Rheumatoid Arthritis

Key clinical point: Ultrasound detected subclinical inflammation in the wrist joints of most patients with rheumatoid arthritis (RA) in clinical remission or with lower disease activity, with the risk for subclinical inflammation being lower among those using biologic therapy.

Major finding: Overall, subclinical inflammation was detected in 57.4% of the patients in complete remission or with lower disease activity. Factors negatively associated with subclinical inflammation included the use of biologic therapy (odds ratio [OR] 0.59; P = .001), methotrexate (OR 0.83; P = .020), and glucocorticoids (OR 0.60; P = .001) and alcohol consumption (OR 0.55; P = .006).

Study details: This cross-sectional study included 1248 patients with RA who underwent gray scale and power Doppler ultrasound assessments of the dorsal radiolunate joints of both wrists.

Disclosures: This study was supported by the Kaohsiung Chang Gung Memorial Hospital, Taiwan, and other sources. The authors declared no conflicts of interest.

Source: Wang YW et al. Factors associated with subclinical inflammation of wrist joints in rheumatoid arthritis patients with low or no disease activity—A RA ultrasound registry study. BMC Musculoskelet Disord. 2023;24:438 (May 30). doi: 10.1186/s12891-023-06521-8

Key clinical point: Ultrasound detected subclinical inflammation in the wrist joints of most patients with rheumatoid arthritis (RA) in clinical remission or with lower disease activity, with the risk for subclinical inflammation being lower among those using biologic therapy.

Major finding: Overall, subclinical inflammation was detected in 57.4% of the patients in complete remission or with lower disease activity. Factors negatively associated with subclinical inflammation included the use of biologic therapy (odds ratio [OR] 0.59; P = .001), methotrexate (OR 0.83; P = .020), and glucocorticoids (OR 0.60; P = .001) and alcohol consumption (OR 0.55; P = .006).

Study details: This cross-sectional study included 1248 patients with RA who underwent gray scale and power Doppler ultrasound assessments of the dorsal radiolunate joints of both wrists.

Disclosures: This study was supported by the Kaohsiung Chang Gung Memorial Hospital, Taiwan, and other sources. The authors declared no conflicts of interest.

Source: Wang YW et al. Factors associated with subclinical inflammation of wrist joints in rheumatoid arthritis patients with low or no disease activity—A RA ultrasound registry study. BMC Musculoskelet Disord. 2023;24:438 (May 30). doi: 10.1186/s12891-023-06521-8

Key clinical point: Ultrasound detected subclinical inflammation in the wrist joints of most patients with rheumatoid arthritis (RA) in clinical remission or with lower disease activity, with the risk for subclinical inflammation being lower among those using biologic therapy.

Major finding: Overall, subclinical inflammation was detected in 57.4% of the patients in complete remission or with lower disease activity. Factors negatively associated with subclinical inflammation included the use of biologic therapy (odds ratio [OR] 0.59; P = .001), methotrexate (OR 0.83; P = .020), and glucocorticoids (OR 0.60; P = .001) and alcohol consumption (OR 0.55; P = .006).

Study details: This cross-sectional study included 1248 patients with RA who underwent gray scale and power Doppler ultrasound assessments of the dorsal radiolunate joints of both wrists.

Disclosures: This study was supported by the Kaohsiung Chang Gung Memorial Hospital, Taiwan, and other sources. The authors declared no conflicts of interest.

Source: Wang YW et al. Factors associated with subclinical inflammation of wrist joints in rheumatoid arthritis patients with low or no disease activity—A RA ultrasound registry study. BMC Musculoskelet Disord. 2023;24:438 (May 30). doi: 10.1186/s12891-023-06521-8

Key clinical point: Depression significantly predicted death in patients with incident rheumatoid arthritis (RA), but with a strength similar to that in matched comparator individuals without RA.

Major finding: The risk for all-cause mortality was >3-fold higher (adjusted hazard rate ratio [aHRR] 3.15; 95% CI 2.62-3.79) in patients with RA with vs without depression, with the risk being higher among patients age < 55 years compared with other age groups (aHRR 8.13; 95% CI 3.89-17.02). In addition, depression predicted all-cause mortality with similar strength in comparator individuals without RA (aHRR 3.77; 95% CI 3.48-4.08).

Study details: This study included 11,071 patients with incident RA and 55,355 matched comparator individuals without RA from the general population.

Disclosures: This study was supported by the Danish Rheumatism Association. The authors declared no conflicts of interest.

Source: Pedersen JK et al. Mortality in patients with incident rheumatoid arthritis and depression: A Danish cohort study of 11,071 patients and 55,355 comparators. Rheumatology (Oxford). 2023 (May 30). doi: 10.1093/rheumatology/kead259

Key clinical point: Depression significantly predicted death in patients with incident rheumatoid arthritis (RA), but with a strength similar to that in matched comparator individuals without RA.

Major finding: The risk for all-cause mortality was >3-fold higher (adjusted hazard rate ratio [aHRR] 3.15; 95% CI 2.62-3.79) in patients with RA with vs without depression, with the risk being higher among patients age < 55 years compared with other age groups (aHRR 8.13; 95% CI 3.89-17.02). In addition, depression predicted all-cause mortality with similar strength in comparator individuals without RA (aHRR 3.77; 95% CI 3.48-4.08).

Study details: This study included 11,071 patients with incident RA and 55,355 matched comparator individuals without RA from the general population.

Disclosures: This study was supported by the Danish Rheumatism Association. The authors declared no conflicts of interest.

Source: Pedersen JK et al. Mortality in patients with incident rheumatoid arthritis and depression: A Danish cohort study of 11,071 patients and 55,355 comparators. Rheumatology (Oxford). 2023 (May 30). doi: 10.1093/rheumatology/kead259

Key clinical point: Depression significantly predicted death in patients with incident rheumatoid arthritis (RA), but with a strength similar to that in matched comparator individuals without RA.

Major finding: The risk for all-cause mortality was >3-fold higher (adjusted hazard rate ratio [aHRR] 3.15; 95% CI 2.62-3.79) in patients with RA with vs without depression, with the risk being higher among patients age < 55 years compared with other age groups (aHRR 8.13; 95% CI 3.89-17.02). In addition, depression predicted all-cause mortality with similar strength in comparator individuals without RA (aHRR 3.77; 95% CI 3.48-4.08).

Study details: This study included 11,071 patients with incident RA and 55,355 matched comparator individuals without RA from the general population.

Disclosures: This study was supported by the Danish Rheumatism Association. The authors declared no conflicts of interest.

Source: Pedersen JK et al. Mortality in patients with incident rheumatoid arthritis and depression: A Danish cohort study of 11,071 patients and 55,355 comparators. Rheumatology (Oxford). 2023 (May 30). doi: 10.1093/rheumatology/kead259

Key clinical point: Perioperative use of Janus kinase inhibitors (JAKi) seemed safe in patients with rheumatoid arthritis (RA) undergoing orthopedic procedures; however, the benefits of withholding JAKi to prevent postoperative complications should be balanced against the risk for a flare-up in disease activity.

Major finding: Overall, 20 patients undergoing 31 orthopedic procedures continued JAKi perioperatively, whereas 16 patients undergoing 18 procedures discontinued JAKi perioperatively by ≥1 dose for various reasons. No surgical site infections were reported during ≥90 days of follow-up. Disease flare-up was observed in 2 patients who discontinued JAKi for 3 and 14 days, respectively; however, those who discontinued JAKi for ≤1 day showed no flare-up.

Study details: This retrospective study included 32 patients with RA who had disease under control with JAKi and underwent a total of 49 orthopedic procedures.

Disclosures: This study did not receive any funding, grants, or other support. K Nishida declared receiving research grants or speaker fees from various sources.

Source: Nishida K et al. Influence of Janus kinase inhibitors on early postoperative complications in patients with rheumatoid arthritis undergoing orthopaedic surgeries. Mod Rheumatol. 2023 (Jun 3). doi: 10.1093/mr/road047

Key clinical point: Perioperative use of Janus kinase inhibitors (JAKi) seemed safe in patients with rheumatoid arthritis (RA) undergoing orthopedic procedures; however, the benefits of withholding JAKi to prevent postoperative complications should be balanced against the risk for a flare-up in disease activity.

