Identification of Multimorbidity Patterns in Rheumatoid Arthritis Through Machine Learning
Authors' conclusion
Cardiopulmonary, cardiometabolic, and mental health and chronic pain disorders represent predominant multimorbidity patterns, each of which is overrepresented in RA.
Study context
- Population
- Patients with rheumatoid arthritis (RA) and matched non-RA patients in a large commercial insurance database (MarketScan) and the Veterans Health Administration (VHA)226,850 MarketScan
- Exposure
- RA vs age- and sex-matched non-RA
- Outcome
- Multimorbidity patterns (from 44 chronic conditions) and their association with RA
Methodological detailsage- and sex-matched (1:1), exploratory factor analysis, conditional logistic regression, machine learning
- Age- and sex-matched (1:1)
- Exploratory factor analysis
- Conditional logistic regression
- Machine learning
Main finding
As reported in the abstract
Multimorbidity patterns
Odds ratio
1.17-2.96
range across each multimorbidity pattern
Odds ratio
2.07-2.96
mental health and chronic pain disorders pattern, most strongly associated with RA
Observational data: associations, not effects.
Original publication
Identification of Multimorbidity Patterns in Rheumatoid Arthritis Through Machine Learning. Arthritis Care Res (Hoboken). Published 19 October 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →