ST-elevation myocardial infarction(STEMI)remains a leading cause of cardiovascular morbidity and mortality worldwide,and accurate early risk stratification is critical for implementing precision therapies in clinical ...ST-elevation myocardial infarction(STEMI)remains a leading cause of cardiovascular morbidity and mortality worldwide,and accurate early risk stratification is critical for implementing precision therapies in clinical practice.However,existing clinical risk scores and manually derived imaging biomarkers have limited accuracy in predicting post-STEMI outcomes.To address this gap,we developed DeepSTEMI,an end-to-end deep learning system that integrates multi-sequence cardiac magnetic resonance(CMR)images with clinical parameters for predicting 2-year major adverse cardiovascular events(MACE).The system comprised two key algorithmic modules:a U-Net module that automatically segments heart regions from raw CMR images and a Transformer-based module that predicted future cardiovascular events.DeepSTEMI was developed using a multicenter dataset(n=610;20,618 images)from STEMI patients enrolled in the EARLY-MYO-CMR registry(NCT03768453),with external validation performed in 334 patients(9944 images)from three independent cardiac centers.In external validation,DeepSTEMI demonstrated superior predictive performance compared to conventional clinical risk scores and manual CMR parameters(AUC 0.894,95%CI:0.823-0.965;overall accuracy 94.3%).The model identified high-risk patients who exhibited a 20-fold MACE risk compared to low-risk counterparts(HR 20.43,log-rank P<0.001).SHapley Additive exPlanations(SHAP)analysis revealed that DeepSTEMI's predictive power stems from clinical-imaging synergy,enabling it to capture complex pathological patterns.DeepSTEMI achieved consistently superior performance over the Eitel score across all subgroups,with the greatest benefit observed in women(NRI 1.597)and in patients imaged 4-7 d post-STEMI(NRI 1.442).Overall,DeepSTEMI serves as an automated,scalable,and interpretable clinical copilot,which advances postSTEMI risk stratification beyond the limitations of current paradigms.展开更多
基金supported by the Innovative Research Group Project of China’s National Natural Science Foundation(82421001)the National Natural Science Foundation of China(823B2005,824B1015,U21A20341,T2525004,82470394,82230014,82202159,81930007,81971570,and 32100426)+13 种基金the National Key Research and Development Program of China(2021YFC2502300 and 2022YFE0103500)the National Science Fund for Distinguished Young Scholars(81625002)the Shanghai Municipal Health Commission(2022JC013,2023ZZ02021,GWVI11.1-26,and 2022ZZ01008)the Science and Technology Commission of Shanghai Municipality(24DZ2202700,22DZ2292400,22JC1402100,and 20YF1426100)the Program of Shanghai Academic Research Leader(21XD1432100)the Shanghai Municipal Education Commission(SHSMU-ZDCX20210700)the Shanghai Municipal Health Commission(202440156)the Shanghai Institutions of Higher Learning,Innovative Research Team of High-Level Local Universities in Shanghai(SHSMU-ZDCX20210700)(Project 2021-01-07-00-02-E00083)the National High Level Hospital Clinical Research Funding(2022-PUMCH-C-023)the MedicalEngineering Joint Funds of Shanghai Jiao Tong University(YG2022QN107 and 2025ZYB-007)the Shanghai Clinical Cohort Program(Reserve Clinical Cohort)by the Shanghai Hospital Deveopment Center(SHDC2025CCS037)the Shanghai Professional Technical Service Platform for Cardio-Cerebral Disease Biobank and Database(22DZ2292400)the Pudong New District Health Commission(PW2023E-02)support from the innovative research team of high-level local universities in Shanghai。
文摘ST-elevation myocardial infarction(STEMI)remains a leading cause of cardiovascular morbidity and mortality worldwide,and accurate early risk stratification is critical for implementing precision therapies in clinical practice.However,existing clinical risk scores and manually derived imaging biomarkers have limited accuracy in predicting post-STEMI outcomes.To address this gap,we developed DeepSTEMI,an end-to-end deep learning system that integrates multi-sequence cardiac magnetic resonance(CMR)images with clinical parameters for predicting 2-year major adverse cardiovascular events(MACE).The system comprised two key algorithmic modules:a U-Net module that automatically segments heart regions from raw CMR images and a Transformer-based module that predicted future cardiovascular events.DeepSTEMI was developed using a multicenter dataset(n=610;20,618 images)from STEMI patients enrolled in the EARLY-MYO-CMR registry(NCT03768453),with external validation performed in 334 patients(9944 images)from three independent cardiac centers.In external validation,DeepSTEMI demonstrated superior predictive performance compared to conventional clinical risk scores and manual CMR parameters(AUC 0.894,95%CI:0.823-0.965;overall accuracy 94.3%).The model identified high-risk patients who exhibited a 20-fold MACE risk compared to low-risk counterparts(HR 20.43,log-rank P<0.001).SHapley Additive exPlanations(SHAP)analysis revealed that DeepSTEMI's predictive power stems from clinical-imaging synergy,enabling it to capture complex pathological patterns.DeepSTEMI achieved consistently superior performance over the Eitel score across all subgroups,with the greatest benefit observed in women(NRI 1.597)and in patients imaged 4-7 d post-STEMI(NRI 1.442).Overall,DeepSTEMI serves as an automated,scalable,and interpretable clinical copilot,which advances postSTEMI risk stratification beyond the limitations of current paradigms.