Major finding: Overall, 20 patients undergoing 31 orthopedic procedures continued JAKi perioperatively, whereas 16 patients undergoing 18 procedures discontinued JAKi perioperatively by ≥1 dose for various reasons. No surgical site infections were reported during ≥90 days of follow-up. Disease flare-up was observed in 2 patients who discontinued JAKi for 3 and 14 days, respectively; however, those who discontinued JAKi for ≤1 day showed no flare-up.

Study details: This retrospective study included 32 patients with RA who had disease under control with JAKi and underwent a total of 49 orthopedic procedures.

Disclosures: This study did not receive any funding, grants, or other support. K Nishida declared receiving research grants or speaker fees from various sources.

Source: Nishida K et al. Influence of Janus kinase inhibitors on early postoperative complications in patients with rheumatoid arthritis undergoing orthopaedic surgeries. Mod Rheumatol. 2023 (Jun 3). doi: 10.1093/mr/road047

Key clinical point: Perioperative use of Janus kinase inhibitors (JAKi) seemed safe in patients with rheumatoid arthritis (RA) undergoing orthopedic procedures; however, the benefits of withholding JAKi to prevent postoperative complications should be balanced against the risk for a flare-up in disease activity.

Major finding: Overall, 20 patients undergoing 31 orthopedic procedures continued JAKi perioperatively, whereas 16 patients undergoing 18 procedures discontinued JAKi perioperatively by ≥1 dose for various reasons. No surgical site infections were reported during ≥90 days of follow-up. Disease flare-up was observed in 2 patients who discontinued JAKi for 3 and 14 days, respectively; however, those who discontinued JAKi for ≤1 day showed no flare-up.

Study details: This retrospective study included 32 patients with RA who had disease under control with JAKi and underwent a total of 49 orthopedic procedures.

Disclosures: This study did not receive any funding, grants, or other support. K Nishida declared receiving research grants or speaker fees from various sources.

Source: Nishida K et al. Influence of Janus kinase inhibitors on early postoperative complications in patients with rheumatoid arthritis undergoing orthopaedic surgeries. Mod Rheumatol. 2023 (Jun 3). doi: 10.1093/mr/road047

Key clinical point: Hydroxychloroquine treatment conferred survival benefits in a dose-dependent manner in patients with elderly-onset rheumatoid arthritis (RA), with patients receiving a monthly cumulative dose of 1374.5-5778.5 mg or more showing better survival than those receiving <1374.5 mg.

Major finding: Hydroxychloroquine treatment was a protective factor against mortality in patients with elderly-onset RA (hazard ratio 0.30; P = .002), with a cumulative dose of <1374.5 mg vs 1374.5-5,778.5 mg or more leading to the lowest survival rate (P < .001).

Study details: Findings are from a retrospective observational study including 980 patients with elderly-onset RA (disease onset after 60 years of age) who had received conventional synthetic, biologic, or targeted synthetic disease-modifying antirheumatic drugs.

Disclosures: This study was supported by the National Science and Technology Council, Taiwan, and other sources. The authors declared no conflicts of interest.

Source: Lin CT et al. Association of hydroxychloroquine use with a dose-dependent decrease in mortality risk in patients with elderly-onset rheumatoid arthritis. Rheumatol Ther. 2023 (May 12). Doi: 10.1007/s40744-023-00561-1

Key clinical point: Hydroxychloroquine treatment conferred survival benefits in a dose-dependent manner in patients with elderly-onset rheumatoid arthritis (RA), with patients receiving a monthly cumulative dose of 1374.5-5778.5 mg or more showing better survival than those receiving <1374.5 mg.

Major finding: Hydroxychloroquine treatment was a protective factor against mortality in patients with elderly-onset RA (hazard ratio 0.30; P = .002), with a cumulative dose of <1374.5 mg vs 1374.5-5,778.5 mg or more leading to the lowest survival rate (P < .001).

Study details: Findings are from a retrospective observational study including 980 patients with elderly-onset RA (disease onset after 60 years of age) who had received conventional synthetic, biologic, or targeted synthetic disease-modifying antirheumatic drugs.

Disclosures: This study was supported by the National Science and Technology Council, Taiwan, and other sources. The authors declared no conflicts of interest.

Source: Lin CT et al. Association of hydroxychloroquine use with a dose-dependent decrease in mortality risk in patients with elderly-onset rheumatoid arthritis. Rheumatol Ther. 2023 (May 12). Doi: 10.1007/s40744-023-00561-1

Key clinical point: Hydroxychloroquine treatment conferred survival benefits in a dose-dependent manner in patients with elderly-onset rheumatoid arthritis (RA), with patients receiving a monthly cumulative dose of 1374.5-5778.5 mg or more showing better survival than those receiving <1374.5 mg.

Major finding: Hydroxychloroquine treatment was a protective factor against mortality in patients with elderly-onset RA (hazard ratio 0.30; P = .002), with a cumulative dose of <1374.5 mg vs 1374.5-5,778.5 mg or more leading to the lowest survival rate (P < .001).

Study details: Findings are from a retrospective observational study including 980 patients with elderly-onset RA (disease onset after 60 years of age) who had received conventional synthetic, biologic, or targeted synthetic disease-modifying antirheumatic drugs.

Disclosures: This study was supported by the National Science and Technology Council, Taiwan, and other sources. The authors declared no conflicts of interest.

Source: Lin CT et al. Association of hydroxychloroquine use with a dose-dependent decrease in mortality risk in patients with elderly-onset rheumatoid arthritis. Rheumatol Ther. 2023 (May 12). Doi: 10.1007/s40744-023-00561-1

Key clinical point: Tofacitinib use increased the risk for herpes zoster (HZ) in patients with rheumatoid arthritis (RA) compared with tumor necrosis factor inhibitor (TNFi); however, the rate of serious HZ or tofacitinib discontinuation due to HZ was low.

Major finding: The incidence of HZ was significantly higher among patients receiving tofacitinib vs TNFi (incidence rate ratio 8.33; P < .001). However, the incidence of serious HZ was not significantly different between the groups (P = .452), with HZ leading to only one case of permanent tofacitinib discontinuation.

Study details: This study included 912 patients with RA from two single-center prospective cohorts (tofacitinib cohort n = 200 and TNFi cohort n = 712).

Disclosures: This study was supported by the Ministry of Health and Welfare, Republic of Korea, and Pfizer. Two authors declared being employees and shareholders of Pfizer Inc. YK Sung declared receiving research grants from Pfizer and other sources. The other authors declared no conflicts of interest.

Source: Song YJ et al. Increased risk of herpes zoster with tofacitinib treatment in Korean patients with rheumatoid arthritis: A single‑center prospective study. Sci Rep. 2023;13:7877 (May 15). doi: 10.1038/s41598-023-33718-7

Key clinical point: Tofacitinib use increased the risk for herpes zoster (HZ) in patients with rheumatoid arthritis (RA) compared with tumor necrosis factor inhibitor (TNFi); however, the rate of serious HZ or tofacitinib discontinuation due to HZ was low.

Major finding: The incidence of HZ was significantly higher among patients receiving tofacitinib vs TNFi (incidence rate ratio 8.33; P < .001). However, the incidence of serious HZ was not significantly different between the groups (P = .452), with HZ leading to only one case of permanent tofacitinib discontinuation.

Study details: This study included 912 patients with RA from two single-center prospective cohorts (tofacitinib cohort n = 200 and TNFi cohort n = 712).

Disclosures: This study was supported by the Ministry of Health and Welfare, Republic of Korea, and Pfizer. Two authors declared being employees and shareholders of Pfizer Inc. YK Sung declared receiving research grants from Pfizer and other sources. The other authors declared no conflicts of interest.

