Machine learning models that integrate cardiac troponin concentrations and clinical features to compute the probability of myocardial infarction outperform current care pathways that use fixed troponin thresholds or risk scores. Adoption of these models could reduce inequalities, prevent unnecessary admissions, and accelerate the diagnosis and treatment of patients with myocardial infarction.

中文翻译：

---

用机器学习改进心肌梗死的诊断

结合心肌肌钙蛋白浓度和临床特征来计算心肌梗死概率的机器学习模型优于使用固定肌钙蛋白阈值或风险评分的当前护理途径。采用这些模型可以减少不平等现象，防止不必要的入院，并加快心肌梗死患者的诊断和治疗。