Development of a decision support system to predict physicians' rehabilitation protocols for patients with knee osteoarthritis

Abstract

To design a medical decision support system (MDSS) that would accurately predict the rehabilitation protocols prescribed by the physicians for patients with knee osteoarthritis (OA) using only their demographic and clinical characteristics. The demographic and clinical variables for 170 patients receiving one of three treatment protocols for knee OA were entered into the MDSS. Demographic variables in the model were age and sex. Clinical variables entered into the model were height, weight, BMI, affected side, severity of knee OA, and severity of pain. All patients in the study received one of three treatment protocols for patients with knee OA: (a) hot packs, followed by electrotherapy and exercise, (b) ice packs, followed by ultrasound and exercise and (c) exercise alone. The resilient back propagation artificial neural network algorithm was used, with a ten-fold cross-validation. It was estimated that the MDSS is able to accurately predict the treatment prescribed by the physician for 87% of the patients. We developed an artificial neural network-based decision support system that can viably aid physicians in determining which treatment protocol would best match the anthropometric and clinical characteristics of patients with knee OA.