Acute myocardial infarction is a leading cause of cardiogenic shock and mortality. The aim of current study is to identify factors and develop machine learning models that predicts in-hospital mortality of ST-segment elevation myocardial infarction (STEMI) patients in South-East Asian population. This is a single center, retrospective study, from patients presenedt to the emergency room at Kaohsiung Chang Gung Memorial Hospital, Taiwan. The study included non-trauma adults (≥20 years of age) who were diagnosed with acute STEMI. A total of 1567 patients who met the inclusion criteria were enrolled. The area under the receiver operating characteristic curve was 0.839 in logistic regression (LR) and 0.825 in random forest (RF). The accuracy was 0.821 in LR and 0.812 in RF. The sensitivity and specificity were 0.883 and 0.815 in LR, and 0.875 and 0.806 in RF. In conclusion, the predictive models developed using LR and RF algorithms can be used to predict the risk of in-hospital death for STEMI patients.

Sepsis is among the most common conditions requiring emergency hospitalization. The early and accurate identification of sepsis patients with a high risk of in-hospital adverse events can aid physicians in making optimal clinical decisions. This study aimed to develop an explainable neural network model to predict adverse events during hospital admission in patients with suspected sepsis. Patient data were collected from a single medical center in Taiwan for the period of 2018–2020. The adverse events considered during hospital admission were cardiac arrest, respiratory failure requiring mechanical ventilation, and transfer to intensive care unit during admission. This study included 9398 patients in the analysis, with 6794 and 2603 patients in the development and validation sets, respectively. The proposed model could predict adverse events with an area under the receiver operating curve of 0.88 and 0.85 in the development and validation sets, respectively. Of the 2603 patients in the test set, 523 (20.1%) were classified as having adverse events during hospital admission. Of these patients, 104 eventually experienced adverse events. Thus, the model can predict adverse events with good performance and therefore, can be regarded as a gatekeeper before patients with sepsis are admitted to the general ward.