Association Rule Mining to Examine Predictors for the Outcome of Gait Rehabilitation Programs in Stroke Survivors

Abstract

This study presents a novel application of association rule data mining to determine the predictors of the response to locomotor training and home exercise for improving gait after stroke. The study was a secondary data analysis on the Locomotor Experience Applied Post Stroke Trial dataset. The association rule analysis was applied to analyze three interventions: (1) early locomotor training, (2) late locomotor training, and (3) home exercise program. The outcome variable was whether participants poststroke had greater than median improvement in the self-selected comfortable gait speed. Three types of predictors were investigated: (1) demographics, (2) behavioral and medical history, and (3) clinical assessments at baseline. Association rules were generated when they meet two criteria determined based on the data: 10% of support and 70% of confidence. The identified rules showed that the predictors of the response were different across the three interventions, which was inconsistent with the previous report based on traditional logistic regression. However, the rules were identified with high confidence but low support, indicating that they were reliable but did not appear often in the Locomotor Experience Applied Post Stroke Trial dataset. Further investigation of these rules with a larger sample size is warranted before applying them to clinical settings.