Yunlong Fan1,2, Junfeng Dong3, Yuanbin Wu1,2, Ming Shen4, Siming Zhu1,2, Xiaoyi He1,2, Shengli Jiang2, Jiakang Shao1, Chao Song1,2. 1. Medical School of Chinese PLA, Beijing, China. 2. Department of Cardiovascular Surgery, the First Medical Centre of Chinese PLA General Hospital, Beijing, China. 3. Department of Organ Transplantation, Changzhen Hospital, Navy Medical University, Shanghai, China. 4. Department of Cardiology, The First Hospital of Hebei Medical University, Shijiazhuang, China.
Abstract
Background: We developed machine learning models that combine preoperative and intraoperative risk factors to predict mortality after cardiac surgery. Methods: Machine learning involving random forest, neural network, support vector machine, and gradient boosting machine was developed and compared with the risk scores of EuroSCORE I and II, Society of Thoracic Surgeons (STS), as well as a logistic regression model. Clinical data were collected from patients undergoing adult cardiac surgery at the First Medical Centre of Chinese PLA General Hospital between December 2008 and December 2017. The primary outcome was post-operative mortality. Model performance was estimated using several metrics, including sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC). The visualization algorithm was implemented using Shapley's additive explanations. Results: A total of 5,443 patients were enrolled during the study period. The mean EuroSCORE II score was 3.7%, and the actual in-hospital mortality rate was 2.7%. For predicting operative mortality after cardiac surgery, the AUC scores were 0.87, 0.79, 0.81, and 0.82 for random forest, neural network, support vector machine, and gradient boosting machine, compared with 0.70, 0.73, 0.71, and 0.74 for EuroSCORE I and II, STS, and logistic regression model. Shapley's additive explanations analysis of random forest yielded the top-20 predictors and individual-level explanations for each prediction. Conclusions: Machine learning models based on available clinical data may be superior to clinical scoring tools in predicting postoperative mortality in patients following cardiac surgery. Explanatory models show the potential to provide personalized risk profiles for individuals by accounting for the contribution of influencing factors. Additional prospective multicenter studies are warranted to confirm the clinical benefit of these machine learning-driven models. 2022 Cardiovascular Diagnosis and Therapy. All rights reserved.
Background: We developed machine learning models that combine preoperative and intraoperative risk factors to predict mortality after cardiac surgery. Methods: Machine learning involving random forest, neural network, support vector machine, and gradient boosting machine was developed and compared with the risk scores of EuroSCORE I and II, Society of Thoracic Surgeons (STS), as well as a logistic regression model. Clinical data were collected from patients undergoing adult cardiac surgery at the First Medical Centre of Chinese PLA General Hospital between December 2008 and December 2017. The primary outcome was post-operative mortality. Model performance was estimated using several metrics, including sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC). The visualization algorithm was implemented using Shapley's additive explanations. Results: A total of 5,443 patients were enrolled during the study period. The mean EuroSCORE II score was 3.7%, and the actual in-hospital mortality rate was 2.7%. For predicting operative mortality after cardiac surgery, the AUC scores were 0.87, 0.79, 0.81, and 0.82 for random forest, neural network, support vector machine, and gradient boosting machine, compared with 0.70, 0.73, 0.71, and 0.74 for EuroSCORE I and II, STS, and logistic regression model. Shapley's additive explanations analysis of random forest yielded the top-20 predictors and individual-level explanations for each prediction. Conclusions: Machine learning models based on available clinical data may be superior to clinical scoring tools in predicting postoperative mortality in patients following cardiac surgery. Explanatory models show the potential to provide personalized risk profiles for individuals by accounting for the contribution of influencing factors. Additional prospective multicenter studies are warranted to confirm the clinical benefit of these machine learning-driven models. 2022 Cardiovascular Diagnosis and Therapy. All rights reserved.
Authors: David M Shahian; Eugene H Blackstone; Fred H Edwards; Frederick L Grover; Gary L Grunkemeier; David C Naftel; Samer A M Nashef; William C Nugent; Eric D Peterson Journal: Ann Thorac Surg Date: 2004-11 Impact factor: 4.330
Authors: Scott M Lundberg; Gabriel Erion; Hugh Chen; Alex DeGrave; Jordan M Prutkin; Bala Nair; Ronit Katz; Jonathan Himmelfarb; Nisha Bansal; Su-In Lee Journal: Nat Mach Intell Date: 2020-01-17
Authors: Sean M O'Brien; Liqi Feng; Xia He; Ying Xian; Jeffrey P Jacobs; Vinay Badhwar; Paul A Kurlansky; Anthony P Furnary; Joseph C Cleveland; Kevin W Lobdell; Christina Vassileva; Moritz C Wyler von Ballmoos; Vinod H Thourani; J Scott Rankin; James R Edgerton; Richard S D'Agostino; Nimesh D Desai; Fred H Edwards; David M Shahian Journal: Ann Thorac Surg Date: 2018-03-22 Impact factor: 4.330
Authors: Arman Kilic; Anshul Goyal; James K Miller; Eva Gjekmarkaj; Weng Lam Tam; Thomas G Gleason; Ibrahim Sultan; Artur Dubrawksi Journal: Ann Thorac Surg Date: 2019-11-07 Impact factor: 4.330
Authors: Bharath Ambale-Venkatesh; Xiaoying Yang; Colin O Wu; Kiang Liu; W Gregory Hundley; Robyn McClelland; Antoinette S Gomes; Aaron R Folsom; Steven Shea; Eliseo Guallar; David A Bluemke; João A C Lima Journal: Circ Res Date: 2017-08-09 Impact factor: 17.367
Authors: Niv Ad; Sari D Holmes; Jay Patel; Graciela Pritchard; Deborah J Shuman; Linda Halpin Journal: Ann Thorac Surg Date: 2016-04-23 Impact factor: 4.330
Authors: Mireille Nieuwenhuis; Hugo G Schnack; Neeltje E van Haren; Julia Lappin; Craig Morgan; Antje A Reinders; Diana Gutierrez-Tordesillas; Roberto Roiz-Santiañez; Maristela S Schaufelberger; Pedro G Rosa; Marcus V Zanetti; Geraldo F Busatto; Benedicto Crespo-Facorro; Patrick D McGorry; Dennis Velakoulis; Christos Pantelis; Stephen J Wood; René S Kahn; Janaina Mourao-Miranda; Paola Dazzan Journal: Neuroimage Date: 2016-07-12 Impact factor: 6.556
Authors: Sergey Efremov; Vladimir Lomivorotov; Christian Stoppe; Anna Shilova; Vladimir Shmyrev; Michail Deryagin; Alexander Karaskov Journal: Nutrients Date: 2017-11-20 Impact factor: 5.717