TY - JOUR T1 - Predicting Response to Tocilizumab Monotherapy in Rheumatoid Arthritis: A Real-World Data Analysis Using Machine Learning JF - The Journal of Rheumatology JO - J Rheumatol DO - 10.3899/jrheum.201626 SP - jrheum.201626 AU - Fredrik D. Johansson AU - Jamie E. Collins AU - Vincent Yau AU - Hongshu Guan AU - Seoyoung C. Kim AU - Elena Losina AU - David Sontag AU - Jacklyn Stratton AU - Huong Trinh AU - Jeffrey Greenberg AU - Daniel H. Solomon Y1 - 2021/05/01 UR - http://www.jrheum.org/content/early/2021/04/27/jrheum.201626.abstract N2 - Objective Tocilizumab (TCZ) had similar efficacy when used as monotherapy or in combination with other treatments for rheumatoid arthritis (RA) in randomized controlled trials (RCT). We derived a remission prediction score for TCZ monotherapy (TCZm) using RCT data and now performed an external validation of the prediction score using “real world data” (RWD). Methods We identified patients in Corrona-RA who used TCZm (n=453), matching the design and patients from four RCTs used in previous work (n=853). Patients were followed to determine remission status at 24 weeks. We compared the performance of remission prediction models in RWD, first based on variables determined in our prior work in RCTs, and then using an extended variable set, comparing logistic regression and random forest models. We included patients on other biologic DMARD monotherapies (bDMARDm) to improve prediction. Results The fraction of patients observed reaching remission on TCZm by their follow-up visit was 12% (n=53) in RWD vs 15% (n=127) in RCTs. Discrimination was good in RWD for the risk score developed in RCTS with AUROC of 0.69 (95% CI 0.62, 0.75). Fitting the same logistic regression model to all bDMARDm patients in the RWD improved the AUROC on held-out TCZm patients to 0.72 (95% CI 0.63, 0.81). Extending the variable set and adding regularization further increased it to 0.76 (95% CI 0.67, 0.84). Conclusion The remission prediction scores, derived in RCTs, discriminated patients in RWD about as well as in RCTs. Discrimination was further improved by retraining models on RWD. ER -