Artificial Intelligence Predicts Cost After Ambulatory Anterior Cruciate Ligament Reconstruction
Authors:
Open Access
- 27 November 2021
- journal article
- Published by Wiley in Arthroscopy, Sports Medicine, and Rehabilitation
- Vol. 3 (6) , e2033-e2045
Abstract
Purpose: To develop and internally validate a machine‐learning algorithm to reliably predict cost after anterior cruciate ligament reconstruction (ACLR). Methods: A retrospective review of the New York State Ambulatory Surgery and Services database was performed to identify patients who underwent elective ACLR from 2015 to 2016. Features included in initial models consisted of patient characteristics (age, sex, insurance status, income, medical comorbidities as classified by the Clinical Classifications Software diagnosis code) as well as intraoperative variables (type of anesthesia and procedure‐specific factors). Models were generated to predict total charges using 4 algorithms: random forest, extreme gradient boost, elastic net penalized regression, and support vector machines with radial kernels. Training was performed with 10‐fold cross‐validation followed by internal validation via 0.632 bootstrapping. Model discriminative performance was assessed by area under the receiver operating characteristic curve, calibration, and the Brier score. Decision curve analysis was performed to demonstrate the net benefit of using the final model in practice. Results: In total, 7,311 patients undergoing ambulatory ACLR were included. The random forest model demonstrated the best performance assessed via internal validation (area under the curve = 0.85), calibration, and the Brier score (0.208). Cost incurred was influenced by anesthesia type, operating room time, and number of chronic comorbidities. Decision curve analysis revealed a net benefit for use of the random forest model and the model was integrated into a web‐based open‐access application. Conclusions: The random forest model predicted cost after ambulatory ACLR using a large, statewide database with good performance. The top variables found to predict increased charges were general anesthesia, operating room time, meniscal repair, self‐pay insurance, patient neighborhood characteristics, and number of chronic conditions. Level of Evidence: III, retrospective cohort study.Keywords
Funding Information
- Arthrex
- Smith and Nephew
- Stryker
This publication has 35 references indexed in Scilit:
- Risk Factors for Hospital Admission After Anterior Cruciate Ligament ReconstructionArthroscopy, 2017
- Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary ViewJournal of Medical Internet Research, 2016
- Risk Factors for Short-term Complications of Anterior Cruciate Ligament Reconstruction in the United StatesThe American Journal of Sports Medicine, 2016
- Factors Associated with Infection Following Anterior Cruciate Ligament ReconstructionJournal of Bone and Joint Surgery, 2015
- Perioperative outcome and cost-effectiveness of spinal versus general anesthesia for lumbar spine surgeryNeurologia i Neurochirurgia Polska, 2014
- Prognosis Research Strategy (PROGRESS) 3: Prognostic Model ResearchPLOS Medicine, 2013
- MissForest—non-parametric missing value imputation for mixed-type dataBioinformatics, 2011
- Multiple imputation for missing data in epidemiological and clinical research: potential and pitfallsBMJ, 2009
- Using the outcome for imputation of missing predictor values was preferredJournal of Clinical Epidemiology, 2006
- A Comparative Study of General Anesthesia, Intravenous Regional Anesthesia, and Axillary Block for Outpatient Hand Surgery: Clinical Outcome and Cost AnalysisAnesthesia & Analgesia, 2001