Source: Song YJ et al. Increased risk of herpes zoster with tofacitinib treatment in Korean patients with rheumatoid arthritis: A single‑center prospective study. Sci Rep. 2023;13:7877 (May 15). doi: 10.1038/s41598-023-33718-7

Key clinical point: Tofacitinib use increased the risk for herpes zoster (HZ) in patients with rheumatoid arthritis (RA) compared with tumor necrosis factor inhibitor (TNFi); however, the rate of serious HZ or tofacitinib discontinuation due to HZ was low.

Major finding: The incidence of HZ was significantly higher among patients receiving tofacitinib vs TNFi (incidence rate ratio 8.33; P < .001). However, the incidence of serious HZ was not significantly different between the groups (P = .452), with HZ leading to only one case of permanent tofacitinib discontinuation.

Study details: This study included 912 patients with RA from two single-center prospective cohorts (tofacitinib cohort n = 200 and TNFi cohort n = 712).

Disclosures: This study was supported by the Ministry of Health and Welfare, Republic of Korea, and Pfizer. Two authors declared being employees and shareholders of Pfizer Inc. YK Sung declared receiving research grants from Pfizer and other sources. The other authors declared no conflicts of interest.

Source: Song YJ et al. Increased risk of herpes zoster with tofacitinib treatment in Korean patients with rheumatoid arthritis: A single‑center prospective study. Sci Rep. 2023;13:7877 (May 15). doi: 10.1038/s41598-023-33718-7

Key clinical point: Frailty is a significant contributing factor leading to methotrexate discontinuation due to adverse events in long-term pretreated patients with rheumatoid arthritis (RA).

Major finding: Overall, 7.4% of the patients discontinued methotrexate due to adverse events during 2 years of follow-up, with methotrexate retention being significantly lower among patients with vs without frailty (P < .05) and frailty being a significant factor contributing to methotrexate discontinuation (adjusted hazard ratio 2.34; 95% CI 1.02-5.37).

Study details: This retrospective longitudinal study included 323 patients with RA who used methotrexate at baseline.

Disclosures: This study did not declare the funding source. The authors did not report conflicts of interest.

Source: Sobue Y et al. Relationship between frailty and methotrexate discontinuation due to adverse events in rheumatoid arthritis patients. Clin Rheumatol. 2023 (May 22). doi: 10.1007/s10067-023-06639-z

Key clinical point: Frailty is a significant contributing factor leading to methotrexate discontinuation due to adverse events in long-term pretreated patients with rheumatoid arthritis (RA).

Major finding: Overall, 7.4% of the patients discontinued methotrexate due to adverse events during 2 years of follow-up, with methotrexate retention being significantly lower among patients with vs without frailty (P < .05) and frailty being a significant factor contributing to methotrexate discontinuation (adjusted hazard ratio 2.34; 95% CI 1.02-5.37).

Study details: This retrospective longitudinal study included 323 patients with RA who used methotrexate at baseline.

Disclosures: This study did not declare the funding source. The authors did not report conflicts of interest.

Source: Sobue Y et al. Relationship between frailty and methotrexate discontinuation due to adverse events in rheumatoid arthritis patients. Clin Rheumatol. 2023 (May 22). doi: 10.1007/s10067-023-06639-z

Key clinical point: Frailty is a significant contributing factor leading to methotrexate discontinuation due to adverse events in long-term pretreated patients with rheumatoid arthritis (RA).

Major finding: Overall, 7.4% of the patients discontinued methotrexate due to adverse events during 2 years of follow-up, with methotrexate retention being significantly lower among patients with vs without frailty (P < .05) and frailty being a significant factor contributing to methotrexate discontinuation (adjusted hazard ratio 2.34; 95% CI 1.02-5.37).

Study details: This retrospective longitudinal study included 323 patients with RA who used methotrexate at baseline.

Disclosures: This study did not declare the funding source. The authors did not report conflicts of interest.

Source: Sobue Y et al. Relationship between frailty and methotrexate discontinuation due to adverse events in rheumatoid arthritis patients. Clin Rheumatol. 2023 (May 22). doi: 10.1007/s10067-023-06639-z

Key clinical point: Concomitant use of antimalarials with biologic disease-modifying antirheumatic drugs (bDMARD) or Janus kinase inhibitors (JAKi) improved the overall safety profile and persistence of treatment in patients with rheumatoid arthritis (RA).

Major finding: The concomitant use vs nonuse of antimalarials was associated with a reduced risk for serious adverse events (multivariate incidence rate ratios [mIRR] 0.49; P < .001), total adverse events (mIRR 0.68; P < .001), and serious infections (mIRR 0.53; P = .007) and with longer survival of treatment course (hazard ratio 0.72; P = .003).

Study details: Findings are from a registry-based cohort study including 1316 patients with RA who initiated their first bDMARD or JAKi with (n = 280) or without (n = 1,036) concomitant antimalarials.

Disclosures: This study was supported by the Brazilian Society of Rheumatology and other sources. The authors declared no conflicts of interest.

Source: Bredemeier M et al, for the Brazilian Society of Rheumatology and the Brazilian Registry of Biological Therapies in Rheumatic Diseases (BiobadaBrasil). The effect of antimalarials on the safety and persistence of treatment with biologic agents or JAK inhibitors in rheumatoid arthritis. Rheumatology (Oxford). 2023 (May 22). doi: 10.1093/rheumatology/kead232

Key clinical point: Concomitant use of antimalarials with biologic disease-modifying antirheumatic drugs (bDMARD) or Janus kinase inhibitors (JAKi) improved the overall safety profile and persistence of treatment in patients with rheumatoid arthritis (RA).

Major finding: The concomitant use vs nonuse of antimalarials was associated with a reduced risk for serious adverse events (multivariate incidence rate ratios [mIRR] 0.49; P < .001), total adverse events (mIRR 0.68; P < .001), and serious infections (mIRR 0.53; P = .007) and with longer survival of treatment course (hazard ratio 0.72; P = .003).

Study details: Findings are from a registry-based cohort study including 1316 patients with RA who initiated their first bDMARD or JAKi with (n = 280) or without (n = 1,036) concomitant antimalarials.

Disclosures: This study was supported by the Brazilian Society of Rheumatology and other sources. The authors declared no conflicts of interest.

Source: Bredemeier M et al, for the Brazilian Society of Rheumatology and the Brazilian Registry of Biological Therapies in Rheumatic Diseases (BiobadaBrasil). The effect of antimalarials on the safety and persistence of treatment with biologic agents or JAK inhibitors in rheumatoid arthritis. Rheumatology (Oxford). 2023 (May 22). doi: 10.1093/rheumatology/kead232

Key clinical point: Concomitant use of antimalarials with biologic disease-modifying antirheumatic drugs (bDMARD) or Janus kinase inhibitors (JAKi) improved the overall safety profile and persistence of treatment in patients with rheumatoid arthritis (RA).

Major finding: The concomitant use vs nonuse of antimalarials was associated with a reduced risk for serious adverse events (multivariate incidence rate ratios [mIRR] 0.49; P < .001), total adverse events (mIRR 0.68; P < .001), and serious infections (mIRR 0.53; P = .007) and with longer survival of treatment course (hazard ratio 0.72; P = .003).

Study details: Findings are from a registry-based cohort study including 1316 patients with RA who initiated their first bDMARD or JAKi with (n = 280) or without (n = 1,036) concomitant antimalarials.

Disclosures: This study was supported by the Brazilian Society of Rheumatology and other sources. The authors declared no conflicts of interest.

Source: Bredemeier M et al, for the Brazilian Society of Rheumatology and the Brazilian Registry of Biological Therapies in Rheumatic Diseases (BiobadaBrasil). The effect of antimalarials on the safety and persistence of treatment with biologic agents or JAK inhibitors in rheumatoid arthritis. Rheumatology (Oxford). 2023 (May 22). doi: 10.1093/rheumatology/kead232

Key clinical point: Peresolimab, a humanized antibody stimulating the programmed cell death protein 1 inhibitory pathway, showed significant efficacy compared with placebo in improving disease activity in patients with moderate-to-severe rheumatoid arthritis (RA).

