Generalizability of machine learning models predicting 30-day unplanned readmission after primary total knee arthroplasty using a nationally representative database

Anirudh Buddhiraju; Michelle Riyo Shimizu; Henry Hojoon Seo; Tony Lin-Wei Chen; MohammadAmin RezazadehSaatlou; Ziwei Huang; Young-Min Kwon

doi:10.1007/s11517-024-03075-2

Generalizability of machine learning models predicting 30-day unplanned readmission after primary total knee arthroplasty using a nationally representative database

Med Biol Eng Comput. 2024 Apr 1. doi: 10.1007/s11517-024-03075-2. Online ahead of print.

Authors

Anirudh Buddhiraju¹, Michelle Riyo Shimizu¹, Henry Hojoon Seo¹, Tony Lin-Wei Chen^{1

2}, MohammadAmin RezazadehSaatlou¹, Ziwei Huang¹, Young-Min Kwon³

Affiliations

¹ Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Boston, MA, 02114, USA.
² Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, 999077, Hong Kong SAR, China.
³ Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Boston, MA, 02114, USA. ymkwon@mgh.harvard.edu.

PMID: 38558351
DOI: 10.1007/s11517-024-03075-2

Abstract

Unplanned readmission after primary total knee arthroplasty (TKA) costs an average of US $39,000 per episode and negatively impacts patient outcomes. Although predictive machine learning (ML) models show promise for risk stratification in specific populations, existing studies do not address model generalizability. This study aimed to establish the generalizability of previous institutionally developed ML models to predict 30-day readmission following primary TKA using a national database. Data from 424,354 patients from the ACS-NSQIP database was used to develop and validate four ML models to predict 30-day readmission risk after primary TKA. Individual model performance was assessed and compared based on discrimination, accuracy, calibration, and clinical utility. Length of stay (> 2.5 days), body mass index (BMI) (> 33.21 kg/m²), and operation time (> 93 min) were important determinants of 30-day readmission. All ML models demonstrated equally good accuracy, calibration, and discriminatory ability (Brier score, ANN = RF = HGB = NEPLR = 0.03; ANN, slope = 0.90, intercept = - 0.11; RF, slope = 0.93, intercept = - 0.12; HGB, slope = 0.90, intercept = - 0.12; NEPLR, slope = 0.77, intercept = 0.01; AUC_ANN = AUC_RF = AUC_HGB = AUC_NEPLR = 0.78). This study validates the generalizability of four previously developed ML algorithms in predicting readmission risk in patients undergoing TKA and offers surgeons an opportunity to reduce readmissions by optimizing discharge planning, BMI, and surgical efficiency.

Keywords: Artificial intelligence (AI); Knee arthroplasty; Machine learning; NSQIP database; Unplanned readmission.