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

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.

Machine learning predicts emergency physician specialties from treatment strategies for patients suspected of myocardial infarction.

BACKGROUND: Our investigation aimed to determine how the diverse backgrounds and medical specialties of emergency physicians (Eps) influence the accuracy of diagnoses and the subsequent treatment pathways for patients presenting preclinically with MI symptoms. By scrutinizing the relationships between EPs' specialties and their approaches to patient care, we aimed to unveil potential variances in diagnostic accuracy and treatment choices. METHODS: In this retrospective, monocenter cohort study, we leveraged machine learning techniques to analyze a comprehensive dataset of 2328 patients with suspected MI, encompassing preclinical diagnoses, electrocardiogram (ECG) interpretations, and subsequent treatment strategies by attending EPs. RESULTS: We demonstrated that diagnosis and treatment patterns of different specialties were distinct enough, that machine learning (ML) was able to differentiate between specialties (maximum area under the receiver operating characteristic = 0.80 for general medicine and 0.80 for surgery). In our study, internist demonstrated the highest accuracy for preclinical identification of STEMI (0.96) whereas surgeons showed the highest accuracy for identifying NSTEMI. Our findings highlight significant correlations between EP specialties and the accuracy of both preclinical diagnoses and subsequent treatment pathways for patients with suspected MI. CONCLUSIONS: Our results offer valuable insights into how the diverse backgrounds and specialties of EPs can influence the optimization of patient care in emergency settings. Understanding these patterns can help in the development of tailored training programs and protocols to enhance diagnostic accuracy and treatment efficacy in emergency cardiac care, ultimately optimizing patient treatment and improving outcomes.