Major finding: At week 12, 700 mg peresolimab vs placebo was associated with a significantly greater change in Disease Activity Scores for 28 joints based on C-reactive protein levels (between-group difference in change from baseline −1.09; P < .001). The safety profiles were similar in all treatment groups, and no deaths were reported.

Study details: This phase 2a trial included 98 patients with moderate-to-severe RA and inadequate or loss of response to or unacceptable side effects with conventional synthetic disease-modifying antirheumatic drugs who were randomly assigned to receive peresolimab (300 or 700 mg) or placebo once every 4 weeks.

Disclosures: This study was supported by Eli Lilly. Five authors declared being employees of or owning stocks in Eli Lilly. Several authors declared ties with various sources, including Eli Lilly.

Source: Tuttle J et al. A phase 2 trial of peresolimab for adults with rheumatoid arthritis. N Engl J Med. 2023;388:1853-1862 (May 18). doi: 10.1056/NEJMoa2209856

Key clinical point: Peresolimab, a humanized antibody stimulating the programmed cell death protein 1 inhibitory pathway, showed significant efficacy compared with placebo in improving disease activity in patients with moderate-to-severe rheumatoid arthritis (RA).

Major finding: At week 12, 700 mg peresolimab vs placebo was associated with a significantly greater change in Disease Activity Scores for 28 joints based on C-reactive protein levels (between-group difference in change from baseline −1.09; P < .001). The safety profiles were similar in all treatment groups, and no deaths were reported.

Study details: This phase 2a trial included 98 patients with moderate-to-severe RA and inadequate or loss of response to or unacceptable side effects with conventional synthetic disease-modifying antirheumatic drugs who were randomly assigned to receive peresolimab (300 or 700 mg) or placebo once every 4 weeks.

Disclosures: This study was supported by Eli Lilly. Five authors declared being employees of or owning stocks in Eli Lilly. Several authors declared ties with various sources, including Eli Lilly.

Source: Tuttle J et al. A phase 2 trial of peresolimab for adults with rheumatoid arthritis. N Engl J Med. 2023;388:1853-1862 (May 18). doi: 10.1056/NEJMoa2209856

Key clinical point: Peresolimab, a humanized antibody stimulating the programmed cell death protein 1 inhibitory pathway, showed significant efficacy compared with placebo in improving disease activity in patients with moderate-to-severe rheumatoid arthritis (RA).

Major finding: At week 12, 700 mg peresolimab vs placebo was associated with a significantly greater change in Disease Activity Scores for 28 joints based on C-reactive protein levels (between-group difference in change from baseline −1.09; P < .001). The safety profiles were similar in all treatment groups, and no deaths were reported.

Study details: This phase 2a trial included 98 patients with moderate-to-severe RA and inadequate or loss of response to or unacceptable side effects with conventional synthetic disease-modifying antirheumatic drugs who were randomly assigned to receive peresolimab (300 or 700 mg) or placebo once every 4 weeks.

Disclosures: This study was supported by Eli Lilly. Five authors declared being employees of or owning stocks in Eli Lilly. Several authors declared ties with various sources, including Eli Lilly.

Source: Tuttle J et al. A phase 2 trial of peresolimab for adults with rheumatoid arthritis. N Engl J Med. 2023;388:1853-1862 (May 18). doi: 10.1056/NEJMoa2209856

Adalimumab, sold under the brand name Humira, enjoyed a long run as one of the world’s best-selling medicines. But its 20-year, competition-free period has ended, and despite its best efforts to delay their arrival, drug manufacturer AbbVie now faces increasing competition from biosimilars entering the marketplace.
 

But one biosimilar about to be launched may be something of a game changer. Coherus BioSciences has announced plans to market its biosimilar Yusimry (adalimumab-aqvh) at a cost of $995 for two autoinjectors. This represents an approximate 85% discount over Humira’s sale list price of $6922.

This price, however, is slated to plunge even further as Coherus has also revealed that it will work with the Mark Cuban Cost Plus Drug Company (MCCPDC) to offer an even lower price. When Yusimry launches in July, it will sell for about $579 for two autoinjectors, making it the lowest-priced adalimumab biosimilar on the market.

“Coherus and Cost Plus Drug Company share a common mission, to increase access to high-quality medicine for patients at an affordable price,” said Dennis Lanfear, MBA, president, CEO and chairman of Coherus. “Mark Cuban and his team offer innovative solutions to health care problems, and Coherus is also a highly innovative company focused on unmet patient needs.”

He noted that, with adalimumab biosimilar pricing, this translates to a low list price approach. “We are pleased that Yusimry will be a part of that, as the first biologic they carry,” Mr. Lanfear said.

MCCPDC prices are based on the cost of ingredients and manufacturing plus 15% margin, a $3 pharmacy dispensing fee, and a $5 shipping fee. The company has expanded its inventory from 100 generics to more than 350 medications since it launched in January 2022. While MCCPDC is primarily directed to people who are paying cash for drugs, it does take insurance from select plans. And even for people who are covered by other insurers, the cost of drugs from Mr. Cuban’s company may be less than their out-of-pocket costs if they did go through their payer.

The low pricing of Yusimry is welcome, said Marcus Snow, MD, an assistant professor in the division of rheumatology at the University of Nebraska Medical Center, Omaha, but he pointed out that it is still a very expensive drug. “For patients who can’t afford Humira due to poor insurance coverage and high out-of-pocket costs, it is a welcome option. But it’s also unclear how many patients who lack adequate health insurance coverage can afford to pay $579 a month out of their own pockets.”
 

The biosimilars are coming

By early December 2022, the Food and Drug Administration had approved seven Humira biosimilars, and Amgen launched the first biosimilar to come on the market, Amjevita, soon afterward. By July 2023, half a dozen more are expected to enter the marketplace, said Steven Horvitz, managing director of EMC Analytics Group, a pharmaceutical research firm.

Mr. Horvitz agrees that the system is out of control, but it is unclear how much of an effect the low price tag on the Coherus product will have. “Some insurers may say, ‘we want the lowest price, and we don’t care about rebates,’ and will go with it,” he said. “PBMs [pharmacy benefit managers] are all about economics, so we have to see how many of their major clients will ask for the lowest price.”

Amgen has more or less followed the status quo on pricing for its biosimilar, but with a twist. It›s being offered at two different prices: $85,494 a year, which is only a 5% discount from Humira’s list price, or at $40,497 a year, a 55% discount. However, to date, the lower price has generally not been granted favorable formulary placement by PBMs. The plans that adopt the higher-priced biosimilar will get bigger rebates, but patients with coinsurance and deductibles will pay more out of pocket.

It is yet unknown how the pricing on Yusimry will affect the biosimilars ready to launch. “Will it give them pause for thought or not make any difference?” Mr. Horvitz said. “The companies do not reveal their pricing before the fact, so we have to wait and see.”

Large PBMs have not jumped at the opportunity to offer the Coherus biosimilar, but SmithRx, which bills itself as “next-generation pharmacy benefits management,” announced that it will offer Yusimry to its members at a discount of more than 90%.

“Unlike traditional PBMs, SmithRx prioritizes transparency and up-front cost savings. Humira is often an employer’s top drug expense so offering a low-cost alternative will have significant impact,” Jake Frenz, CEO and founder of SmithRx, said in a statement. “We’re excited to work with Cost Plus Drugs to bring this biosimilar to our members – and significantly reduce costs for them and their employers.”

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

Adalimumab, sold under the brand name Humira, enjoyed a long run as one of the world’s best-selling medicines. But its 20-year, competition-free period has ended, and despite its best efforts to delay their arrival, drug manufacturer AbbVie now faces increasing competition from biosimilars entering the marketplace.
 

But one biosimilar about to be launched may be something of a game changer. Coherus BioSciences has announced plans to market its biosimilar Yusimry (adalimumab-aqvh) at a cost of $995 for two autoinjectors. This represents an approximate 85% discount over Humira’s sale list price of $6922.

This price, however, is slated to plunge even further as Coherus has also revealed that it will work with the Mark Cuban Cost Plus Drug Company (MCCPDC) to offer an even lower price. When Yusimry launches in July, it will sell for about $579 for two autoinjectors, making it the lowest-priced adalimumab biosimilar on the market.

