Preclinical identification of acute coronary syndrome without high sensitivity troponin assays using machine learning algorithms

Abstract

Preclinical management of patients with acute chest pain and their identification as candidates for urgent coronary revascularization without the use of high sensitivity troponin essays remains a critical challenge in emergency medicine. We enrolled 2760 patients (average age 70 years, 58.6% male) with chest pain and suspected ACS, who were admitted to the Emergency Department of the University Hospital Tübingen, Germany, between August 2016 and October 2020. Using 26 features, eight Machine learning models (non-deep learning models) were trained with data from the preclinical rescue protocol and compared to the “TropOut” score (a modified version of the “preHEART” score which consists of history, ECG, age and cardiac risk but without troponin analysis) to predict major adverse cardiac event (MACE) and acute coronary artery occlusion (ACAO). In our study population MACE occurred in 823 (29.8%) patients and ACAO occurred in 480 patients (17.4%). Interestingly, we found that all machine learning models outperformed the “TropOut” score. The VC and the LR models showed the highest area under the receiver operating characteristic (AUROC) for predicting MACE (AUROC = 0.78) and the VC showed the highest AUROC for predicting ACAO (AUROC = 0.81). A SHapley Additive exPlanations (SHAP) analyses based on the XGB model showed that presence of ST-elevations in the electrocardiogram (ECG) were the most important features to predict both endpoints.

Convolutional Neural Network-Based ECG Signal Classification Model: A Study on Addressing Class Imbalance and Enhancing Model Interpretability

“…For instance, Rashed-Al-Mahfu et al [30] successfully demonstrated the effectiveness of SHAP value analysis in identifying key frequency features that impact ECG signal classification. Moreover, Goldschmied et al [31] used SHAP value analysis to reveal ST-segment elevation in ECG as a key predictor of cardiac events, while Mehari et al [32] showed a strong correlation between SHAP values and other feature importance ranking methods, providing new perspectives for heart disease diagnosis. The ECG-iCOVIDNet model proposed by Agrawal et al [33] enhanced the interpretability of ECG changes in COVID-19 convalescent patients using SHAP technology, and Jekova et al [34] assessed the importance of atrioventricular synchrony in atrial fibrillation detection with SHAP value analysis.…”