Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2023 Jan 30:rs.3.rs-2510930.
doi: 10.21203/rs.3.rs-2510930/v1.

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

Salah Al-Zaiti  1 , Christian Martin-Gill  1 , Jessica Zégre-Hemsey  2 , Zeineb Bouzid  1 , Ziad Faramand  3 , Mohammad Alrawashdeh  4 , Richard Gregg  5 , Stephanie Helman  1 , Nathan Riek  1 , Karina Kraevsky-Phillips  1 , Gilles Clermont  1 , Murat Akcakaya  1 , Susan Sereika  1 , Peter Van Dam  6 , Stephen Smith  7 , Yochai Birnbaum  8 , Samir Saba  1 , Ervin Sejdic  9 , Clifton Callaway  1
Affiliations

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

Salah Al-Zaiti et al. Res Sq. .

Update in

  • Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction.
    Al-Zaiti SS, Martin-Gill C, Zègre-Hemsey JK, Bouzid Z, Faramand Z, Alrawashdeh MO, Gregg RE, Helman S, Riek NT, Kraevsky-Phillips K, Clermont G, Akcakaya M, Sereika SM, Van Dam P, Smith SW, Birnbaum Y, Saba S, Sejdic E, Callaway CW. Al-Zaiti SS, et al. Nat Med. 2023 Jul;29(7):1804-1813. doi: 10.1038/s41591-023-02396-3. Epub 2023 Jun 29. Nat Med. 2023. PMID: 37386246 Free PMC article.

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.

PubMed Disclaimer

Conflict of interest statement

DECLARATION OF INTERESTS

US Patent # 10820822, Owner: University of Pittsburgh, Inventors: SSA, ES, and CWC.

Figures

Figure 1
Figure 1. Cohort and sample selection
This flow diagram shows patient inclusion and exclusion in each cohort, as well as the dataset partition for training, internal testing, and external validation. Exclusions are not mutually exclusive.
Figure 2
Figure 2. Algorithm derivation and testing
This figure shows (A) the classification performance of the machine learning model against other reference standards for detecting occlusion myocardial infarction (OMI), (B) the probability density plots of OMI(+) and OMI(−) classes as denoted by the machine learning model, along with optimal cutoffs of low-risk, intermediate, and high-risk, and (C) distribution of patients in low-risk (+), intermediate risk (++) and high-risk (+++) as per the machine learning model and HEART score.
Figure 3
Figure 3. Model explainability for OMI detection
This figure shows (A) SHAP values for the 25 most important features driving the predictions of the machine learning classifier in the derivation cohort, and (B) the aggregate median beats of ECGs with occlusion myocardial infarction (OMI) class (red) and the aggregate median beats of ECGs with normal sinus rhythm and no OMI (blue).
Figure 4
Figure 4. External validation of ECG-SMART algorithm
This figure shows (A) the classification performance of the machine learning model against other reference standards for detecting occlusion myocardial infarction (OMI), (B) the independent clinical predictors of OMI on multivariate logistic regression testing, and (C) the overall sensitivity and specificity (95% confidence interval [CI]) of the derived OMI score, along with breakdown across subgroups based on age, sex, comorbidities, and baseline ECG findings. The size of markers denotes the sample size of the respective subgroup.
Figure 5
Figure 5. Decision analysis for the incremental gain of OMI risk score in reclassifying patients
This figure simulates the incremental gain of the derived risk score in reclassifying the initial triage decisions by emergency personnel at first medical contact.
See this image and copyright information in PMC

References

    1. Al-Zaiti S, Macleod MR, Van Dam PM, Smith SW, Birnbaum Y. Emerging ECG Methods for Acute Coronary Syndrome Detection: Recommendations & Future Opportunities. Journal of Electrocardiology. 2022;74:65–72. - PMC - PubMed
    1. Birnbaum Y, Wilson JM, Fiol M, de Luna AB, Eskola M, Nikus K. ECG diagnosis and classification of acute coronary syndromes. Annals of Noninvasive Electrocardiology. 2014;19(1):4–14. - PMC - PubMed
    1. Goodacre S, Pett P Arnold J, et al. Clinical diagnosis of acute coronary syndrome in patients with chest pain and a normal or non-diagnostic electrocardiogram. Emergency medicine journal. 2009;26(12):866–870. - PubMed
    1. Boubaker H, Grissa MH, Beltaief K, et al. A new score for the diagnosis of acute coronary syndrome in acute chest pain with non-diagnostic ECG and normal troponin. Emergency Medicine Journal. 2015;32(10):764–768. - PubMed
    1. Ioannidis JP Salem D, Chew PW, Lau J. Accuracy and clinical effect of out-of-hospital electrocardiography in the diagnosis of acute cardiac ischemia: a meta-analysis. Annals of emergency medicine. 2001;37(5):461–470. - PubMed

Publication types

LinkOut - more resources