Advertisement
Mayo Clinic Proceedings Home

Implementation of an All-Day Artificial Intelligence–Based Triage System to Accelerate Door-to-Balloon Times

Published:November 03, 2022DOI:https://doi.org/10.1016/j.mayocp.2022.05.014

      Abstract

      Objective

      To implement an all-day artificial intelligence (AI)–based system to facilitate chest pain triage in the emergency department.

      Methods

      The AI-based triage system encompasses an AI model combining a convolutional neural network and long short-term memory to detect ST-elevation myocardial infarction (STEMI) on electrocardiography (ECG) and a clinical risk score (ASAP) to prioritize patients for ECG examination. The AI model was developed on 2907 twelve-lead ECGs: 882 STEMI and 2025 non-STEMI ECGs.

      Results

      Between November 1, 2019, and October 31, 2020, we enrolled 154 consecutive patients with STEMI: 68 during the AI-based triage period and 86 during the conventional triage period. The mean ± SD door-to-balloon (D2B) time was significantly shortened from 64.5±35.3 minutes to 53.2±12.7 minutes (P=.007), with 98.5% vs 87.2% (P=.009) of D2B times being less than 90 minutes in the AI group vs the conventional group. Among patients with an ASAP score of 3 or higher, the median door-to-ECG time decreased from 30 minutes (interquartile range [IQR], 7−59 minutes) to 6 minutes (IQR, 4−30 minutes) (P<.001). The overall performances of the AI model in identifying STEMI from 21,035 ECGs assessed by accuracy, precision, recall, area under the receiver operating characteristic curve, F1 score, and specificity were 0.997, 0.802, 0.977, 0.999, 0.881, and 0.998, respectively.

      Conclusion

      Implementation of an all-day AI-based triage system significantly reduced the D2B time, with a corresponding increase in the percentage of D2B times less than 90 minutes in the emergency department. This system may help minimize preventable delays in D2B times for patients with STEMI undergoing primary percutaneous coronary intervention.

      Abbreviations and Acronyms:

