Dataset Information

Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact.

ABSTRACT: Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting ECG are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but we currently have no accurate tools to identify them during initial triage. Herein, we report 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, significantly boosting both precision and sensitivity. Our derived OMI risk score provided superior rule-in and rule-out accuracy compared to routine care, and when combined with the clinical judgment of trained emergency personnel, this score 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.

SUBMITTER: Al-Zaiti S

PROVIDER: S-EPMC9915770 | biostudies-literature | 2023 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact.

Al-Zaiti Salah S Martin-Gill Christian C Zégre-Hemsey Jessica J Bouzid Zeineb Z Faramand Ziad Z Alrawashdeh Mohammad M Gregg Richard R Helman Stephanie S Riek Nathan N Kraevsky-Phillips Karina K Clermont Gilles G Akcakaya Murat M Sereika Susan S Van Dam Peter P Smith Stephen S Birnbaum Yochai Y Saba Samir S Sejdic Ervin E Callaway Clifton C

Research square 20230130

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting ECG are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but we currently have no accurate tools to identify them during initial triage. Herein, we report 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 val ...[more]

PMID: 36778371

Similar Datasets

Project description:ObjectivesCompare gender disparities in ST-elevation myocardial infarction (STEMI) regarding first medical contact (FMC) and prehospital delay times and explore factors associated with prehospital delay in men and women separately.DesignCross-sectional study based on medical records and a validated questionnaire. Eligible patients were enrolled within 24 hours after admittance to hospital.SettingPatients were included from November 2012 to January 2014 from five Swedish hospitals with catheterisation facilities 24/7.Participants340 men and 109 women aged between 31 and 95 years completed the survey.Main outcome measuresFMC were divided into five possible contacts: primary healthcare centre by phone or directly, national advisory nurse by phone, emergency medical services (EMS) and emergency room directly. Two parts of prehospital delay times were studied: time from symptom onset to FMC and time from symptom onset to diagnostic ECG.ResultsWomen more often called an advisory nurse as FMC (28% vs 18%, p=0.02). They had a longer delay until FMC, 90 (IQR 39-221) vs 66 (28-161) min, p=0.04 and until ECG, 146 (68-316) vs 103 (61-221) min, p=0.03. Men went to hospital because of believing they were stricken by an MI to a higher extent than women did (25% vs 15%, p=0.04) and were more often recommended to call EMS by bystanders (38% vs 22%, p<0.01). Hesitating about going to hospital and experiencing pain in the stomach/back/shoulders were factors associated with longer delays in women. Believing the symptoms would disappear or interpreting them as nothing serious were corresponding factors in men. In both genders bystanders acting by contacting EMS explained shorter prehospital delays.ConclusionsIn STEMI, women differed from men in FMC and they had longer delays. This was partly due to atypical symptoms and a longer decision time. Bystanders acted more promptly when men than when women fell ill. Public knowledge of MI symptoms, and how to act properly, still seems insufficient.

Dataset Information

Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact.

Publications

Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets