Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model
Background Early prediction of heart failure (HF) after acute myocardial infarction (AMI) is essential for personalized treatment. We aimed to use interpretable machine learning (ML) methods to develop a risk prediction model for HF in AMI patients.MethodsWe retrospectively included patients initial...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2025.1444323/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589846310289408 |
|---|---|
| author | Qingqing Lin Qingqing Lin Wenxiang Zhao Wenxiang Zhao Hailin Zhang Hailin Zhang Wenhao Chen Sheng Lian Qinyun Ruan Qinyun Ruan Zhaoyang Qu Zhaoyang Qu Yimin Lin Yimin Lin Dajun Chai Dajun Chai Dajun Chai Dajun Chai Xiaoyan Lin Xiaoyan Lin Xiaoyan Lin Xiaoyan Lin |
| author_facet | Qingqing Lin Qingqing Lin Wenxiang Zhao Wenxiang Zhao Hailin Zhang Hailin Zhang Wenhao Chen Sheng Lian Qinyun Ruan Qinyun Ruan Zhaoyang Qu Zhaoyang Qu Yimin Lin Yimin Lin Dajun Chai Dajun Chai Dajun Chai Dajun Chai Xiaoyan Lin Xiaoyan Lin Xiaoyan Lin Xiaoyan Lin |
| author_sort | Qingqing Lin |
| collection | DOAJ |
| description | Background
Early prediction of heart failure (HF) after acute myocardial infarction (AMI) is essential for personalized treatment. We aimed to use interpretable machine learning (ML) methods to develop a risk prediction model for HF in AMI patients.MethodsWe retrospectively included patients initially with AMI who received percutaneous coronary intervention (PCI) in our hospital from November 2016 to February 2020. The primary endpoint was the occurrence of HF within 3 years after operation. For developing a predictive model for HF risk in AMI patients, the least absolute shrinkage and selection operator (LASSO) Regression was used to feature selection, and four ML algorithms including Random Forest (RF), Extreme Gradient Boost (XGBoost), Support Vector Machine (SVM), and Logistic Regression (LR) were employed to develop the model on the training set. The performance evaluation of the prediction model was carried out on the training set and the testing set, utilizing metrics including AUC (Area under the receiver operating characteristic curve), calibration plot, and decision curve analysis (DCA). In addition, we used the Shapley Additive Explanations (SHAP) value to determine the importance of the selected features and interpret the optimal model.ResultsA total of 1220 AMI patients were included and 244 (20%) patients developed HF during follow-up. Among the four evaluated ML models, the XGBoost model exhibited exceptional accuracy, with an AUC value of 0.922. The SHAP method showed that left ventricular ejection fraction (LVEF), left ventricular end-systolic diameter (LVDs) and lactate dehydrogenase (LDH) were identified as the three most important characteristics to predict HF risk in AMI patients. Individual risk assessment was performed using SHAP plots and waterfall plot analysis.ConclusionsOur research demonstrates the potential of ML methods in the early prediction of HF risk in AMI patients. Furthermore, it enhances the interpretability of the XGBoost model through SHAP analysis to guide clinical decision-making. |
| format | Article |
| id | doaj-art-6c2d377746c14e4c9333e3e9ca590b9b |
| institution | Kabale University |
| issn | 2297-055X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj-art-6c2d377746c14e4c9333e3e9ca590b9b2025-01-24T07:13:32ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2025-01-011210.3389/fcvm.2025.14443231444323Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning modelQingqing Lin0Qingqing Lin1Wenxiang Zhao2Wenxiang Zhao3Hailin Zhang4Hailin Zhang5Wenhao Chen6Sheng Lian7Qinyun Ruan8Qinyun Ruan9Zhaoyang Qu10Zhaoyang Qu11Yimin Lin12Yimin Lin13Dajun Chai14Dajun Chai15Dajun Chai16Dajun Chai17Xiaoyan Lin18Xiaoyan Lin19Xiaoyan Lin20Xiaoyan Lin21Department of Ultrasound, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaDepartment of Cardiology, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaDepartment of Cardiology, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaFujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, ChinaFujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, ChinaDepartment of Ultrasound, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaDepartment of Ultrasound, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaDepartment of Ultrasound, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaDepartment of Cardiology, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaKey Laboratory of Metabolic Cardiovascular Disease of Fujian Province Colleges and Universities, Fuzhou, ChinaClinical Research Center for Metabolic Heart Disease of Fujian Province, Fuzhou, ChinaDepartment of Ultrasound, The First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaNational Regional Medical Center, Binhai Branch of the First Affiliated Hospital, Fujian Medical University, Fuzhou, ChinaKey Laboratory of Metabolic Cardiovascular Disease of Fujian Province Colleges