Predicting Remission Among Patients With Rheumatoid Arthritis Starting Tocilizumab Monotherapy: Model Derivation and Remission Score Development

Abstract

Objective. Most patients with rheumatoid arthritis (RA) strive to consolidate their treatment from methotrexate combinations. The objective of this analysis was to identify patients with RA most likely to achieve remission with tocilizumab (TCZ) monotherapy by developing and validating a prediction model and associated remission score.Methods. We identified four TCZ monotherapy randomized controlled trials in RA and chose two for derivation and two for internal validation. Remission was defined as a Clinical Disease Activity Index score less than 2.8 at 24 weeks post randomization. We used logistic regression to assess the association between each predictor and remission. After selecting variables and assessing model performance in the derivation data set, we assessed model performance in the validation data set. The cohorts were combined to calculate a remission prediction score.Results. The variables selected included younger age, male sex, lower baseline Clinical Disease Activity Index score, shorter RA disease duration, region of the world (Europe and South America [increased odds of remission] versus Asia and North America), no previous exposure to disease-modifying antirheumatic drugs and/or methotrexate, lower baseline Health Assessment Questionnaire Disability Index score, and baseline hematocrit. The area under the receiver operating characteristic curve was 0.739 in the derivation data set and 0.756 in the validation data set. Patients were categorized into three remission prediction categories based on the remission prediction score: 40% in the low (less than 10% probability of remission), 45% in the intermediate (10%-25% probability), and 15% in the moderate remission prediction category (greater than 25% probability).Conclusion. We used easily accessible factors to develop a remission prediction score to predict RA remission at 24 weeks after initializing TCZ monotherapy. These results may provide guidance to clinicians tailoring treatment options based on clinical characteristics.

Predicting Response to Tocilizumab Monotherapy in Rheumatoid Arthritis: A Real-World Data Analysis Using Machine Learning

“…A) to what extent do the ndings of Collins et al 3 replicate in RWD? B.1) will expanding the set of remission predictors improve model t?…”

“…As a baseline model, we used the remission model derived by Collins et al 3 derived from patients on TCZm from two RCTs. 7,8 In the Collins study, twelve variables representing demographics, basic RA characteristics and treatment history were included in a logistic regression (LR) model based on three alternative criteria: an a priori baseline set of covariates, the model odds ratio (OR), and the model t (expressed as the Akaike Information Criterion, AIC).…”

“…AUROC near 0.5 is no better than random selection. The primary outcome of interest was disease remission at 24 weeks following initiation of monotherapy, to match the outcome of the RCTs used by Collins et al 3 Remission was de ned by a Clinical Disease Activity Index (CDAI) < 2.8. 12 A bene t of the CDAI remission criteria is that it does not require access to a laboratory measurement and is thus widely available in RWD.…”

“…5 Real-world data (RWD) offer important advantages over RCTs in that patients are more heterogeneous, with a greater variety of clinical characteristics as well as experience with other biologic and targeted DMARD treatments. We examined the performance of our original prediction score 3 for remission among patients using TCZm among patients in Corrona, a large RWD set from the US. 6 We employed various machine learning algorithms to take advantage of the copious data contained within Corrona.…”

Predicting Response to Tocilizumab Monotherapy in Rheumatoid Arthritis: A Real-world Data Analysis Using Machine Learning

“…We recently examined clinical data from several randomized controlled trials (RCTs) and were able to derive and validate a prediction score for remission among patients using tocilizumab monotherapy (TCZm). 3 Monotherapy with TCZ has been found more effective than monotherapy with some targeted therapies for RA. 4 However, RCT data may not always replicate in typical practice with real world data.…”