Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jan 13;37(1):3.
doi: 10.1186/s43019-024-00256-z.

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

Anirudh Buddhiraju  1 , Michelle Riyo Shimizu  1 , Tony Lin-Wei Chen  1 , Henry Hojoon Seo  1 , Blake M Bacevich  1 , Pengwei Xiao  1 , Young-Min Kwon  2
Affiliations

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

Anirudh Buddhiraju et al. Knee Surg Relat Res. .

Abstract

Background: Unplanned readmission, a measure of surgical quality, occurs after 4.8% of primary total knee arthroplasties (TKA). Although the prediction of individualized readmission risk may inform appropriate preoperative interventions, current predictive models, such as the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) surgical risk calculator (SRC), have limited utility. This study aims to compare the predictive accuracy of the SRC with a novel artificial neural network (ANN) algorithm for 30-day readmission after primary TKA, using the same set of clinical variables from a large national database.

Methods: Patients undergoing primary TKA between 2013 and 2020 were identified from the ACS-NSQIP database and randomly stratified into training and validation cohorts. The ANN was developed using data from the training cohort with fivefold cross-validation performed five times. ANN and SRC performance were subsequently evaluated in the distinct validation cohort, and predictive performance was compared on the basis of discrimination, calibration, accuracy, and clinical utility.

Results: The overall cohort consisted of 365,394 patients (trainingN = 362,559; validationN = 2835), with 11,392 (3.1%) readmitted within 30 days. While the ANN demonstrated good discrimination and calibration (area under the curve (AUC)ANN = 0.72, slope = 1.32, intercept = -0.09) in the validation cohort, the SRC demonstrated poor discrimination (AUCSRC = 0.55) and underestimated readmission risk (slope = -0.21, intercept = 0.04). Although both models possessed similar accuracy (Brier score: ANN = 0.03; SRC = 0.02), only the ANN demonstrated a higher net benefit than intervening in all or no patients on the decision curve analysis. The strongest predictors of readmission were body mass index (> 33.5 kg/m2), age (> 69 years), and male sex.

Conclusions: This study demonstrates the superior predictive ability and potential clinical utility of the ANN over the conventional SRC when constrained to the same variables. By identifying the most important predictors of readmission following TKA, our findings may assist in the development of novel clinical decision support tools, potentially improving preoperative counseling and postoperative monitoring practices in at-risk patients.

Keywords: Clinical decision support; Deep learning; Readmissions; Risk assessments; Total knee arthroplasty.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: This study was determined by the IRB to be exempt from review as it only uses deidentified patient data. Consent for publication: Not applicable. Competing interests: The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
Receiver operating characteristic curve, calibration plot, and decision curve of the artificial neural network model in predicting 30-day readmission rates following primary total knee arthroplasty
Fig. 2
Fig. 2
Receiver operating characteristic curve, calibration plot, and decision curve of the ACS-NSQIP surgical risk calculator in predicting 30-day readmission rates following primary total knee arthroplasty
Fig. 3
Fig. 3
Global predictor importance plot illustrating the relative importance of each predictor in the ANN model for determining the risk of readmission following primary total knee arthroplasty
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Sloan M, Premkumar A, Sheth NP (2018) Projected volume of primary total joint arthroplasty in the U.S., 2014 to 2030. J Bone Joint Surg Am 100(17):1455–1460 - PubMed
    1. Papakostidis C, Giannoudis PV, Watson JT, Zura R, Steen RG (2021) Serious adverse events and 30-day hospital readmission rate following elective total knee arthroplasty: a systematic review and meta-analysis. J Orthop Surg Res 16(1):236 - PMC - PubMed
    1. Gao J, Xing D, Dong S, Lin J (2020) The primary total knee arthroplasty: a global analysis. J Orthop Surg Res 15(1):190 - PMC - PubMed
    1. Kurtz SM, Lau EC, Ong KL, Adler EM, Kolisek FR, Manley MT (2017) Which clinical and patient factors influence the national economic burden of hospital readmissions after total joint arthroplasty? Clin Orthop Relat Res. 10.1007/s11999-017-5244-6 - PMC - PubMed
    1. Urish KL, Qin Y, Li BY, Borza T, Sessine M, Kirk P et al (2018) Predictors and cost of readmission in total knee arthroplasty. J Arthroplasty 33(9):2759–2763 - PMC - PubMed

LinkOut - more resources