Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs

Abstract

Background Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients tapering bDMARDs using machine learning methods. Methods Longitudinal clinical data of RA patients on bDMARDs from a randomized controlled trial of treatment withdrawal (RETRO) were used to build a predictive model to estimate the probability of a flare. Four basic machine learning models were trained, and their predictions were additionally combined to train an ensemble learning method, a stacking meta-classifier model to predict the individual flare probability within 14 weeks after each visit. Prediction performance was estimated using nested cross-validation as the area under the receiver operating curve (AUROC). Predictor importance was estimated using the permutation importance approach. Results Data of 135 visits from 41 patients were included. A model selection approach based on nested cross-validation was implemented to find the most suitable modeling formalism for the flare prediction task as well as the optimal model hyper-parameters. Moreover, an approach based on stacking different classifiers was successfully applied to create a powerful and flexible prediction model with the final measured AUROC of 0.81 (95%CI 0.73–0.89). The percent dose change of bDMARDs, clinical disease activity (DAS-28 ESR), disease duration, and inflammatory markers were the most important predictors of a flare. Conclusion Machine learning methods were deemed feasible to predict flares after tapering bDMARDs in RA patients in sustained remission.

Using real-world data to dynamically predict flares during tapering of biological DMARDs in rheumatoid arthritis: development, validation, and potential impact of prediction-aided decisions

“…Two studies have incorporated such dynamic variables to predict RA disease activity over time [ 24 , 25 ]. The study by Norgeot et al [ 24 ] found the Clinical Disease Activity Index (CDAI), CRP/ESR, glucocorticoid use, and other DMARD use to be important predictors.…”

Proteomic Approaches to Defining Remission and the Risk of Relapse in Rheumatoid Arthritis

“…The RETRO clinical trial has previously generated predictive models that were based on clinical parameters and serum studies ( 16 , 17 ). ACPA seropositivity appears to be an important indicator for increased risk of future relapse ( 17 ), while clinical parameters have modest predictive value even when combined with advanced machine learning techniques ( 43 ). It remains unclear if these indicators are clinically applicable and generalizable to a wide range of RA patient populations.…”

Demographic and Clinical Characteristics of Patients with Sustained and Switching Treatments Using Biological and Targeted Synthetic Disease-Modifying Antirheumatic Drugs: A Multicenter, Observational Cross-Sectional Study for Rheumatoid Arthritis

“…Besides, Erythrocyte Sedimentation Ratebased Disease Activity Score in 28 joints (DAS28-ESR), C-reactive protein-based Disease Activity Score in 28 joints (DAS28-CRP), Clinical Disease Activity Index (CDAI) score, and the Simplified Disease Activity Index (SDAI, 0-86) were also used to grade the disease [2,5,6,16].…”

“…Rheumatoid arthritis (RA) is one of the chronic inflammatory diseases that cause erosive arthritis and consequently functional loss if it is not treated with early effective treatment modalities [ 1 , 2 ]. Remission rates usually depend on several factors belonging to the patients and the medications used for RA.…”