Inferring disease severity in rheumatoid arthritis using predictive modeling in administrative claims databases.

Urmila Chandran,Paul E Stang,Jenna Reps,Patrick B Ryan,Domenico Paolo Emanuele Margiotta

doi:10.1371/journal.pone.0226255

Abstract

BackgroundConfounding by disease severity is an issue in pharmacoepidemiology studies of rheumatoid arthritis (RA), due to channeling of sicker patients to certain therapies. To address the issue of limited clinical data for confounder adjustment, a patient-level prediction model to differentiate between patients prescribed and not prescribed advanced therapies was developed as a surrogate for disease severity, using all available data from a US claims database.MethodsData from adult RA patients were used to build regularized logistic regression models to predict current and future disease severity using a biologic or tofacitinib prescription claim as a surrogate for moderate-to-severe disease. Model discrimination was assessed using the area under the receiver (AUC) operating characteristic curve, tested and trained in Optum Clinformatics® Extended DataMart (Optum) and additionally validated in three external IBM MarketScan® databases. The model was further validated in the Optum database across a range of patient cohorts.ResultsIn the Optum database (n = 68,608), the AUC for discriminating RA patients with a prescription claim for a biologic or tofacitinib versus those without in the 90 days following index diagnosis was 0.80. Model AUCs were 0.77 in IBM CCAE (n = 75,579) and IBM MDCD (n = 7,537) and 0.75 in IBM MDCR (n = 36,090). There was little change in the prediction model assessing discrimination 730 days following index diagnosis (prediction model AUC in Optum was 0.79).ConclusionsA prediction model demonstrated good discrimination across multiple claims databases to identify RA patients with a prescription claim for advanced therapies during different time-at-risk periods as proxy for current and future moderate-to-severe disease. This work provides a robust model-derived risk score that can be used as a potential covariate and proxy measure to adjust for confounding by severity in multivariable models in the RA population. An R package to develop the prediction model and risk score are available in an open source platform for researchers.

Highlights

To address the issue of limited clinical data for confounder adjustment, a patient-level prediction model to differentiate between patients prescribed and not prescribed advanced therapies was developed as a surrogate for disease severity, using all available data from a US claims database
In our efforts to enable use and reproducibility of the prediction model and public sharing of study results, we have created an interactive online shiny app available at http://data.ohdsi.org/RASeverity/, where readers can freely access the prediction models, model performance data, and all other results presented in the manuscript
Insurance claims databases are being increasingly employed in drug safety studies, due to the advantages of large sample size, representativeness of patients in routine practice, comprehensive capture of all health encounters, and relative efficiency compared with randomized clinical trials and patient registers

Summary

Introduction

Insurance claims databases are being increasingly employed in drug safety studies, due to the advantages of large sample size, representativeness of patients in routine practice, comprehensive capture of all health encounters, and relative efficiency compared with randomized clinical trials and patient registers. Rheumatoid arthritis (RA) disease activity, which is one of the most frequently used factors indicating poor prognosis is generally assessed by the number of swollen and tender joint counts, serum levels of C-reactive protein and erythrocyte sedimentation rate, and physical and functional disability [2]. Such clinical and laboratory data to assess disease activity are not routinely or explicitly captured in an administrative claims database, which limit ability of researchers to minimize imbalances due to confounding by disease severity when comparing different treatments in RA patients using large claims databases.

Objectives

Methods

Discussion

Conclusion