Development and benchmarking of machine learning models to classify patients suitable for outpatient lower extremity joint arthroplasty

Haoyu Jia; Sierra Simpson; Varshini Sathish; Brian P Curran; Alvaro A Macias; Ruth S Waterman; Rodney A Gabriel

doi:10.1016/j.jclinane.2023.111147

Development and benchmarking of machine learning models to classify patients suitable for outpatient lower extremity joint arthroplasty

J Clin Anesth. 2023 Sep:88:111147. doi: 10.1016/j.jclinane.2023.111147. Epub 2023 May 16.

Authors

Haoyu Jia¹, Sierra Simpson², Varshini Sathish³, Brian P Curran⁴, Alvaro A Macias⁴, Ruth S Waterman⁴, Rodney A Gabriel⁵

Affiliations

¹ Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USA; Division of Perioperative Informatics, Department of Anesthesiology, University of California San Diego, La Jolla, CA 92093, USA.
² Division of Perioperative Informatics, Department of Anesthesiology, University of California San Diego, La Jolla, CA 92093, USA; Department of Psychiatry, University of California San Diego, La Jolla, CA 92093, USA.
³ Division of Perioperative Informatics, Department of Anesthesiology, University of California San Diego, La Jolla, CA 92093, USA.
⁴ Department of Psychiatry, University of California San Diego, La Jolla, CA 92093, USA.
⁵ Division of Perioperative Informatics, Department of Anesthesiology, University of California San Diego, La Jolla, CA 92093, USA. Electronic address: ragabriel@health.ucsd.edu.

PMID: 37201387
DOI: 10.1016/j.jclinane.2023.111147

Abstract

Study objective: Performing hip or knee arthroplasty as an outpatient surgery has been shown to be operationally and financially beneficial for selected patients. By applying machine learning models to predict patients suitable for outpatient arthroplasty, health care systems can better utilize resources efficiently. The goal of this study was to develop predictive models for identifying patients likely to be discharged same-day following hip or knee arthroplasty.

Design: Model performance was assessed with 10-fold stratified cross-validation, evaluated over baseline determined by the proportion of eligible outpatient arthroplasty over sample size. The models used for classification were logistic regression, support vector classifier, balanced random forest, balanced bagging XGBoost classifier, and balanced bagging LightGBM classifier.

Setting: The patient records were sampled from arthroplasty procedures at a single institution from October 2013 to November 2021.

Patients: The electronic intake records of 7322 knee and hip arthroplasty patients were sampled for the dataset. After data processing, 5523 records were kept for model training and validation.

Interventions: None.

Measurements: The primary measures for the models were the F1-score, area under the receiver operating characteristic curve (ROCAUC), and area under the precision-recall curve. To measure feature importance, the SHapley Additive exPlanations value (SHAP) were reported from the model with the highest F1-score.

Results: The best performing classifier (balanced random forest classifier) achieved an F1-score of 0.347: an improvement of 0.174 over baseline and 0.031 over logistic regression. The ROCAUC for this model was 0.734. Using SHAP, the top determinant features of the model included patient sex, surgical approach, surgery type, and body mass index.

Conclusions: Machine learning models may utilize electronic health records to screen arthroplasty procedures for outpatient eligibility. Tree-based models demonstrated superior performance in this study.

Keywords: Arthroplasty; Machine learning; Outpatient surgery.

MeSH terms

Arthroplasty, Replacement, Hip*
Arthroplasty, Replacement, Knee*
Benchmarking
Humans
Lower Extremity
Machine Learning
Outpatients