and Universities, Fuzhou, ChinaClinical Research Center for Metabolic Heart Disease of Fujian Province, Fuzhou, ChinaBackground Early prediction of heart failure (HF) after acute myocardial infarction (AMI) is essential for personalized treatment. We aimed to use interpretable machine learning (ML) methods to develop a risk prediction model for HF in AMI patients.MethodsWe retrospectively included patients initially with AMI who received percutaneous coronary intervention (PCI) in our hospital from November 2016 to February 2020. The primary endpoint was the occurrence of HF within 3 years after operation. For developing a predictive model for HF risk in AMI patients, the least absolute shrinkage and selection operator (LASSO) Regression was used to feature selection, and four ML algorithms including Random Forest (RF), Extreme Gradient Boost (XGBoost), Support Vector Machine (SVM), and Logistic Regression (LR) were employed to develop the model on the training set. The performance evaluation of the prediction model was carried out on the training set and the testing set, utilizing metrics including AUC (Area under the receiver operating characteristic curve), calibration plot, and decision curve analysis (DCA). In addition, we used the Shapley Additive Explanations (SHAP) value to determine the importance of the selected features and interpret the optimal model.ResultsA total of 1220 AMI patients were included and 244 (20%) patients developed HF during follow-up. Among the four evaluated ML models, the XGBoost model exhibited exceptional accuracy, with an AUC value of 0.922. The SHAP method showed that left ventricular ejection fraction (LVEF), left ventricular end-systolic diameter (LVDs) and lactate dehydrogenase (LDH) were identified as the three most important characteristics to predict HF risk in AMI patients. Individual risk assessment was performed using SHAP plots and waterfall plot analysis.ConclusionsOur research demonstrates the potential of ML methods in the early prediction of HF risk in AMI patients. Furthermore, it enhances the interpretability of the XGBoost model through SHAP analysis to guide clinical decision-making.https://www.frontiersin.org/articles/10.3389/fcvm.2025.1444323/fullacute myocardial infarctionheart failuremachine learningpredictshapley additive explanations |
| spellingShingle | Qingqing Lin Qingqing Lin Wenxiang Zhao Wenxiang Zhao Hailin Zhang Hailin Zhang Wenhao Chen Sheng Lian Qinyun Ruan Qinyun Ruan Zhaoyang Qu Zhaoyang Qu Yimin Lin Yimin Lin Dajun Chai Dajun Chai Dajun Chai Dajun Chai Xiaoyan Lin Xiaoyan Lin Xiaoyan Lin Xiaoyan Lin Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model Frontiers in Cardiovascular Medicine acute myocardial infarction heart failure machine learning predict shapley additive explanations |
| title | Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model |
| title_full | Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model |
| title_fullStr | Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model |
| title_full_unstemmed | Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model |
| title_short | Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model |
| title_sort | predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model |
| topic | acute myocardial infarction heart failure machine learning predict shapley additive explanations |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2025.1444323/full |
| work_keys_str_mv | AT qingqinglin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT qingqinglin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT wenxiangzhao predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT wenxiangzhao predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT hailinzhang predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT hailinzhang predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT wenhaochen predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT shenglian predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT qinyunruan predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT qinyunruan predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT zhaoyangqu predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT zhaoyangqu predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT yiminlin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT yiminlin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT dajunchai predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT dajunchai predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT dajunchai predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT dajunchai predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT xiaoyanlin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT xiaoyanlin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT xiaoyanlin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel AT xiaoyanlin predictingtheriskofheartfailureafteracutemyocardialinfarctionusinganinterpretablemachinelearningmodel |