Predicting the risk of venous thromboembolism events in older adults with rheumatoid arthritis after initiating targeted disease-modifying antirheumatic drugs: a comparison of the random survival forest and regularized cox regression models.

Abstract

To develop a random survival forest (RSF) machine learning (ML) model for predicting venous thromboembolism (VTE) risk in rheumatoid arthritis (RA) patients initiating biological (b) or targeted synthetic (ts) disease-modifying antirheumatic drugs (DMARDs) and compare its model performance with a regularized Cox regression (RegCox) model. This retrospective cohort study using the 5% Medicare data (2012-2020) identified older RA patients (&#x2265; 65&#x2009;years) initiating b/tsDMARDs (index date), including tumor necrosis factor inhibitors (TNFi) bDMARDs, non-TNFi bDMARDs, and tsDMARDs between January 1, 2013, through December 31, 2019. Study cohort was followed until an incident composite VTE event or censoring. Data were divided into training (75%) and testing (25%) sets. The RSF model was trained to predict VTE events during the follow-up period in the training set, with the RegCox model as the reference model. The performance of these models was evaluated in the testing data using the C-index. Variable importance of the predictors was assessed. Of 3,648 RA patients, 360 (9.87%) experienced any VTE event. The RSF model had better performance (C-index [95% CI]&#x2009;=&#x2009;0.609[0.602-0.617]) than the RegCox model (C-index [95% CI]&#x2009;=&#x2009;0.599[0.597-0.602], <i>p</i>&#x2009;=&#x2009;0.0021). Variables commonly identified as the top influential variables were varicose veins, inpatient visits, Elixhauser score, emergency room visits, and outpatient visits. The RSF model performed slightly better in identifying VTE in RA patients after b/tsDMARDs initiation than RegCox. Incorporating additional clinical and contextual information beyond claims data may further enhance predictive accuracy in future studies. Biological (b) and targeted synthetic (ts) disease-modifying antirheumatic drugs (DMARDs) are newer medications that can treat rheumatoid arthritis (RA). However, recent randomized controlled clinical trials found the tsDMARDs may increase the risk of venous thromboembolism (VTE) among patients with RA. In this study, we developed a novel random survival forest (RSF) machine learning model to predict the VTE risk involving 3,648 older adults (&#x2265;65) with RA who were newly prescribed b/tsDMARD. Our results suggested that the RSF model achieved modest improved performance compared to the RegCox model in predicting the risk of VTE among these older adults with RA. Our findings from the RSF model may help rheumatologists better understand the high-risk RA patient profile who may be at risk of VTE. Incorporating additional variables from other datasets may improve the RSF&#x2019;s model performance.