed.

Dr. Ende, the coauthor of a commentary in Obstetrics & Gynecology on risk assessment for postpartum hemorrhage, said algorithm developers must be sensitive to pre-existing disparities in health care that may affect the data they use to build the software.

She pointed to uterine atony – a known risk factor for hemorrhage – as an example. In her own research, she and her colleagues identified women with atony by searching their medical records for medications used to treat the condition. But when they ran their model, Black women were less likely to develop uterine atony, which the team knew wasn’t true in the real world. They traced the problem to an existing disparity in obstetric care: Black women with uterine atony were less likely than women of other races to receive medications for the condition.

“People need to be cognizant as they are developing these types of prediction models and be extremely careful to avoid perpetuating any disparities in care,” Dr. Ende cautioned. On the other hand, if carefully developed, these tools might also help reduce disparities in health care by standardizing risk stratification and clinical practices, she said.

In addition to independent validation of data-based risk prediction tools, Dr. Ende said ensuring that clinicians are properly trained to use these tools is crucial.

“Implementation may be the biggest limitation,” she said.

Dr. Ende and Dr. Li have disclosed no relevant financial relationships.

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