Study Reveals Principal Component Is Effective in Patient Profiling in RA
Researchers have identified 5 distinct phenotypes of rheumatoid arthritis (RA) using data‐driven patient profiling, in a recent study that confirmed the efficacy of using principal component (PC) as a patient-profiling tool to determine and support treatment for patients with RA.
Researchers analyzed the Brigham and Women’s Rheumatoid Arthritis Sequential Study (BRASS) in order to support the validity in identifying patient phenotypes, offering clinical insight into potential disease progression, treatment response, and symptoms as well as risk of adverse reactions.
“Patient demographic, socioeconomic, health, and disease characteristics recorded at entry into a large, single‐center, prospective observational registry cohort—BRASS—were harmonized using PC analysis to reduce dimensionality and collinearity,” the authors reported.
The analysis included 1,443 patients, 142 variables, and 41 confirmed PCs—totaling 77% of the cumulative variance in the data.
The cluster analysis found 5 patient clusters, including:
- “less RA disease activity and multimorbidity, lower incidence of comorbidities and shorter RA duration;
- less RA disease activity/multimorbidity, longer RA duration, more infections, psychiatric comorbidities, health care utilization;
- moderate RA disease activity/multimorbidity, more neurologic comorbidity;
- more RA disease activity/multimorbidity, shorter RA duration, more metabolic comorbidity, higher body mass index; and
- more RA disease activity/multimorbidity, longer RA duration, more hepatic, orthopedic comorbidity and RA‐related surgeries.”
The authors concluded, “These results illustrate the potential of data-drive patient profiling as a tool to support personalized medicine in RA.”
--Angelique Platas
Reference
Curtis JR, Weinblatt M, Saag K, et al. Data‐driven patient clustering and differential clinical outcomes in the brigham and women’s rheumatoid arthritis sequential study registry. AC&R. 2021;73(4):471-480