Using machine learning methods to predict prolonged operative time in elective total shoulder arthroplasty

Cesar D. Lopez, Michael Constant, Matthew JJ Anderson, Jamie E. Confino, Nathan S. Lanham, Charles M. Jobin

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Background: Machine learning (ML) is a form of artificial intelligence in which computer algorithms improve automatically with experience. Recently, ML has been utilized to predict operative characteristics and patient outcomes for orthopedic procedures, thereby allowing for better patient selection and preoperative planning. This study sought to develop ML models to aid in predicting operative time and 30-day postoperative complications for elective total shoulder arthroplasty and to compare them to regression models. Methods: This cross-sectional national database study identified patients who underwent elective total shoulder arthroplasty from 2012 to 2018 in the American College of Surgeons National Surgical Quality Improvement Program registry. Boosted decision tree and artificial neural network (ANN) ML models were developed to predict prolonged operative time and 30-day postoperative complication rates. Model performance was measured using the area under the receiver operating characteristic curve and overall accuracy. Multivariate binary logistic regression analyses were also used to identify variables that predicted prolonged operative time and 30-day postoperative complication rates. ML model performance was then compared to the regression models in predicting outcomes. Results: In total, 21,544 elective total shoulder arthroplasty procedures met inclusion criteria. Variables associated with greater odds of prolonged operative time included male sex (odds ratio [OR] = 0.66; 95% confidence interval [CI] = 0.61-0.71; P < .001), obesity (OR = 1.19; 95% CI = 1.09-1.29; P < .001), age under 70 years (OR = 0.77; 95% CI = 0.71-0.85; P < .001), smoking history (OR = 1.16; 95% CI = 1.03-1.32; P = .022), and history of cancer (OR = 2.91; 95% CI = 1.52-5.54; P = .001). The boosted decision tree model yielded an area under the curve (AUC) of 0.642, with an overall accuracy of 85.6% for predicting prolonged operative time. The ANN model had an AUC of 0.906 and overall accuracy of 84.7%, while the regression model had an AUC of 0.590 with overall accuracy of 85.6%. Thirty-day complication rate (7.7% vs. 3.9%, respectively; P < .001) and reoperation rate (1.8% vs. 1.2%, respectively; P = .006) also differed significantly between the prolonged operative duration and normal operative duration cohorts. Conclusion: This is the first study to successfully develop ML models for predicting operative time in total shoulder arthroplasty and compare them to existing methods of data analysis. The ANN model was superior to the other models in predicting prolonged operative time. With regard to 30-day postoperative complications, both ML models displayed fair predictive capacity, compared to the regression model, which had poor predictive performance.

Original languageEnglish (US)
Pages (from-to)452-461
Number of pages10
JournalSeminars in Arthroplasty
Volume32
Issue number3
DOIs
StatePublished - Sep 2022

All Science Journal Classification (ASJC) codes

  • Surgery
  • Orthopedics and Sports Medicine

Cite this