USING NEURAL NETWORKS TO IDENTIFY PATIENTS UNLIKELY TO ACHIEVE A REDUCTION IN BODILY PAIN AFTER TOTAL HIP-REPLACEMENT SURGERY

OBJECTIVES. Fourteen patient-provided variables were chosen as potenti al predictors for improvement after total hip replacement surgery. The se variables included patient demographic information, as well as preo perative physical function. METHODS. A neural network was trained to p redict the relative success of total hip replacement surgery using thi s presurgical patient survey information. The outcome measure was impr ovement in the Medical Outcomes Study 36 Short Form Health Survey pain score between the preoperative assessment and the 1-year postoperativ e assessment. For the study sample, 221 patients were selected who had complete information for the composite outcome variable. A backpropag ation feedforward neural network was trained to predict the output var iable using the jackknife method. RESULTS. Performance of the neural n etwork was assessed by calculating the area under the receiver operati ng characteristic curve for the network's ability to predict whether t he pain score was improved after total hip replacement surgery. The ob served area under the receiver operating characteristic curve was 0.79 . For comparison, a linear regression model built using the same data had a receiver operating characteristic area of 0.74 (P = 0.23). CONCL USIONS. This research therefore showed the ability of neural networks to predict the success of total hip replacement more accurately. Our r esults further indicate that it may be possible to predict which patie nts are at greatest risk of a poor outcome.