Rheum Round-up: ACR/ARP Annual Meeting Highlights, AI in Rheumatology, and more

Here are the top stories covered by DocWire News this week in the Rheumatology section. In this edition, read about the use of artificial intelligence in rheumatic and musculoskeletal diseases, how exercise identity affects knee replacement outcomes, the symptoms considered most important by rheumatoid arthritis (RA) patients, and the effectiveness of low-dose rituximab in RA.

A presentation during The American College of Rheumatology/Association of Rheumatology Professionals Annual Meeting (ACR/ARP Annual Meeting) discussed the current status of the use of artificial intelligence (AI) and big data in various rheumatic and musculoskeletal diseases (RMDs). Among 567 RMD-related articles discovered in the search, 55 RMD articles were included in the analysis and compared to 55 articles in other medical fields. The majority of the RMD articles pertained to inflammatory joint diseases or osteoarthritis. Among the RMD articles, the mean number of data points was 746 million, compared to 9.1 billion among the non-RMD articles. Representation of data sources varied among the RMDs (clinical, 47%; biological, 15%; and radiological, 29%), but was more similar among the non-RMDs (clinical, 31%; biological, 31%; and imaging sources, 29%). Traditional big data analysis were observed in 18% of RMDs and 15% of non-RMDs, and AI methods were observed in 82% and 85%, respectively. Nearly all of the AI papers discussed machine learning (RMDs, n = 44/45; non-RMDs, n = 47/47), the most common of which was artificial neural network (RMDs, n = 20/44; non-RMDs, n = 24/47).

Total knee replacement patients with a positive self-reported exercise identity may have some better physical outcomes than those with a negative exercise identity, according to a study. The findings were presented at the ACR/ARP Annual Meeting. The analysis included 19 patients (average age, 63.0±7.4 years; body mass index, 32.8±6.2 kg/m2). Collectively, the group had an average 5.6 valid days of wearing the activPAL, which includes a daily step counter and estimates average daily minutes spent upright, standing, and stepping. The positive exercise identity group, compared to the negative identity group, had significantly more steps per day (5,145±2,034 vs. 3,128±1,578) as well as minutes spent upright (283.9±96.8 vs. 170.7±61.4), standing (203.4±70.2 vs. 121.0±40.8), and stepping (80.6±31.6 vs. 49.7±22.3).

A recent study evaluated patient-reported outcomes (PROs) considered the most significant by patients with rheumatoid arthritis (RA). The results of the study were presented in a poster at the ACR/ARP Annual Meeting. At the time the poster was created, the study had enrolled 292 patients, of whom 253 completed baseline assessments. More than half (n = 164, 64.8%) of patients self-reported an osteoarthritis diagnosis; nearly half (n = 123, 48.6% of the cohort reported an rheumatoid arthritis (RA) diagnosis. Common comorbid conditions included depression (n = 128, 50.6%), hypertension (n = 116, 45.8%), and hypercholesterolemia (n = 89, 35.2%); others included psoriasis, diabetes, cancer, deep vein thrombosis, skin cancer, stroke, myocardial infarction, and pulmonary embolism. The top two baseline PRO selections were fatigue and any pain that effected function/behavior (each n = 211, 83.4%), followed closely by any mental health (n = 208, 82.2%) and physical function (n = 181, 71.5%). OMERACT RA flare was also offered as an option to the 123 patients with RA, of whom 86 (69.9%) selected this PRO.

A randomized trial compared the efficacy of different doses of rituximab in RA patients. Here, the researchers compared two ultra-low doses of rituximab—500 mg and 200 mg—to a standard low dose of 1,000 mg in RA patients with adequate response to standard doses. A total of 142 patients were randomized to receive 1,000 mg (n = 29), 500 mg (n = 58), or 200 mg (2 = 55) doses. At three months, the 500 mg dose group did not have significantly different outcomes compared to the 1,000 mg group (mean change from baseline in DAS28-CRP, –0.07; 95% CI –0.41–0.27), but by six months the 500 mg group was no longer non-inferior (mean change from baseline in DAS28-CRP, 0.29; 95% CI –0.08–0.65). Serious adverse events occurred in 13 patients—three (10%) in the 1000 mg group, six (10%) in the 500 mg group, and four (7%) in the 200 mg group—the most common of which were cardiovascular. The ultra-low dose groups had a significantly lower infection rate than the standard group (1,000 mg dose, 1.24 infections per patient-year; 500 mg dose, 0.52; 200 mg dose, 0.55, rate ratio, 0.42; 95% CI 0.21–0.83; P=0.013 for 500 mg vs. 1,000 mg; rate ratio, 0.44; 95% CI 0.22–0.88; P=0.019 for 200 mg vs. 1,000 mg). No deaths were reported.