“Coherus and Cost Plus Drug Company share a common mission, to increase access to high-quality medicine for patients at an affordable price,” said Dennis Lanfear, MBA, president, CEO and chairman of Coherus. “Mark Cuban and his team offer innovative solutions to health care problems, and Coherus is also a highly innovative company focused on unmet patient needs.”

He noted that, with adalimumab biosimilar pricing, this translates to a low list price approach. “We are pleased that Yusimry will be a part of that, as the first biologic they carry,” Mr. Lanfear said.

MCCPDC prices are based on the cost of ingredients and manufacturing plus 15% margin, a $3 pharmacy dispensing fee, and a $5 shipping fee. The company has expanded its inventory from 100 generics to more than 350 medications since it launched in January 2022. While MCCPDC is primarily directed to people who are paying cash for drugs, it does take insurance from select plans. And even for people who are covered by other insurers, the cost of drugs from Mr. Cuban’s company may be less than their out-of-pocket costs if they did go through their payer.

The low pricing of Yusimry is welcome, said Marcus Snow, MD, an assistant professor in the division of rheumatology at the University of Nebraska Medical Center, Omaha, but he pointed out that it is still a very expensive drug. “For patients who can’t afford Humira due to poor insurance coverage and high out-of-pocket costs, it is a welcome option. But it’s also unclear how many patients who lack adequate health insurance coverage can afford to pay $579 a month out of their own pockets.”
 

The biosimilars are coming

By early December 2022, the Food and Drug Administration had approved seven Humira biosimilars, and Amgen launched the first biosimilar to come on the market, Amjevita, soon afterward. By July 2023, half a dozen more are expected to enter the marketplace, said Steven Horvitz, managing director of EMC Analytics Group, a pharmaceutical research firm.

Mr. Horvitz agrees that the system is out of control, but it is unclear how much of an effect the low price tag on the Coherus product will have. “Some insurers may say, ‘we want the lowest price, and we don’t care about rebates,’ and will go with it,” he said. “PBMs [pharmacy benefit managers] are all about economics, so we have to see how many of their major clients will ask for the lowest price.”

Amgen has more or less followed the status quo on pricing for its biosimilar, but with a twist. It›s being offered at two different prices: $85,494 a year, which is only a 5% discount from Humira’s list price, or at $40,497 a year, a 55% discount. However, to date, the lower price has generally not been granted favorable formulary placement by PBMs. The plans that adopt the higher-priced biosimilar will get bigger rebates, but patients with coinsurance and deductibles will pay more out of pocket.

It is yet unknown how the pricing on Yusimry will affect the biosimilars ready to launch. “Will it give them pause for thought or not make any difference?” Mr. Horvitz said. “The companies do not reveal their pricing before the fact, so we have to wait and see.”

Large PBMs have not jumped at the opportunity to offer the Coherus biosimilar, but SmithRx, which bills itself as “next-generation pharmacy benefits management,” announced that it will offer Yusimry to its members at a discount of more than 90%.

“Unlike traditional PBMs, SmithRx prioritizes transparency and up-front cost savings. Humira is often an employer’s top drug expense so offering a low-cost alternative will have significant impact,” Jake Frenz, CEO and founder of SmithRx, said in a statement. “We’re excited to work with Cost Plus Drugs to bring this biosimilar to our members – and significantly reduce costs for them and their employers.”

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

Adalimumab, sold under the brand name Humira, enjoyed a long run as one of the world’s best-selling medicines. But its 20-year, competition-free period has ended, and despite its best efforts to delay their arrival, drug manufacturer AbbVie now faces increasing competition from biosimilars entering the marketplace.
 

But one biosimilar about to be launched may be something of a game changer. Coherus BioSciences has announced plans to market its biosimilar Yusimry (adalimumab-aqvh) at a cost of $995 for two autoinjectors. This represents an approximate 85% discount over Humira’s sale list price of $6922.

This price, however, is slated to plunge even further as Coherus has also revealed that it will work with the Mark Cuban Cost Plus Drug Company (MCCPDC) to offer an even lower price. When Yusimry launches in July, it will sell for about $579 for two autoinjectors, making it the lowest-priced adalimumab biosimilar on the market.

“Coherus and Cost Plus Drug Company share a common mission, to increase access to high-quality medicine for patients at an affordable price,” said Dennis Lanfear, MBA, president, CEO and chairman of Coherus. “Mark Cuban and his team offer innovative solutions to health care problems, and Coherus is also a highly innovative company focused on unmet patient needs.”

He noted that, with adalimumab biosimilar pricing, this translates to a low list price approach. “We are pleased that Yusimry will be a part of that, as the first biologic they carry,” Mr. Lanfear said.

MCCPDC prices are based on the cost of ingredients and manufacturing plus 15% margin, a $3 pharmacy dispensing fee, and a $5 shipping fee. The company has expanded its inventory from 100 generics to more than 350 medications since it launched in January 2022. While MCCPDC is primarily directed to people who are paying cash for drugs, it does take insurance from select plans. And even for people who are covered by other insurers, the cost of drugs from Mr. Cuban’s company may be less than their out-of-pocket costs if they did go through their payer.

The low pricing of Yusimry is welcome, said Marcus Snow, MD, an assistant professor in the division of rheumatology at the University of Nebraska Medical Center, Omaha, but he pointed out that it is still a very expensive drug. “For patients who can’t afford Humira due to poor insurance coverage and high out-of-pocket costs, it is a welcome option. But it’s also unclear how many patients who lack adequate health insurance coverage can afford to pay $579 a month out of their own pockets.”
 

The biosimilars are coming

By early December 2022, the Food and Drug Administration had approved seven Humira biosimilars, and Amgen launched the first biosimilar to come on the market, Amjevita, soon afterward. By July 2023, half a dozen more are expected to enter the marketplace, said Steven Horvitz, managing director of EMC Analytics Group, a pharmaceutical research firm.

Mr. Horvitz agrees that the system is out of control, but it is unclear how much of an effect the low price tag on the Coherus product will have. “Some insurers may say, ‘we want the lowest price, and we don’t care about rebates,’ and will go with it,” he said. “PBMs [pharmacy benefit managers] are all about economics, so we have to see how many of their major clients will ask for the lowest price.”

Amgen has more or less followed the status quo on pricing for its biosimilar, but with a twist. It›s being offered at two different prices: $85,494 a year, which is only a 5% discount from Humira’s list price, or at $40,497 a year, a 55% discount. However, to date, the lower price has generally not been granted favorable formulary placement by PBMs. The plans that adopt the higher-priced biosimilar will get bigger rebates, but patients with coinsurance and deductibles will pay more out of pocket.

It is yet unknown how the pricing on Yusimry will affect the biosimilars ready to launch. “Will it give them pause for thought or not make any difference?” Mr. Horvitz said. “The companies do not reveal their pricing before the fact, so we have to wait and see.”

Large PBMs have not jumped at the opportunity to offer the Coherus biosimilar, but SmithRx, which bills itself as “next-generation pharmacy benefits management,” announced that it will offer Yusimry to its members at a discount of more than 90%.

“Unlike traditional PBMs, SmithRx prioritizes transparency and up-front cost savings. Humira is often an employer’s top drug expense so offering a low-cost alternative will have significant impact,” Jake Frenz, CEO and founder of SmithRx, said in a statement. “We’re excited to work with Cost Plus Drugs to bring this biosimilar to our members – and significantly reduce costs for them and their employers.”

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

MILAN – Two independent efforts to use artificial intelligence (AI) to predict the development of early rheumatoid arthritis (RA) from patients with signs and symptoms not meeting full disease criteria showed good, near expert-level accuracy, according to findings from two studies presented at the annual European Congress of Rheumatology.

In one study, researchers from Leiden University Medical Center in the Netherlands developed an AI-based method to automatically analyze MR scans of extremities in order to predict early rheumatoid arthritis. The second study involved a Japanese research team that used machine learning to create a model capable of predicting progression from undifferentiated arthritis (UA) to RA. Both approaches would facilitate early diagnosis of RA, enabling timely treatment and improved clinical outcomes.

