Shangyu Liu1, Shengwen Yang2, Anlu Xing3, Lihui Zheng1, Lishui Shen1, Bin Tu1, Yan Yao1. 1. The Cardiac Arrhythmia Center, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. 2. Beijing Key Laboratory of Hypertension, Beijing Chaoyang Hospital, Capital Medical University, Beijing, China. 3. Autodesk, San Francisco, CA, USA.
Abstract
BACKGROUND: Traditional prognostic risk assessment in patients with coronary artery disease undergoing percutaneous coronary intervention (PCI) is based on a limited selection of clinical and imaging findings. Machine learning (ML) can consider a higher number and complexity of variables and may be useful for characterising cardiovascular risk, predicting outcomes, and identifying biomarkers in large population studies. METHODS: We prospectively enrolled 9,680 consecutive patients with coronary artery disease who underwent PCI at our institution between January 2013 and December 2013. Clinical features were selected and used to train 6 different ML models (support vector machine, decision tree, random forest, gradient boosting decision tree, neural network, and logistic regression) to predict cardiovascular outcomes, 10-fold cross-validation to evaluate the performance of models. RESULTS: During the 5-year follow-up, 467 (4.82%) patients died. Eighty-seven risk baseline measurements were used to train ML models. Compared with the other models, the random forest model (RF-PCI) exhibited the best performance on predicting all-cause mortality (area under the receiver operating characteristic curve: 0.71±0.04). Calibration plots demonstrated a slight overprediction for patients using the RF-PCI model (Hosmer-Lemeshow test: P>0.05). The top 15 features related to PCI candidates' long-term prognosis, among which 11 were laboratory measures. CONCLUSIONS: ML models improved the prediction of long-term all-cause mortality in patients with coronary artery disease before PCI. The performance of the RF model was better than that of the other models, providing a meaningful stratification. 2021 Cardiovascular Diagnosis and Therapy. All rights reserved.
BACKGROUND: Traditional prognostic risk assessment in patients with coronary artery disease undergoing percutaneous coronary intervention (PCI) is based on a limited selection of clinical and imaging findings. Machine learning (ML) can consider a higher number and complexity of variables and may be useful for characterising cardiovascular risk, predicting outcomes, and identifying biomarkers in large population studies. METHODS: We prospectively enrolled 9,680 consecutive patients with coronary artery disease who underwent PCI at our institution between January 2013 and December 2013. Clinical features were selected and used to train 6 different ML models (support vector machine, decision tree, random forest, gradient boosting decision tree, neural network, and logistic regression) to predict cardiovascular outcomes, 10-fold cross-validation to evaluate the performance of models. RESULTS: During the 5-year follow-up, 467 (4.82%) patients died. Eighty-seven risk baseline measurements were used to train ML models. Compared with the other models, the random forest model (RF-PCI) exhibited the best performance on predicting all-cause mortality (area under the receiver operating characteristic curve: 0.71±0.04). Calibration plots demonstrated a slight overprediction for patients using the RF-PCI model (Hosmer-Lemeshow test: P>0.05). The top 15 features related to PCI candidates' long-term prognosis, among which 11 were laboratory measures. CONCLUSIONS: ML models improved the prediction of long-term all-cause mortality in patients with coronary artery disease before PCI. The performance of the RF model was better than that of the other models, providing a meaningful stratification. 2021 Cardiovascular Diagnosis and Therapy. All rights reserved.
Authors: E M Antman; M Cohen; P J Bernink; C H McCabe; T Horacek; G Papuchis; B Mautner; R Corbalan; D Radley; E Braunwald Journal: JAMA Date: 2000-08-16 Impact factor: 56.272
Authors: Subhi J Al'Aref; Khalil Anchouche; Gurpreet Singh; Piotr J Slomka; Kranthi K Kolli; Amit Kumar; Mohit Pandey; Gabriel Maliakal; Alexander R van Rosendael; Ashley N Beecy; Daniel S Berman; Jonathan Leipsic; Koen Nieman; Daniele Andreini; Gianluca Pontone; U Joseph Schoepf; Leslee J Shaw; Hyuk-Jae Chang; Jagat Narula; Jeroen J Bax; Yuanfang Guan; James K Min Journal: Eur Heart J Date: 2019-06-21 Impact factor: 29.983
Authors: Geert Litjens; Francesco Ciompi; Jelmer M Wolterink; Bob D de Vos; Tim Leiner; Jonas Teuwen; Ivana Išgum Journal: JACC Cardiovasc Imaging Date: 2019-08
Authors: Marco Roffi; Carlo Patrono; Jean-Philippe Collet; Christian Mueller; Marco Valgimigli; Felicita Andreotti; Jeroen J Bax; Michael A Borger; Carlos Brotons; Derek P Chew; Baris Gencer; Gerd Hasenfuss; Keld Kjeldsen; Patrizio Lancellotti; Ulf Landmesser; Julinda Mehilli; Debabrata Mukherjee; Robert F Storey; Stephan Windecker Journal: Eur Heart J Date: 2015-08-29 Impact factor: 29.983