Evaluation of Preoperative Variables that Improve the Predictive Accuracy of the Risk Assessment and Prediction Tool in Primary Total Hip Arthroplasty

Abstract

Introduction: Discharge disposition after total joint arthroplasty may be predictable. Previous literature has attempted to improve upon models such as the Risk Assessment and Prediction Tool (RAPT) in an effort to optimize postoperative planning. The purpose of this study was to determine whether preoperative laboratory values and other previously unstudied demographic factors could improve the predictive accuracy of the RAPT. Methods: All patients included had RAPT scores in addition to the following preoperative laboratory values: red blood cell count, albumin, and vitamin D. All values were recorded within 90 days of surgery. Demographic variables including marital status, American Society of Anesthesiologists (ASA) scores, body mass index, Charlson Comorbidity Index, and depression were also evaluated. Binary logistic regression was used to determine the significance of each factor in association with discharge disposition. Results: Univariate logistic regression found significant associations between discharge disposition and all original RAPT factors as well as nonmarried patients (P < 0.001), ASA class 3 to 4 (P < 0.001), body mass index >30 kg/m2 (P = 0.065), red blood cell count <4 million/mm3 (P < 0.001), albumin <3.5 g/dL (P < 0.001), Charlson Comorbidity Index (P < 0.001), and a history of depression (P < 0.001). All notable univariate models were used to create a multivariate model with an overall predictive accuracy of 90.1%. Conclusions: The addition of preoperative laboratory values and additional demographic data to the RAPT may improve its PA. Orthopaedic surgeons could benefit from incorporating these values as part of their discharge planning in THA. Machine learning may be able to identify other factors to make the model even more predictive.