Machine Learning to Predict Length of Stay Following Revision Hip Arthroplasty

Abstract

Predicting length of stay (LOS) for revision total hip arthroplasty (rTHA) remains challenging due to the complexity of cases and increased complication rates compared with primary total hip arthroplasty. Artificial intelligence may play a role in predicting LOS after rTHA. This study aims to develop a machine learning model to predict LOS in rTHA patients based on preoperative and intraoperative factors. The American College of Surgeons National Surgical Quality Improvement Program database was used to identify patients undergoing a rTHA between 2012 and 2018. The data were used to train both random forest machine and logistic regression machine learning models to predict short LOS (≤ 1 day) or long LOS (≥ 2 days). Statistical analysis was performed to analyze differences between short and long LOS groups. Logistic regression analysis was used to calculate odds ratios associated with long LOS. A total of 4,228 patients were identified in this analysis with a mean postoperative LOS of 3.69 days. Preoperative features associated with a short LOS included male sex, noninfectious revision, spinal anesthesia, later year of operation, younger age, smoking history, and lower body mass index. Area under the receiver operating characteristic curve was calculated to measure model performance for the random forest model and logistic regression model as 0.76 and 0.78, respectively. The machine learning model presented here was able to reasonably predict LOS for revision hip arthroplasty showing promise for use as patient selection tool to identify short LOS patients.

Keywords

machine learning - clinical decision support - patient selection - revision total hip arthroplasty - length of stay

Publication History

Received: 30 August 2022

Accepted: 22 December 2023

Article published online:
27 February 2024

• References

• 1 Aynardi M, Post Z, Ong A, Orozco F, Sukin DC. Outpatient surgery as a means of cost reduction in total hip arthroplasty: a case-control study. HSS J 2014; 10 (03) 252-255
• 2 Courtney PM, Boniello AJ, Berger RA. Complications following outpatient total joint arthroplasty: an analysis of a national database. J Arthroplasty 2017; 32 (05) 1426-1430
• 3 Hsiue PP, Chen CJ, Villalpando C, Ponzio D, Khoshbin A, Stavrakis AI. Trends and patient factors associated with technology-assisted total hip arthroplasty in the United States from 2005 to 2014. Arthroplast Today 2020; 6 (01) 112-117.e1
• 4 Kurtz SM, Ong KL, Lau E, Bozic KJ. Impact of the economic downturn on total joint replacement demand in the United States: updated projections to 2021. J Bone Joint Surg Am 2014; 96 (08) 624-630
• 5 Rubin LE, Blood TD, Defillo-Draiby JC. Total hip and knee arthroplasty in patients older than age 80 years. J Am Acad Orthop Surg 2016; 24 (10) 683-690
• 6 Gwam CU, Mistry JB, Mohamed NS. et al. Current epidemiology of revision total hip arthroplasty in the United States: National Inpatient Sample 2009 to 2013. J Arthroplasty 2017; 32 (07) 2088-2092
• 7 Comprehensive Care for Joint Replacement Model. Accessed August 1, 2022 at: https://innovation.cms.gov/innovation-models/cjr
• 8 Cantrell CK, DeBell HA, Lehtonen EJ. et al. Risk factors for readmission within thirty days following revision total hip arthroplasty. J Clin Orthop Trauma 2020; 11 (01) 38-42
• 9 Merrill RK, Ferrandino RM, Hoffman R, Shaffer GW, Ndu A. Machine learning accurately predicts short-term outcomes following open reduction and internal fixation of ankle fractures. J Foot Ankle Surg 2019; 58 (03) 410-416
• 10 Biron DR, Sinha I, Kleiner JE. et al. A novel machine learning model developed to assist in patient selection for outpatient total shoulder arthroplasty. J Am Acad Orthop Surg 2020; 28 (13) e580-e585
• 11 Ramkumar PN, Karnuta JM, Navarro SM. et al. Deep learning preoperatively predicts value metrics for primary total knee arthroplasty: development and validation of an Artificial Neural Network Model. J Arthroplasty 2019; 34 (10) 2220-2227.e1
• 12 Ramkumar PN, Navarro SM, Haeberle HS. et al. Development and validation of a machine learning algorithm after primary total hip arthroplasty: applications to length of stay and payment models. J Arthroplasty 2019; 34 (04) 632-637
• 13 About ACS NSQIP: History. Accessed August 1, 2022 at: https://www.facs.org/quality-programs/acs-nsqip/about/history
• 14 Aluthge D, Bot BCBI, Restrepo MI, Gelin F, sinhaishan, TagBot J. bcbi/PredictMD.jl: v0.34.19; 2020. Accessed July 1, 2020 at: https://doi.org/10.5281/ZENODO.3880614
• 15 Buller LT, Hubbard TA, Ziemba-Davis M, Deckard ER, Meneghini RM. Safety of same and next day discharge following revision hip and knee arthroplasty using modern perioperative protocols. J Arthroplasty 2021; 36 (01) 30-36
• 16 Liu P, Li X, Luo M. et al. Risk factors for carbapenem-resistant Klebsiella pneumoniae infection: a meta-analysis. Microb Drug Resist 2018; 24 (02) 190-198
• 17 Boddapati V, Fu MC, Tetreault MW, Blevins JL, Richardson SS, Su EP. Short-term complications after revision hip arthroplasty for prosthetic joint infection are increased relative to noninfectious revisions. J Arthroplasty 2018; 33 (09) 2997-3002
• 18 Navarro SM, Wang EY, Haeberle HS. et al. Machine learning and primary total knee arthroplasty: patient forecasting for a patient-specific payment model. J Arthroplasty 2018; 33 (12) 3617-3623
• 19 Courtney PM, Ashley BS, Hume EL, Kamath AF. Are bundled payments a viable reimbursement model for revision total joint arthroplasty?. Clin Orthop Relat Res 2016; 474 (12) 2714-2721
• 20 Klouche S, Sariali E, Mamoudy P. Total hip arthroplasty revision due to infection: a cost analysis approach. Orthop Traumatol Surg Res 2010; 96 (02) 124-132