The Utilization of Artificial Neural Networks for the Prediction of 90-day Unplanned Readmissions Following Total Knee Arthroplasty

Overview

Journal Arch Orthop Trauma Surg

Specialties Emergency Medicine
General Surgery
Orthopedics

Date 2022 Aug 7

PMID 35933638

Authors

Christian Klemt

Venkatsaiakhil Tirumala

Yasamin Habibi

Anirudh Buddhiraju

Tony Lin-Wei Chen

Young-Min Kwon

Affiliations

Soon will be listed here.

Abstract

Background: A reliable predictive tool to predict unplanned readmissions has the potential to lower readmission rates through targeted pre-operative counseling and intervention with respect to modifiable risk factors. This study aimed to develop and internally validate machine learning models for the prediction of 90-day unplanned readmissions following total knee arthroplasty.

Methods: A total of 10,021 consecutive patients underwent total knee arthroplasty. Patient charts were manually reviewed to identify patient demographics and surgical variables that may be associated with 90-day unplanned hospital readmissions. Four machine learning algorithms (artificial neural networks, support vector machine, k-nearest neighbor, and elastic-net penalized logistic regression) were developed to predict 90-day unplanned readmissions following total knee arthroplasty and these models were evaluated using ROC AUC statistics as well as calibration and decision curve analysis.

Results: Within the study cohort, 644 patients (6.4%) were readmitted within 90 days. The factors most significantly associated with 90-day unplanned hospital readmissions included drug abuse, surgical operative time, and American Society of Anaesthesiologist Physical Status (ASA) score. The machine learning models all achieved excellent performance across discrimination (AUC > 0.82), calibration, and decision curve analysis.

Conclusion: This study developed four machine learning models for the prediction of 90-day unplanned hospital readmissions in patients following total knee arthroplasty. The strongest predictors for unplanned hospital readmissions were drug abuse, surgical operative time, and ASA score. The study findings show excellent model performance across all four models, highlighting the potential of these models for the identification of high-risk patients prior to surgery for whom coordinated care efforts may decrease the risk of subsequent hospital readmission.

Level Of Evidence: Level III, case-control retrospective analysis.

Citing Articles

Comparing prediction accuracy for 30-day readmission following primary total knee arthroplasty: the ACS-NSQIP risk calculator versus a novel artificial neural network model.

Buddhiraju A, Shimizu M, Chen T, Seo H, Bacevich B, Xiao P Knee Surg Relat Res. 2025; 37(1):3.

PMID: 39806502 PMC: 11727824. DOI: 10.1186/s43019-024-00256-z.

Artificial intelligence in planned orthopaedic care.

Georgiakakis E, Khan A, Logishetty K, Sarraf K SICOT J. 2024; 10:49.

PMID: 39570038 PMC: 11580622. DOI: 10.1051/sicotj/2024044.

On the Horizon: Specific Applications of Automation and Artificial Intelligence in Anesthesiology.

Davoud S, Kovacheva V Curr Anesthesiol Rep. 2023; 13(2):31-40.

PMID: 38106626 PMC: 10722862. DOI: 10.1007/s40140-023-00558-0.

A role for artificial intelligence applications inside and outside of the operating theatre: a review of contemporary use associated with total knee arthroplasty.

Kurmis A Arthroplasty. 2023; 5(1):40.

PMID: 37400876 PMC: 10318748. DOI: 10.1186/s42836-023-00189-0.

Improving Resource Utilization for Arthroplasty Care by Leveraging Machine Learning and Optimization: A Systematic Review.

Entezari B, Koucheki R, Abbas A, Toor J, Wolfstadt J, Ravi B Arthroplast Today. 2023; 20:101116.

PMID: 36938350 PMC: 10014272. DOI: 10.1016/j.artd.2023.101116.

References

Berwick D, Nolan T, Whittington J . The triple aim: care, health, and cost. Health Aff (Millwood). 2008; 27(3):759-69. DOI: 10.1377/hlthaff.27.3.759. View

Goltz D, Ryan S, Hopkins T, Howell C, Attarian D, Bolognesi M . A Novel Risk Calculator Predicts 90-Day Readmission Following Total Joint Arthroplasty. J Bone Joint Surg Am. 2019; 101(6):547-556. DOI: 10.2106/JBJS.18.00843. View

Iorio R, Clair A, Inneh I, Slover J, Bosco J, Zuckerman J . Early Results of Medicare's Bundled Payment Initiative for a 90-Day Total Joint Arthroplasty Episode of Care. J Arthroplasty. 2015; 31(2):343-50. DOI: 10.1016/j.arth.2015.09.004. View

Goltz D, Baumgartner B, Politzer C, DiLallo M, Bolognesi M, Seyler T . The American College of Surgeons National Surgical Quality Improvement Program Surgical Risk Calculator Has a Role in Predicting Discharge to Post-Acute Care in Total Joint Arthroplasty. J Arthroplasty. 2017; 33(1):25-29. DOI: 10.1016/j.arth.2017.08.008. View

