Optimal inputs for machine learning models in predicting total joint arthroplasty outcomes: a systematic review.

Abstract

Machine learning (ML) models may offer a novel solution to reducing postoperative complication rates and improving post-surgical outcomes after total joint arthroplasty (TJA). However, the variety of different ML models that exist paired with the increasing number of potential inputs can make the implementation of this tool challenging. Therefore, we conducted a systematic review to assess the most optimal inputs of different ML models in predicting postoperative (1) medical outcomes, (2) orthopedic outcomes, and (3) patient-reported outcome measures (PROMs) after total joint arthroplasty. The PubMed, MEDLINE, EBSCOhost, and Google Scholar databases were utilized to identify all studies evaluating ML models predicting outcomes following TJA between January 1, 2000, and June 23, 2023 (PROSPERO study protocol registration: CRD42023437586). The mean risk of bias in non-randomized studies-of interventions score, was 13.8 ± 0.5. Our initial query yielded 656 articles, of which 25 articles aligned with our aims, examining over 20 machine learning models and 1,555,300 surgeries. The area under the curve (AUC), accuracy, inputs, and the importance of each input were reported. Twelve studies evaluating medical complications with 13ML models reported AUCs ranging from 0.57 to 0.997 and accuracy between 88% and 99.98%. Key predictors included age, hyper-coagulopathy, total number of diagnoses, admission month, and malnutrition. Five studies evaluating orthopedic complications with 10ML models reported AUCs from 0.49 to 0.93 and accuracy ranging from 92 to 97%, with age, BMI, CCI, AKSS scores, and height identified as key predictors. Ten studies evaluating PROMs comprising of 12 different ML models had an AUC ranging from 0.453 to 0.97 ranked preoperative PROMs as the post-predictive input. Overall, age was the most predictive risk factor for complications post-total joint arthroplasty (TJA). These studies demonstrate the predictive capabilities of these models for anticipating complications and outcomes. Furthermore, these studies also highlight ML models' ability to identify non-classical variables not commonly considered in addition to confirming variables known to be crucial. To advance the field, forthcoming research should adhere to established guidelines for model development and training, employ industry-standard input parameters, and subject their models to external validity assessments.