Machine learning model identifies patient gait speed throughout the episode of care, generating notifications for clinician evaluation

Introduction

The advent of digital and mobile health innovations, especially use of wearables for passive data collection, allows remote monitoring and creates an abundance of data. For this information to be interpretable, machine learning (ML) processes are necessary.

Research question

Can a machine learning model successfully identify patients expected to have low gait speed in the early recovery period following joint replacement surgery?

Methods

A commercial database from a smartphone-based care management platform passively collecting mobility data pre- and post-lower limb arthroplasty was used. We sought to create a ML model to predict gait speed recovery curves and identify patients at risk of poor gait speed outcome, a measure associated with range of motion and patient-reported outcomes. Model performance including sensitivity, specificity, precision, and accuracy were determined. Receiver operator curve (ROC) analysis was used to compare true and false positive rates. To benchmark our model, we compared threshold-based notifications based on the patient’s current gait speed.

Results

The performance of the predictive model was significantly improved compared to baseline of threshold-based exceptions using current gait speed. The ML model currently provides 53 % precision, 88 % accuracy, 36 % sensitivity, and 95 % specificity on the held-out test set. The ROC analysis suggests good clinical performance (AUC=0.81).

Significance

Utilization of ML to predict gait recovery following total joint replacement is feasible and provides results with excellent specificity. This model will allow inclusion of additional data for retraining as patient populations evolve. Clinician feedback regarding notifications, including resulting actions and outcomes, can be used to further inform the model and improve clinical utility.