Machine Learning Approaches to Classify Self-Reported Rheumatoid Arthritis Health Scores Using Activity Tracker Data.

Abstract

The increasing use of activity trackers in mobile health studies to passively collect physical data has shown promise to lessen participation burden to provide actively contributed patient reported outcome (PRO) information. Our goal was to develop machine learning models to classify patient-reported outcome (PRO) scores using Fitbit data from a cohort of patients with rheumatoid arthritis (RA). The increasing use of activity trackers in mobile health studies to passively collect physical data has shown promise to lessen participation burden to provide actively contributed patient reported outcome (PRO) information. Our goal was to develop machine learning models to classify patient-reported outcome (PRO) scores using Fitbit data from a cohort of patients with rheumatoid arthritis (RA). Two different models were built to classify PRO scores; a random forest (RF) Classifier model that treated each week of observations independently when making weekly predictions of PRO scores, and a hidden Markov model (HMM) that additionally took correlations between successive weeks into account. Analyses compared model evaluation metrics for: 1) a binary task of distinguishing a normal PRO score from a severe PRO score, and 2) a multiclass task of classifying a PRO score state for a given week. For both the binary and multiclass tasks, the HMM significantly (p < 0.05) outperformed the RF for most PRO scores, and the highest AUC, Pearson's Correlation coefficient, and Cohen's Kappa coefficient were 0.751, 0.458, and 0.450 respectively. While further validation of our results and evaluation in a real-world setting yet remains, this study demonstrates the ability of physical activity tracker data to classify health status over time in patients with RA and enables the possibility of scheduling preventive clinical interventions as needed. If patient outcomes can be monitored in real time, there is potential to improve clinical care for patients with other chronic conditions.