Preoperative Prediction and Risk Factor Identification of Hospital Length of Stay for Total Joint Arthroplasty Patients Using Machine Learning

Aug 5, 2026

Upload by Patrick

Background: This study aims to clarify hospital length of stay (LOS) among inpatients undergoing total joint arthroplasty (TJA) within a high-efficiency, hospital-based pathway. Methods: Retrospective review of 1,401 consecutive primary and revision TJA patients (2016–2019) across 67 patient and preoperative characteristics using multiple machine learning models. Results: Patients clustered into outpatient, short-stay (1–2 days), and prolonged-stay (≥3 days) groups; lower Risk Assessment and Prediction Tool score, unplanned admission/transfer, and cardiovascular history increased LOS, while documented preoperative narcotic use and preoperative corticosteroids reduced LOS. Conclusions: Outpatients and short-stay episodes dominate, with a distinct prolonged group.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Policy background and LOS reduction controversies

Patient setting decisions after CMS billing changes

Background

Methods

Results

LOS distribution and patient grouping

Machine learning predictors of LOS

Conclusions

Arthroplasty Today 22 (2023) 101166 Contents lists available at ScienceDirect Arthroplasty Today journal homepage: [http://www. arthroplastytoday. org/](http://www. arthroplastytoday. org/) | Original research
Preoperative Prediction and Risk Factor Identiﬁcation of Hospital Length of Stay for Total Joint Arthroplasty Patients Using Machine Learning
Jaeyoung Park, PhD a, Xiang Zhong, PhD b, *, Emilie N. Miley, DAT, ATC c, Chancellor F. Gray, MD c
a Booth School of Business, University of Chicago, Chicago, IL, USA
b Department of Industrial and Systems Engineering, University of Florida, Gainesville, FL, USAc Department of Orthopaedic Surgery and Sports Medicine, University of Florida, Gainesville, FL, USA | | | | --- | --- | --- | | a r t i c l e i n f o | | a b s t r a c t | | Article history:
Received 31 March 2023
Accepted 24 May 2023
Available online xxx | | Background: The aim of this study was to improve understanding of hospital length of stay (LOS) inpatients undergoing total joint arthroplasty (TJA) in a high-efﬁciency, hospital-based pathway.
Methods: We retrospectively reviewed 1401 consecutive primary and revision TJA patients across 67 patient and preoperative care characteristics from 2016 to 2019 from the institutional electronic health records. A machine learning approach, testing multiple models, was used to assess predictors of LOS.
Results: The median LOS was 1 day; outpatients accounted for 16.5%, 1-day inpatient stays for 38.0%, 2-day stays for 26.4%, and 3-days or more for 19.1%. Patients characteristically fell into 1 of 3 broad categories that contained relatively similar characteristics: outpatient (0-day LOS), short stay (1-to 2-day LOS), and prolonged stay (3 days or greater). The random forest models suggested that a lower Risk Assessment and Prediction Tool score, unplanned admission or hospital transfer, and a medical history of cardiovascular disease were associated with an increased LOS. Documented narcotic use for surgery preparation prior to hospitalization and preoperative corticosteroid use were factors independently associated with a decreased LOS.
Conclusions: After TJA, most patients have either an outpatient or short-stay hospital episode. Patients who stay 2 days do not differ substantially from patients who stay 1 day, while there is a distinct group that requires prolonged admission. Our machine learning models support a better understanding of the patient factors associated with different hospital LOS categories for TJA, demonstrating the potential for improved health policy decisions and risk stratiﬁcation for centers caring for complex patients.
© 2023 The Authors. Published by Elsevier Inc. on behalf of The American Association of Hip and Knee Surgeons. This is an open access article under the CC BY-NC-ND license ([http://creativecommons.org/lice](http://creativecommons.org/lice)nses/by-nc-nd/4.0/). | | Keywords:
Machine learning Total joint arthroplasty Hospital length of stay Health policy | | | Introduction Total joint arthroplasty (TJA) is one of the most successful and highest-value surgical procedures in any area of medicine [1] in terms of improvement in quality-adjusted life years for healthcare dollars spent. The growth in TJA surgical volume continues despite * Corresponding author. 482 Weil Hall, P.O. Box 116595, Gainesville, FL 32611- 6595, USA. Tel.: þ1 352 294 7716. E-mail address: xiang.zhong@ise.uﬂ.edu the recent novel coronavirus pandemic [2], and TJA remains one of the highest expenditures for the Centers for Medicare & Medicaid Services (CMS). With the high spending impact of TJA, CMS introduced alternative payment models to promote incentives for costeffective and high-quality care [3]. Additionally, many relevant healthcare policies have encouraged arthroplasty surgeons to reduce hospital stays and postdischarge adverse events (eg, emergency room visits, readmissions, and acute care resource utilizatio

FAQs

How were hospital length of stay (LOS) predictors evaluated in this study?

The study retrospectively analyzed 1,401 primary and revision TJA patients using a machine learning approach that tested multiple models to identify LOS predictors.

How did the researchers categorize patients based on LOS after TJA?

Patients were grouped into outpatient (0-day LOS), short stay (1–2 days), and prolonged stay (3 days or more).

Which factors were associated with increased or decreased LOS?

Increased LOS was associated with lower Risk Assessment and Prediction Tool scores, unplanned admission or hospital transfer, and cardiovascular disease history. Decreased LOS was independently associated with documented narcotic use for surgery preparation prior to hospitalization and preoperative corticosteroid use.

Aug 5, 2026

Upload by Patrick