Edelstein A, Kwasny M, Suleiman L, Khakhkhar R, Moore M, Beal M . Can the American College of Surgeons Risk Calculator Predict 30-Day Complications After Knee and Hip Arthroplasty?. J Arthroplasty. 2015; 30(9 Suppl):5-10. DOI: 10.1016/j.arth.2015.01.057. View

Haeberle H, Helm J, Navarro S, Karnuta J, Schaffer J, Callaghan J . Artificial Intelligence and Machine Learning in Lower Extremity Arthroplasty: A Review. J Arthroplasty. 2019; 34(10):2201-2203. DOI: 10.1016/j.arth.2019.05.055. View

Bini S . Artificial Intelligence, Machine Learning, Deep Learning, and Cognitive Computing: What Do These Terms Mean and How Will They Impact Health Care?. J Arthroplasty. 2018; 33(8):2358-2361. DOI: 10.1016/j.arth.2018.02.067. View

Kunze K, Polce E, Sadauskas A, Levine B . Development of Machine Learning Algorithms to Predict Patient Dissatisfaction After Primary Total Knee Arthroplasty. J Arthroplasty. 2020; 35(11):3117-3122. DOI: 10.1016/j.arth.2020.05.061. View

Karhade A, Schwab J, Bedair H . Development of Machine Learning Algorithms for Prediction of Sustained Postoperative Opioid Prescriptions After Total Hip Arthroplasty. J Arthroplasty. 2019; 34(10):2272-2277.e1. DOI: 10.1016/j.arth.2019.06.013. View

10.

Ramkumar P, Harris J, Noble P . Patient-reported outcome measures after total knee arthroplasty: a systematic review. Bone Joint Res. 2015; 4(7):120-7. PMC: 4602194. DOI: 10.1302/2046-3758.47.2000380. View

11.

Ramkumar P, Muschler G, Spindler K, Harris J, McCulloch P, Mont M . Open mHealth Architecture: A Primer for Tomorrow's Orthopedic Surgeon and Introduction to Its Use in Lower Extremity Arthroplasty. J Arthroplasty. 2016; 32(4):1058-1062. DOI: 10.1016/j.arth.2016.11.019. View

12.

Siracuse B, Ippolito J, Gibson P, Ohman-Strickland P, Beebe K . A Preoperative Scale for Determining Surgical Readmission Risk After Total Knee Arthroplasty. J Bone Joint Surg Am. 2017; 99(21):e112. DOI: 10.2106/JBJS.16.01043. View

13.

Karhade A, Ogink P, Thio Q, Broekman M, Cha T, Hershman S . Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion. Spine J. 2019; 19(6):976-983. DOI: 10.1016/j.spinee.2019.01.009. View

14.

Sniderman J, Stark R, Schwartz C, Imam H, Finkelstein J, Nousiainen M . Patient Factors That Matter in Predicting Hip Arthroplasty Outcomes: A Machine-Learning Approach. J Arthroplasty. 2021; 36(6):2024-2032. DOI: 10.1016/j.arth.2020.12.038. View

15.

Yeo I, Klemt C, Melnic C, Pattavina M, Oliveira B, Kwon Y . Predicting surgical operative time in primary total knee arthroplasty utilizing machine learning models. Arch Orthop Trauma Surg. 2022; 143(6):3299-3307. DOI: 10.1007/s00402-022-04588-x. View

16.

Nwachukwu B, Bozic K, Schairer W, Bernstein J, Jevsevar D, Marx R . Current status of cost utility analyses in total joint arthroplasty: a systematic review. Clin Orthop Relat Res. 2014; 473(5):1815-27. PMC: 4385366. DOI: 10.1007/s11999-014-3964-4. View

17.

Boozary A, Manchin 3rd J, Wicker R . The Medicare Hospital Readmissions Reduction Program: Time for Reform. JAMA. 2015; 314(4):347-8. DOI: 10.1001/jama.2015.6507. View

18.

Steyerberg E, Vergouwe Y . Towards better clinical prediction models: seven steps for development and an ABCD for validation. Eur Heart J. 2014; 35(29):1925-31. PMC: 4155437. DOI: 10.1093/eurheartj/ehu207. View

19.

Schaeffer J, Scott D, Godin J, Attarian D, Wellman S, Mather 3rd R . The Association of ASA Class on Total Knee and Total Hip Arthroplasty Readmission Rates in an Academic Hospital. J Arthroplasty. 2015; 30(5):723-7. DOI: 10.1016/j.arth.2014.12.014. View

20.

Kurtz S, Lau E, Ong K, Adler E, Kolisek F, Manley M . Hospital, Patient, and Clinical Factors Influence 30- and 90-Day Readmission After Primary Total Hip Arthroplasty. J Arthroplasty. 2016; 31(10):2130-8. DOI: 10.1016/j.arth.2016.03.041. View