Predicting 30-day unplanned hospital readmission after revision total knee arthroplasty: machine learning model analysis of a national patient cohort

Tony Lin-Wei Chen; Michelle Riyo Shimizu; Anirudh Buddhiraju; Henry Hojoon Seo; Murad Abdullah Subih; Shane Fei Chen; Young-Min Kwon

doi:10.1007/s11517-024-03054-7

Predicting 30-day unplanned hospital readmission after revision total knee arthroplasty: machine learning model analysis of a national patient cohort

Med Biol Eng Comput. 2024 Mar 7. doi: 10.1007/s11517-024-03054-7. Online ahead of print.

Authors

Tony Lin-Wei Chen^{1

2}, Michelle Riyo Shimizu¹, Anirudh Buddhiraju¹, Henry Hojoon Seo¹, Murad Abdullah Subih¹, Shane Fei Chen^{1

2}, Young-Min Kwon³

Affiliations

¹ Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
² Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China.
³ Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA. ymkwon@mgh.harvard.edu.

PMID: 38451418
DOI: 10.1007/s11517-024-03054-7

Abstract

Revision total knee arthroplasty (TKA) is associated with a higher risk of readmission than primary TKA. Identifying individual patients predisposed to readmission can facilitate proactive optimization and increase care efficiency. This study developed machine learning (ML) models to predict unplanned readmission following revision TKA using a national-scale patient dataset. A total of 17,443 revision TKA cases (2013-2020) were acquired from the ACS NSQIP database. Four ML models (artificial neural networks, random forest, histogram-based gradient boosting, and k-nearest neighbor) were developed on relevant patient variables to predict readmission following revision TKA. The length of stay, operation time, body mass index (BMI), and laboratory test results were the strongest predictors of readmission. Histogram-based gradient boosting was the best performer in distinguishing readmission (AUC: 0.95) and estimating the readmission probability for individual patients (calibration slope: 1.13; calibration intercept: -0.00; Brier score: 0.064). All models produced higher net benefit than the default strategies of treating all or no patients, supporting the clinical utility of the models. ML demonstrated excellent performance for the prediction of readmission following revision TKA. Optimization of important predictors highlighted by our model may decrease preventable hospital readmission following surgery, thereby leading to reduced financial burden and improved patient satisfaction.

Keywords: Length of stay; Machine learning; Total knee arthroplasty.