What is the clinical evidence from this study?

Study design: Cohort. Population: Rheumatoid arthritis. Intervention: Random survival forest (RSF) model vs. Regularized Cox regression (RegCox) model. Primary outcome: Incident composite VTE event (p=0.0021).

What question did this study set out to answer?

The aim was to develop a machine learning model to predict VTE risk in older RA patients starting DMARDs and compare it with a traditional regression model.

May 8, 2026

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

Resultado clave

A random survival forest model outperformed regularized Cox regression in predicting venous thromboembolism risk in older rheumatoid arthritis patients initiating b/tsDMARDs (P=0.0021).

Puntos clave

The aim was to develop a machine learning model to predict VTE risk in older RA patients starting DMARDs and compare it with a traditional regression model.
Utilized retrospective cohort data from 2012-2020, involving older RA patients (≥ 65 years) initiating b/tsDMARDs.
Divided data into training (75%) and testing (25%) sets for model evaluation.
Assessed model performance using the C-index and identified influential predictors.
The RSF model showed improved performance in predicting VTE compared to the RegCox model (p=0.0021).
Key predictors of VTE risk included varicose veins, inpatient visits, and Elixhauser score.
Incorporating additional clinical data may enhance predictive accuracy further.

Diseño del estudio

Tipo

Cohort

PICO estructurado

Does a random survival forest model improve the prediction of incident composite VTE events in older RA patients initiating b/tsDMARDs compared to a regularized Cox regression model?

Población

Older adults (≥ 65 years) with rheumatoid arthritis initiating biological or targeted synthetic disease-modifying antirheumatic drugs (b/tsDMARDs) using 5% Medicare data (2012-2020).

Intervención

Random survival forest (RSF) machine learning model for predicting VTE risk

Comparador

Regularized Cox regression (RegCox) model

Resultado

Model performance for predicting incident composite VTE events, evaluated using the C-indexcomposite

A random survival forest machine learning model performed slightly better than regularized Cox regression in predicting VTE risk among older adults with rheumatoid arthritis initiating targeted DMARDs.

Resultado numérico

valor p: p=0.0021

Limitaciones

Lacks additional clinical and contextual information beyond claims data

Resumen

OBJECTIVES: 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. METHODS: This retrospective cohort study using the 5% Medicare data (2012-2020) identified older RA patients (≥ 65 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. RESULTS: = 0.0021). Variables commonly identified as the top influential variables were varicose veins, inpatient visits, Elixhauser score, emergency room visits, and outpatient visits. CONCLUSIONS: 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.

Me gusta

Guardar