Dr. Lennart Jans

Lennart Jans, MD, PhD, who was not involved in either study but works with AI-assisted imaging analysis on a daily basis as head of clinics in musculoskeletal radiology at Ghent University Hospital and a professor of radiology at Ghent University in Belgium, said that integrating AI into health care poses several challenging aspects that need to be addressed. “There are three main challenges associated with the development and implementation of AI-based tools in clinical practice,” he said. “Firstly, obtaining heterogeneous datasets from different image hardware vendors, diverse racial and ethnic backgrounds, and various ages and genders is crucial for training and testing the AI algorithms. Secondly, AI algorithms need to achieve a predetermined performance level depending on the specific use case. Finally, a regulatory pathway must be followed to obtain the necessary FDA or MDR [medical devices regulation] certification before applying an AI use case in clinical practice.”
 

RA prediction

Yanli Li, the first author of the study and a member of the division of image processing at Leiden University Medical Center, explained the potential benefits of early RA prediction. “If we could determine whether a patient presenting with clinically suspected arthralgia (CSA) or early onset arthritis (EAC) is likely to develop RA in the near future, physicians could initiate treatment earlier, reducing the risk of disease progression.”

Currently, rheumatologists estimate the likelihood of developing RA by visually scoring MR scans using the RAMRIS scoring system. “We decided to explore the use of AI,” Dr. Li explained, “because it could save time, reduce costs and labor, eliminate the need for scoring training, and allow for hypothesis-free discoveries.”

The research team collected MR scans of the hands and feet from Leiden University Medical Center’s radiology department. The dataset consisted of images from 177 healthy individuals, 692 subjects with CSA (including 113 who developed RA), and 969 with EAC (including 447 who developed RA). The images underwent automated preprocessing to remove artifacts and standardize the input for the computer. Subsequently, a deep learning model was trained to predict RA development within a 2-year time frame.

The training process involved several steps. Initially, the researchers pretrained the model to learn anatomy by masking parts of the images and tasking the computer with reconstructing them. Subsequently, the AI was trained to differentiate between the groups (EAC vs. healthy and CSA vs. healthy), then between RA and other disorders. Finally, the AI model was trained to predict RA.

The accuracy of the model was evaluated using the area under the receiver operator characteristic curve (AUROC). The model that was trained using MR scans of the hands (including the wrist and metacarpophalangeal joints) achieved a mean AUROC of 0.84 for distinguishing EAC from healthy subjects and 0.83 for distinguishing CSA from healthy subjects. The model trained using MR scans of both the hands and feet achieved a mean AUROC of 0.71 for distinguishing RA from non-RA cases in EAC. The accuracy of the model in predicting RA using MR scans of the hands was 0.73, which closely matches the reported accuracy of visual scoring by human experts (0.74). Importantly, the generation and analysis of heat maps suggested that the deep learning model predicts RA based on known inflammatory signals.

“Automatic RA prediction using AI interpretation of MR scans is feasible,” Dr. Li said. “Incorporating additional clinical data will likely further enhance the AI prediction, and the heat maps may contribute to the discovery of new MRI biomarkers for RA development.”

“AI models and engines have achieved near-expertise levels for various use cases, including the early detection of RA on MRI scans of the hands,” said Dr. Jans, the Ghent University radiologist. “We are observing the same progress in AI detection of rheumatic diseases in other imaging modalities, such as radiography, CT, and ultrasound. However, it is important to note that the reported performances often apply to selected cohorts with standardized imaging protocols. The next challenge [for Dr. Li and colleagues, and others] will be to train and test these algorithms using more heterogeneous datasets to make them applicable in real-world settings.”
 

A ‘transitional phase’ of applying AI techniques

“In a medical setting, as computer scientists, we face unique challenges,” pointed out Berend C. Stoel, MSc, PhD, the senior author of the Leiden study. “Our team consists of approximately 30-35 researchers, primarily electrical engineers or computer scientists, situated within the radiology department of Leiden University Medical Center. Our focus is on image processing, seeking AI-based solutions for image analysis, particularly utilizing deep learning techniques.”

Their objective is to validate this method more broadly, and to achieve that, they require collaboration with other hospitals. Up until now, they have primarily worked with a specific type of MR images, extremity MR scans. These scans are conducted in only a few centers equipped with extremity MR scanners, which can accommodate only hands or feet.

“We are currently in a transitional phase, aiming to apply our methods to standard MR scans, which are more widely available,” Dr. Stoel informed this news organization. “We are engaged in various projects. One project, nearing completion, involves the scoring of early RA, where we train the computer to imitate the actions of rheumatologists or radiologists. We started with a relatively straightforward approach, but AI offers a multitude of possibilities. In the project presented at EULAR, we manipulated the images in a different manner, attempting to predict future events. We also have a parallel project where we employ AI to detect inflammatory changes over time by analyzing sequences of images (MR scans). Furthermore, we have developed AI models to distinguish between treatment and placebo groups. Once the neural network has been trained for this task, we can inquire about the location and timing of changes, thereby gaining insights into the therapy’s response.

“When considering the history of AI, it has experienced both ups and downs. We are currently in a promising phase, but if certain projects fail, expectations might diminish. My hope is that we will indeed revolutionize and enhance disease diagnosis, monitoring, and prediction. Additionally, AI may provide us with additional information that we, as humans, may not be able to extract from these images. However, it is difficult to predict where we will stand in 5-10 years,” he concluded.
 

Predicting disease progression

The second study, which explored the application of AI in predicting the progression of undifferentiated arthritis (UA) to RA, was presented by Takayuki Fujii, MD, PhD, assistant professor in the department of advanced medicine for rheumatic diseases at Kyoto University’s Graduate School of Medicine in Japan. “Predicting the progression of RA from UA remains an unmet medical need,” he reminded the audience.

Dr. Takayuki Fujii

Dr. Fujii’s team used data from the KURAMA cohort, a large observational RA cohort from a single center, to develop a machine learning model. The study included a total of 322 patients initially diagnosed with UA. The deep neural network (DNN) model was trained using 24 clinical features that are easily obtainable in routine clinical practice, such as age, sex, C-reactive protein (CRP) levels, and disease activity score in 28 joints using erythrocyte sedimentation rate (DAS28-ESR). The DNN model achieved a prediction accuracy of 85.1% in the training cohort. When the model was applied to validation data from an external dataset consisting of 88 patients from the ANSWER cohort, a large multicenter observational RA cohort, the prediction accuracy was 80%.

“We have developed a machine learning model that can predict the progression of RA from UA using clinical parameters,” Dr. Fujii concluded. “This model has the potential to assist rheumatologists in providing appropriate care and timely intervention for patients with UA.”

“Dr. Fujii presented a fascinating study,” Dr. Jans said. “They achieved an accuracy of 80% when applying a DNN model to predict progression from UA to RA. This level of accuracy is relatively high and certainly promising. However, it is important to consider that a pre-test probability of 30% [for progressing from UA to RA]  is also relatively high, which partially explains the high accuracy. Nonetheless, this study represents a significant step forward in the clinical management of patients with UA, as it helps identify those who may benefit the most from regular clinical follow-up.”

Dr. Li and Dr. Stoel report no relevant financial relationships with industry. Dr. Fujii has received speaking fees from Asahi Kasei, AbbVie, Chugai, and Tanabe Mitsubishi Pharma. Dr. Jans has received speaking fees from AbbVie, UCB, Lilly, and Novartis; he is cofounder of RheumaFinder. The Leiden study was funded by the Dutch Research Council and the China Scholarship Council. The study by Dr. Fujii and colleagues had no outside funding.

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

MILAN – Two independent efforts to use artificial intelligence (AI) to predict the development of early rheumatoid arthritis (RA) from patients with signs and symptoms not meeting full disease criteria showed good, near expert-level accuracy, according to findings from two studies presented at the annual European Congress of Rheumatology.

