Dimitris Bertsimas1, Daisy Zhuo2,3, Jack Dunn2,3, Jordan Levine2,3, Eugenio Zuccarelli1, Nikos Smyrnakis4, Zdzislaw Tobota5, Bohdan Maruszewski5, Jose Fragata6, George E Sarris7. 1. Operations Research Center and Sloan School of Management, 2167Massachusetts Institute of Technology, Cambridge, MA, USA. 2. Alexandria Health, Cambridge, MA. 3. Alexandria Health, Providence, RI, USA. 4. Operations Research Center, 2167Massachusetts Institute of Technology, Cambridge, MA, USA. 5. Department for Pediatric Cardiothoracic Surgery, 49805Children's Memorial Health Institute, Warsaw, Poland. 6. Hospital de Santa Marta and NOVA University, Lisbon, Portugal. 7. Athens Heart Surgery Institute, Greece.
Abstract
OBJECTIVE: Risk assessment tools typically used in congenital heart surgery (CHS) assume that various possible risk factors interact in a linear and additive fashion, an assumption that may not reflect reality. Using artificial intelligence techniques, we sought to develop nonlinear models for predicting outcomes in CHS. METHODS: We built machine learning (ML) models to predict mortality, postoperative mechanical ventilatory support time (MVST), and hospital length of stay (LOS) for patients who underwent CHS, based on data of more than 235,000 patients and 295,000 operations provided by the European Congenital Heart Surgeons Association Congenital Database. We used optimal classification trees (OCTs) methodology for its interpretability and accuracy, and compared to logistic regression and state-of-the-art ML methods (Random Forests, Gradient Boosting), reporting their area under the curve (AUC or c-statistic) for both training and testing data sets. RESULTS: Optimal classification trees achieve outstanding performance across all three models (mortality AUC = 0.86, prolonged MVST AUC = 0.85, prolonged LOS AUC = 0.82), while being intuitively interpretable. The most significant predictors of mortality are procedure, age, and weight, followed by days since previous admission and any general preoperative patient risk factors. CONCLUSIONS: The nonlinear ML-based models of OCTs are intuitively interpretable and provide superior predictive power. The associated risk calculator allows easy, accurate, and understandable estimation of individual patient risks, in the theoretical framework of the average performance of all centers represented in the database. This methodology has the potential to facilitate decision-making and resource optimization in CHS, enabling total quality management and precise benchmarking initiatives.
OBJECTIVE: Risk assessment tools typically used in congenital heart surgery (CHS) assume that various possible risk factors interact in a linear and additive fashion, an assumption that may not reflect reality. Using artificial intelligence techniques, we sought to develop nonlinear models for predicting outcomes in CHS. METHODS: We built machine learning (ML) models to predict mortality, postoperative mechanical ventilatory support time (MVST), and hospital length of stay (LOS) for patients who underwent CHS, based on data of more than 235,000 patients and 295,000 operations provided by the European Congenital Heart Surgeons Association Congenital Database. We used optimal classification trees (OCTs) methodology for its interpretability and accuracy, and compared to logistic regression and state-of-the-art ML methods (Random Forests, Gradient Boosting), reporting their area under the curve (AUC or c-statistic) for both training and testing data sets. RESULTS: Optimal classification trees achieve outstanding performance across all three models (mortality AUC = 0.86, prolonged MVST AUC = 0.85, prolonged LOS AUC = 0.82), while being intuitively interpretable. The most significant predictors of mortality are procedure, age, and weight, followed by days since previous admission and any general preoperative patient risk factors. CONCLUSIONS: The nonlinear ML-based models of OCTs are intuitively interpretable and provide superior predictive power. The associated risk calculator allows easy, accurate, and understandable estimation of individual patient risks, in the theoretical framework of the average performance of all centers represented in the database. This methodology has the potential to facilitate decision-making and resource optimization in CHS, enabling total quality management and precise benchmarking initiatives.
Authors: Alexis C Gimovsky; Daisy Zhuo; Jordan T Levine; Jack Dunn; Maxime Amarm; Alan M Peaceman Journal: Health Serv Res Date: 2022-01-12 Impact factor: 3.734
Authors: Jef Van den Eynde; Cedric Manlhiot; Alexander Van De Bruaene; Gerhard-Paul Diller; Alejandro F Frangi; Werner Budts; Shelby Kutty Journal: Front Cardiovasc Med Date: 2021-12-02