biostudies-literatureDavoudi ANational Institute of Neurological Disorders and StrokeNIBIB NIH HHSNIA NIH HHSNational Natural Science Foundation of ChinaNINDS NIH HHSNational Institute of Biomedical Imaging and Bioengineering970281https://www.ebi.ac.uk/biostudies/studies/S-EPMC9874861biostudies-literatureUnknown4<h4>Introduction</h4>Overall performance of machine learning-based prediction models is promising; however, their generalizability and fairness must be vigorously investigated to ensure they perform sufficiently well for all patients.<h4>Objective</h4>This study aimed to evaluate prediction bias in machine learning models used for predicting acute postoperative pain.<h4>Method</h4>We conducted a retrospective review of electronic health records for patients undergoing orthopedic surgery from June 1, 2011, to June 30, 2019, at the University of Florida Health system/Shands Hospital. CatBoost machine learning models were trained for predicting the binary outcome of low (≤4) and high pain (>4). Model biases were assessed against seven protected attributes of age, sex, race, area deprivation iFrontiers in digital healthFairness in the prediction of acute postoperative pain using machine learning models.PMC9874861R01NS120924R01 AG055337R01 NS120924K07 AG073468, R01 AG121647R21 EB0273441750192, R01EB029699, R21EB027344R01 EB029699K07 AG066813K07 AG073468Hagen JIson RRashidi PSajdeya RPrice CCTighe PJDavoudi AfalseFairness in the prediction of acute postoperative pain using machine learning models.<h4>Introduction</h4>Overall performance of machine learning-based prediction models is promising; however, their generalizability and fairness must be vigorously investigated to ensure they perform sufficiently well for all patients.<h4>Objective</h4>This study aimed to evaluate prediction bias in machine learning models used for predicting acute postoperative pain.<h4>Method</h4>We conducted a retrospective review of electronic health records for patients undergoing orthopedic surgery from June 1, 2011, to June 30, 2019, at the University of Florida Health system/Shands Hospital. CatBoost machine learning models were trained for predicting the binary outcome of low (≤4) and high pain (>4). Model biases were assessed against seven protected attributes of age, sex, race, area deprivation i2022-01-01T00:00:00Z20222026-03-15T13:49:36.043Z2025-04-06T14:11:33.63ZS-EPMC98748613671461110.3389/fdgth.2022.970281