In one study, researchers from Leiden University Medical Center in the Netherlands developed an AI-based method to automatically analyze MR scans of extremities in order to predict early rheumatoid arthritis. The second study involved a Japanese research team that used machine learning to create a model capable of predicting progression from undifferentiated arthritis (UA) to RA. Both approaches would facilitate early diagnosis of RA, enabling timely treatment and improved clinical outcomes.

Dr. Lennart Jans

Lennart Jans, MD, PhD, who was not involved in either study but works with AI-assisted imaging analysis on a daily basis as head of clinics in musculoskeletal radiology at Ghent University Hospital and a professor of radiology at Ghent University in Belgium, said that integrating AI into health care poses several challenging aspects that need to be addressed. “There are three main challenges associated with the development and implementation of AI-based tools in clinical practice,” he said. “Firstly, obtaining heterogeneous datasets from different image hardware vendors, diverse racial and ethnic backgrounds, and various ages and genders is crucial for training and testing the AI algorithms. Secondly, AI algorithms need to achieve a predetermined performance level depending on the specific use case. Finally, a regulatory pathway must be followed to obtain the necessary FDA or MDR [medical devices regulation] certification before applying an AI use case in clinical practice.”
 

RA prediction

Yanli Li, the first author of the study and a member of the division of image processing at Leiden University Medical Center, explained the potential benefits of early RA prediction. “If we could determine whether a patient presenting with clinically suspected arthralgia (CSA) or early onset arthritis (EAC) is likely to develop RA in the near future, physicians could initiate treatment earlier, reducing the risk of disease progression.”

Currently, rheumatologists estimate the likelihood of developing RA by visually scoring MR scans using the RAMRIS scoring system. “We decided to explore the use of AI,” Dr. Li explained, “because it could save time, reduce costs and labor, eliminate the need for scoring training, and allow for hypothesis-free discoveries.”

The research team collected MR scans of the hands and feet from Leiden University Medical Center’s radiology department. The dataset consisted of images from 177 healthy individuals, 692 subjects with CSA (including 113 who developed RA), and 969 with EAC (including 447 who developed RA). The images underwent automated preprocessing to remove artifacts and standardize the input for the computer. Subsequently, a deep learning model was trained to predict RA development within a 2-year time frame.

The training process involved several steps. Initially, the researchers pretrained the model to learn anatomy by masking parts of the images and tasking the computer with reconstructing them. Subsequently, the AI was trained to differentiate between the groups (EAC vs. healthy and CSA vs. healthy), then between RA and other disorders. Finally, the AI model was trained to predict RA.

The accuracy of the model was evaluated using the area under the receiver operator characteristic curve (AUROC). The model that was trained using MR scans of the hands (including the wrist and metacarpophalangeal joints) achieved a mean AUROC of 0.84 for distinguishing EAC from healthy subjects and 0.83 for distinguishing CSA from healthy subjects. The model trained using MR scans of both the hands and feet achieved a mean AUROC of 0.71 for distinguishing RA from non-RA cases in EAC. The accuracy of the model in predicting RA using MR scans of the hands was 0.73, which closely matches the reported accuracy of visual scoring by human experts (0.74). Importantly, the generation and analysis of heat maps suggested that the deep learning model predicts RA based on known inflammatory signals.

“Automatic RA prediction using AI interpretation of MR scans is feasible,” Dr. Li said. “Incorporating additional clinical data will likely further enhance the AI prediction, and the heat maps may contribute to the discovery of new MRI biomarkers for RA development.”

“AI models and engines have achieved near-expertise levels for various use cases, including the early detection of RA on MRI scans of the hands,” said Dr. Jans, the Ghent University radiologist. “We are observing the same progress in AI detection of rheumatic diseases in other imaging modalities, such as radiography, CT, and ultrasound. However, it is important to note that the reported performances often apply to selected cohorts with standardized imaging protocols. The next challenge [for Dr. Li and colleagues, and others] will be to train and test these algorithms using more heterogeneous datasets to make them applicable in real-world settings.”
 

A ‘transitional phase’ of applying AI techniques

“In a medical setting, as computer scientists, we face unique challenges,” pointed out Berend C. Stoel, MSc, PhD, the senior author of the Leiden study. “Our team consists of approximately 30-35 researchers, primarily electrical engineers or computer scientists, situated within the radiology department of Leiden University Medical Center. Our focus is on image processing, seeking AI-based solutions for image analysis, particularly utilizing deep learning techniques.”

Their objective is to validate this method more broadly, and to achieve that, they require collaboration with other hospitals. Up until now, they have primarily worked with a specific type of MR images, extremity MR scans. These scans are conducted in only a few centers equipped with extremity MR scanners, which can accommodate only hands or feet.

“We are currently in a transitional phase, aiming to apply our methods to standard MR scans, which are more widely available,” Dr. Stoel informed this news organization. “We are engaged in various projects. One project, nearing completion, involves the scoring of early RA, where we train the computer to imitate the actions of rheumatologists or radiologists. We started with a relatively straightforward approach, but AI offers a multitude of possibilities. In the project presented at EULAR, we manipulated the images in a different manner, attempting to predict future events. We also have a parallel project where we employ AI to detect inflammatory changes over time by analyzing sequences of images (MR scans). Furthermore, we have developed AI models to distinguish between treatment and placebo groups. Once the neural network has been trained for this task, we can inquire about the location and timing of changes, thereby gaining insights into the therapy’s response.

“When considering the history of AI, it has experienced both ups and downs. We are currently in a promising phase, but if certain projects fail, expectations might diminish. My hope is that we will indeed revolutionize and enhance disease diagnosis, monitoring, and prediction. Additionally, AI may provide us with additional information that we, as humans, may not be able to extract from these images. However, it is difficult to predict where we will stand in 5-10 years,” he concluded.
 

Predicting disease progression

The second study, which explored the application of AI in predicting the progression of undifferentiated arthritis (UA) to RA, was presented by Takayuki Fujii, MD, PhD, assistant professor in the department of advanced medicine for rheumatic diseases at Kyoto University’s Graduate School of Medicine in Japan. “Predicting the progression of RA from UA remains an unmet medical need,” he reminded the audience.

Dr. Takayuki Fujii

Dr. Fujii’s team used data from the KURAMA cohort, a large observational RA cohort from a single center, to develop a machine learning model. The study included a total of 322 patients initially diagnosed with UA. The deep neural network (DNN) model was trained using 24 clinical features that are easily obtainable in routine clinical practice, such as age, sex, C-reactive protein (CRP) levels, and disease activity score in 28 joints using erythrocyte sedimentation rate (DAS28-ESR). The DNN model achieved a prediction accuracy of 85.1% in the training cohort. When the model was applied to validation data from an external dataset consisting of 88 patients from the ANSWER cohort, a large multicenter observational RA cohort, the prediction accuracy was 80%.

“We have developed a machine learning model that can predict the progression of RA from UA using clinical parameters,” Dr. Fujii concluded. “This model has the potential to assist rheumatologists in providing appropriate care and timely intervention for patients with UA.”

“Dr. Fujii presented a fascinating study,” Dr. Jans said. “They achieved an accuracy of 80% when applying a DNN model to predict progression from UA to RA. This level of accuracy is relatively high and certainly promising. However, it is important to consider that a pre-test probability of 30% [for progressing from UA to RA]  is also relatively high, which partially explains the high accuracy. Nonetheless, this study represents a significant step forward in the clinical management of patients with UA, as it helps identify those who may benefit the most from regular clinical follow-up.”

Dr. Li and Dr. Stoel report no relevant financial relationships with industry. Dr. Fujii has received speaking fees from Asahi Kasei, AbbVie, Chugai, and Tanabe Mitsubishi Pharma. Dr. Jans has received speaking fees from AbbVie, UCB, Lilly, and Novartis; he is cofounder of RheumaFinder. The Leiden study was funded by the Dutch Research Council and the China Scholarship Council. The study by Dr. Fujii and colleagues had no outside funding.

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

MILAN – Two independent efforts to use artificial intelligence (AI) to predict the development of early rheumatoid arthritis (RA) from patients with signs and symptoms not meeting full disease criteria showed good, near expert-level accuracy, according to findings from two studies presented at the annual European Congress of Rheumatology.

