4, 5 To reduce surgical complications and improve postoperative outcomes, focus has shifted to preoperative and perioperative care for patients at high risk. Of the 15% of patients who experience complications, 50% are patients considered to be high risk. 4, 5 Improving health outcomes after surgery represents an enormous opportunity, and improvement in surgical quality and health care costs is a priority for health care services and payors. These were estimated to cost hospitals more than $11 000 per case, amounting to more than $31.35 billion nationally per year. 2 There are an estimated 48.4 million surgical procedures performed in the United States annually, 3 and 30-day postoperative complications may arise in up to 15% of patients. 1, 2 While it does not constitute its own category in mortality tables published by the Centers for Disease Control and Prevention, the magnitude of 30-day postoperative mortality was approximately the third leading contributor to all-cause death in the United States until COVID-19. 1 Surprisingly, the third leading contributor to deaths on a global scale is postoperative death within 30 days, estimated to occur among 4.2 million people (7.7%) who die each year worldwide. Worldwide, the 2 leading causes of mortality are heart disease and stroke, which combined, account for more than 25% of mortal events (15 million events). These findings suggest that using this model to identify patients at increased risk of adverse outcomes prior to surgery may allow for individualized perioperative care, which may be associated with improved outcomes. The model outperformed the NSQIP tool as measured by AUROC (0.945 vs 0.897, for a difference of 0.048), specificity (0.87 vs 0.68 ), and accuracy (0.85 vs 0.69 ).Ĭonclusions and Relevance This study found that an automated machine learning model was accurate in identifying patients undergoing surgery who were at high risk of adverse outcomes using only preoperative variables within the electronic health record, with superior performance compared with the NSQIP calculator. The area under the receiver operating characteristic curve (AUROC) for mortality was 0.972 (95% CI, 0.971-0.973) for the training set and 0.946 (95% CI, 0.943-0.948) for the test set. After deployment in clinical use, another 206 353 patients were prospectively evaluated an additional 902 patients were selected for comparing the accuracy of the UPMC model and NSQIP tool for predicting mortality. Results Among 1 477 561 patients included in model development (806 148 females age, 56.8 years), 1 016 966 patient encounters were used for training and 254 242 separate encounters were used for testing the model. Main Outcomes and Measures Postoperative mortality and major adverse cardiac and cerebrovascular events (MACCEs) at 30 days were evaluated. Data were analyzed from September through December 2021.Įxposure Undergoing any type of surgical procedure. Accuracy was compared between the UPMC model and National Surgical Quality Improvement Program (NSQIP) surgical risk calculator for predicting mortality. The Shapley additive explanations method was used for model interpretability and further validation. A gradient-boosted decision tree machine learning method was used for developing a preoperative surgical risk prediction tool. The study included 3 phases: (1) building and validating a model on a retrospective population, (2) testing model accuracy on a retrospective population, and (3) validating the model prospectively in clinical care. Objective To evaluate the accuracy of an automated machine-learning model in the identification of patients at high risk of adverse outcomes from surgery using only data in the electronic health record.ĭesign, Setting, and Participants This prognostic study was conducted among 1 477 561 patients undergoing surgery at 20 community and tertiary care hospitals in the University of Pittsburgh Medical Center (UPMC) health network. Importance Identifying patients at high risk of adverse outcomes prior to surgery may allow for interventions associated with improved postoperative outcomes however, few tools exist for automated prediction. Shared Decision Making and Communication.Scientific Discovery and the Future of Medicine.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |