Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction

Abstract

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting electrocardiogram (ECG) are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but, currently, there are no accurate tools to identify them during initial triage. Here we report, to our knowledge, the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI. Using 7,313 consecutive patients from multiple clinical sites, we derived and externally validated an intelligent model that outperformed practicing clinicians and other widely used commercial interpretation systems, substantially boosting both precision and sensitivity. Our derived OMI risk score provided enhanced rule-in and rule-out accuracy relevant to routine care, and, when combined with the clinical judgment of trained emergency personnel, it helped correctly reclassify one in three patients with chest pain. ECG features driving our models were validated by clinical experts, providing plausible mechanistic links to myocardial injury.

International evaluation of an artificial intelligence–powered electrocardiogram model detecting acute coronary occlusion myocardial infarction

“… 23 , 32–36 In addition, they often employed a spectrum of input clinical features in addition to the ECG waveform restricting their practical, real-world implementation. 16 , 37–43 Moreover, they depended on the acquisition of digital 10 s ECGs from a single vendor limiting the broader adoption. 23 , 31–43 Finally, their validation was not scrutinized in sizeable external and international data sets.…”

“…Recently, a machine learning approach has outperformed standard ECG criteria in detecting acute OMI correlating 73 hand-selected morphological ECG features and clinical parameters. 16 In this study, we introduce an international validation of an automated deep learning artificial intelligence (AI) model detecting acute OMI using only a single-standard 12-lead ECG as input and hypothesize that it would outperform the existing state-of-the-art ECG criteria for the detection of acute OMI and match the performance of interpreters with special expertise in ECG OMI diagnosis.…”

A machine learning-based predictive model of causality in orthopaedic medical malpractice cases in China

“…As for Random Forest, its hyperparameters had "n_estimators: range (10, 300, 10)", "min_samples_split: range (5, 50, 5)", "min_samples_leaf: range (2, 40, 2)", "max_depth: range (1, 30, 2)", "criterion: ’gini’, ’entropy’ ", "class_weight: None, ’balanced’ ". As for XGBoost, "max_depth: [ 3 , 5 , 7 ] ", "learning_rate: [0.1, 0.01, 0.001] ", "subsample: [0.1, 0.01, 0.001] ", "colsample_bytree: [0.5, 0.7, 1] ", "gamma: [0, 0.1, 0.2, 0.3, 0.4] ", "reg_alpha: [0, 0.001, 0.005, 0.01, 0.05] ", "reg_lambda: [0, 0.001, 0.005, 0.01, 0.05] ". The hyperparameters of LightGBM was same as XGBoost except "gamma".…”

“…Machine learning (ML) is subfield of artificial intelligence (AI) that focuses on teaching computers to identify and interpret patterns within data through training [ 1 ]. ML have demonstrated potential across various domains within the biomedical sciences, such as genomics [ 2 , 3 ], clinical medicine [ 4 , 5 ] and forensic medicine [ 6 , 7 ]. Models that have been published in clinical medicine can enhance the alertness of clinicians, carry out diagnostic procedures, predict events pertinent to clinical practice, and steer the process of making clinical decisions [ 8 , 9 ].…”

Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association

“…26 Second, AI/ML algorithms can identify subtle and interrelated nonlinear patterns in the ECG often not recognizable to experts, enhancing disease phenotyping. 30 Third, because cardiac electrical activity may be affected before mechanical or structural abnormalities are evident on imaging, such algorithms may enable the identification of occult disease and prediction of impending disease. By segregating subtypes of similar conditions, AI/ML of the ECG may reveal novel phenotypes.…”