In one study, researchers from Leiden University Medical Center in the Netherlands developed an AI-based method to automatically analyze MR scans of extremities in order to predict early rheumatoid arthritis. The second study involved a Japanese research team that used machine learning to create a model capable of predicting progression from undifferentiated arthritis (UA) to RA. Both approaches would facilitate early diagnosis of RA, enabling timely treatment and improved clinical outcomes.

Dr. Lennart Jans

Lennart Jans, MD, PhD, who was not involved in either study but works with AI-assisted imaging analysis on a daily basis as head of clinics in musculoskeletal radiology at Ghent University Hospital and a professor of radiology at Ghent University in Belgium, said that integrating AI into health care poses several challenging aspects that need to be addressed. “There are three main challenges associated with the development and implementation of AI-based tools in clinical practice,” he said. “Firstly, obtaining heterogeneous datasets from different image hardware vendors, diverse racial and ethnic backgrounds, and various ages and genders is crucial for training and testing the AI algorithms. Secondly, AI algorithms need to achieve a predetermined performance level depending on the specific use case. Finally, a regulatory pathway must be followed to obtain the necessary FDA or MDR [medical devices regulation] certification before applying an AI use case in clinical practice.”
 

RA prediction

Yanli Li, the first author of the study and a member of the division of image processing at Leiden University Medical Center, explained the potential benefits of early RA prediction. “If we could determine whether a patient presenting with clinically suspected arthralgia (CSA) or early onset arthritis (EAC) is likely to develop RA in the near future, physicians could initiate treatment earlier, reducing the risk of disease progression.”

Currently, rheumatologists estimate the likelihood of developing RA by visually scoring MR scans using the RAMRIS scoring system. “We decided to explore the use of AI,” Dr. Li explained, “because it could save time, reduce costs and labor, eliminate the need for scoring training, and allow for hypothesis-free discoveries.”

The research team collected MR scans of the hands and feet from Leiden University Medical Center’s radiology department. The dataset consisted of images from 177 healthy individuals, 692 subjects with CSA (including 113 who developed RA), and 969 with EAC (including 447 who developed RA). The images underwent automated preprocessing to remove artifacts and standardize the input for the computer. Subsequently, a deep learning model was trained to predict RA development within a 2-year time frame.

The training process involved several steps. Initially, the researchers pretrained the model to learn anatomy by masking parts of the images and tasking the computer with reconstructing them. Subsequently, the AI was trained to differentiate between the groups (EAC vs. healthy and CSA vs. healthy), then between RA and other disorders. Finally, the AI model was trained to predict RA.

The accuracy of the model was evaluated using the area under the receiver operator characteristic curve (AUROC). The model that was trained using MR scans of the hands (including the wrist and metacarpophalangeal joints) achieved a mean AUROC of 0.84 for distinguishing EAC from healthy subjects and 0.83 for distinguishing CSA from healthy subjects. The model trained using MR scans of both the hands and feet achieved a mean AUROC of 0.71 for distinguishing RA from non-RA cases in EAC. The accuracy of the model in predicting RA using MR scans of the hands was 0.73, which closely matches the reported accuracy of visual scoring by human experts (0.74). Importantly, the generation and analysis of heat maps suggested that the deep learning model predicts RA based on known inflammatory signals.

“Automatic RA prediction using AI interpretation of MR scans is feasible,” Dr. Li said. “Incorporating additional clinical data will likely further enhance the AI prediction, and the heat maps may contribute to the discovery of new MRI biomarkers for RA development.”

“AI models and engines have achieved near-expertise levels for various use cases, including the early detection of RA on MRI scans of the hands,” said Dr. Jans, the Ghent University radiologist. “We are observing the same progress in AI detection of rheumatic diseases in other imaging modalities, such as radiography, CT, and ultrasound. However, it is important to note that the reported performances often apply to selected cohorts with standardized imaging protocols. The next challenge [for Dr. Li and colleagues, and others] will be to train and test these algorithms using more heterogeneous datasets to make them applicable in real-world settings.”
 

A ‘transitional phase’ of applying AI techniques

“In a medical setting, as computer scientists, we face unique challenges,” pointed out Berend C. Stoel, MSc, PhD, the senior author of the Leiden study. “Our team consists of approximately 30-35 researchers, primarily electrical engineers or computer scientists, situated within the radiology department of Leiden University Medical Center. Our focus is on image processing, seeking AI-based solutions for image analysis, particularly utilizing deep learning techniques.”

Their objective is to validate this method more broadly, and to achieve that, they require collaboration with other hospitals. Up until now, they have primarily worked with a specific type of MR images, extremity MR scans. These scans are conducted in only a few centers equipped with extremity MR scanners, which can accommodate only hands or feet.

“We are currently in a transitional phase, aiming to apply our methods to standard MR scans, which are more widely available,” Dr. Stoel informed this news organization. “We are engaged in various projects. One project, nearing completion, involves the scoring of early RA, where we train the computer to imitate the actions of rheumatologists or radiologists. We started with a relatively straightforward approach, but AI offers a multitude of possibilities. In the project presented at EULAR, we manipulated the images in a different manner, attempting to predict future events. We also have a parallel project where we employ AI to detect inflammatory changes over time by analyzing sequences of images (MR scans). Furthermore, we have developed AI models to distinguish between treatment and placebo groups. Once the neural network has been trained for this task, we can inquire about the location and timing of changes, thereby gaining insights into the therapy’s response.

“When considering the history of AI, it has experienced both ups and downs. We are currently in a promising phase, but if certain projects fail, expectations might diminish. My hope is that we will indeed revolutionize and enhance disease diagnosis, monitoring, and prediction. Additionally, AI may provide us with additional information that we, as humans, may not be able to extract from these images. However, it is difficult to predict where we will stand in 5-10 years,” he concluded.
 

Predicting disease progression

The second study, which explored the application of AI in predicting the progression of undifferentiated arthritis (UA) to RA, was presented by Takayuki Fujii, MD, PhD, assistant professor in the department of advanced medicine for rheumatic diseases at Kyoto University’s Graduate School of Medicine in Japan. “Predicting the progression of RA from UA remains an unmet medical need,” he reminded the audience.

Dr. Takayuki Fujii

Dr. Fujii’s team used data from the KURAMA cohort, a large observational RA cohort from a single center, to develop a machine learning model. The study included a total of 322 patients initially diagnosed with UA. The deep neural network (DNN) model was trained using 24 clinical features that are easily obtainable in routine clinical practice, such as age, sex, C-reactive protein (CRP) levels, and disease activity score in 28 joints using erythrocyte sedimentation rate (DAS28-ESR). The DNN model achieved a prediction accuracy of 85.1% in the training cohort. When the model was applied to validation data from an external dataset consisting of 88 patients from the ANSWER cohort, a large multicenter observational RA cohort, the prediction accuracy was 80%.

“We have developed a machine learning model that can predict the progression of RA from UA using clinical parameters,” Dr. Fujii concluded. “This model has the potential to assist rheumatologists in providing appropriate care and timely intervention for patients with UA.”

“Dr. Fujii presented a fascinating study,” Dr. Jans said. “They achieved an accuracy of 80% when applying a DNN model to predict progression from UA to RA. This level of accuracy is relatively high and certainly promising. However, it is important to consider that a pre-test probability of 30% [for progressing from UA to RA]  is also relatively high, which partially explains the high accuracy. Nonetheless, this study represents a significant step forward in the clinical management of patients with UA, as it helps identify those who may benefit the most from regular clinical follow-up.”

Dr. Li and Dr. Stoel report no relevant financial relationships with industry. Dr. Fujii has received speaking fees from Asahi Kasei, AbbVie, Chugai, and Tanabe Mitsubishi Pharma. Dr. Jans has received speaking fees from AbbVie, UCB, Lilly, and Novartis; he is cofounder of RheumaFinder. The Leiden study was funded by the Dutch Research Council and the China Scholarship Council. The study by Dr. Fujii and colleagues had no outside funding.

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