      1D (1-dimensional), AI (artificial intelligence), CAD (coronary artery disease), cath lab (catheterization laboratory), CNN (convolutional neural network), D2B (door-to-balloon), ECG (electrocardiography), ED (emergency department), GRACE (Global Registry of Acute Coronary Events), LSTM (long short-term memory), PPCI (primary percutaneous coronary intervention), STEMI (ST-segment elevation myocardial infarction), TIMI (Thrombolysis in Myocardial Infarction)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Mayo Clinic Proceedings
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Gibson C.M.
        • Pride Y.B.
        • Frederick P.D.
        • et al.
        Trends in reperfusion strategies, door-to-needle and door-to-balloon times, and in-hospital mortality among patients with ST-segment elevation myocardial infarction enrolled in the National Registry of Myocardial Infarction from 1990 to 2006.
        Am Heart J. 2008; 156: 1035-1044
        • Sivagangabalan G.
        • Ong A.T.
        • Narayan A.
        • et al.
        Effect of prehospital triage on revascularization times, left ventricular function, and survival in patients with ST-elevation myocardial infarction.
        Am J Cardiol. 2009; 103: 907-912
        • Gersh B.J.
        • Stone G.W.
        • White H.D.
        • Holmes Jr., D.R.
        Pharmacological facilitation of primary percutaneous coronary intervention for acute myocardial infarction: is the slope of the curve the shape of the future?.
        JAMA. 2005; 293: 979-986
        • O'Gara P.T.
        • Kushner F.G.
        • Ascheim D.D.
        • et al.
        2013 ACCF/AHA guideline for the management of ST-elevation myocardial infarction: a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines.
        J Am Coll Cardiol. 2013; 61: e78-e140
        • Ibanez B.
        • James S.
        • Agewall S.
        • et al.
        2017 ESC Guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation: the Task Force for the management of acute myocardial infarction in patients presenting with ST-segment elevation of the European Society of Cardiology (ESC).
        Eur Heart J. 2018; 39: 119-177
        • Garvey J.L.
        • Zegre-Hemsey J.
        • Gregg R.
        • Studnek J.R.
        Electrocardiographic diagnosis of ST segment elevation myocardial infarction: an evaluation of three automated interpretation algorithms.
        J Electrocardiol. 2016; 49: 728-732
        • Bosson N.
        • Sanko S.
        • Stickney R.E.
        • et al.
        Causes of prehospital misinterpretations of ST elevation myocardial infarction.
        Prehosp Emerg Care. 2017; 21: 283-290
        • Chang K.C.
        • Hsieh P.H.
        • Wu M.Y.
        • et al.
        Usefulness of multi-labelling artificial intelligence in detecting rhythm disorders and acute ST-elevation myocardial infarction on 12-lead electrocardiogram.
        Eur Heart J Digial Health. 2021; 2: 299-310
        • Chang K.C.
        • Hsieh P.H.
        • Wu M.Y.
        • et al.
        Usefulness of machine learning-based detection and classification of cardiac arrhythmias with 12-lead electrocardiograms.
        Can J Cardiol. 2021; 37: 94-104
        • Thygesen K.
        • Alpert J.S.
        • Jaffe A.S.
        • et al.
        Third universal definition of myocardial infarction.
        Circulation. 2012; 126: 2020-2035
        • GRACE Investigators
        Rationale and design of the GRACE (Global Registry of Acute Coronary Events) Project: a multinational registry of patients hospitalized with acute coronary syndromes.
        Am Heart J. 2001; 141: 190-199
        • Wilson P.W.
        • D'Agostino R.B.
        • Levy D.
        • Belanger A.M.
        • Silbershatz H.
        • Kannel W.B.
        Prediction of coronary heart disease using risk factor categories.
        Circulation. 1998; 97: 1837-1847
        • Rathore S.S.
        • Curtis J.P.
        • Chen J.
        • et al.
        Association of door-to-balloon time and mortality in patients admitted to hospital with ST elevation myocardial infarction: national cohort study.
        BMJ. 2009; 338: b1807
        • McNamara R.L.
        • Wang Y.
        • Herrin J.
        • et al.
        Effect of door-to-balloon time on mortality in patients with ST-segment elevation myocardial infarction.
        J Am Coll Cardiol. 2006; 47: 2180-2186
        • Nallamothu B.K.
        • Normand S.L.
        • Wang Y.
        • et al.
        Relation between door-to-balloon times and mortality after primary percutaneous coronary intervention over time: a retrospective study.
        Lancet. 2015; 385: 1114-1122
        • Foo C.Y.
        • Andrianopoulos N.
        • Brennan A.
        • et al.
        Re-examining the effect of door-to-balloon delay on STEMI outcomes in the context of unmeasured confounders: a retrospective cohort study.
        Sci Rep. 2019; 919978
        • Park J.
        • Choi K.H.
        • Lee J.M.
        • et al.
        Prognostic implications of door-to-balloon time and onset-to-door time on mortality in patients with ST-segment-elevation myocardial infarction treated with primary percutaneous coronary intervention.
        J Am Heart Assoc. 2019; 8e012188
        • Wang Y.C.
        • Huang Y.Y.
        • Lo P.H.
        • Chang K.C.
        • Chen C.H.
        • Chen M.F.
        Age-dependent impact of new ESC-Guideline recommended door-to-balloon times on mid-term survival in acute ST-elevation myocardial infarction patients undergoing primary percutaneous coronary intervention.
        Int J Cardiol. 2016; 222: 242-246
        • Wang Y.C.
        • Wu H.P.
        • Lo P.H.
        • Liang H.Y.
        • Chang K.C.
        Impact of prolonged door-to-balloon times on the diastolic function in acute ST-elevation myocardial infarction patients undergoing primary percutaneous coronary intervention.
        Acta Cardiol Sin. 2015; 31: 281-291
        • Koh J.Q.
        • Tong D.C.
        • Sriamareswaran R.
        • et al.
        In-hospital ‘CODE STEMI’ improves door-to-balloon time in patients undergoing primary percutaneous coronary intervention.
        Emerg Med Australas. 2018; 30: 222-227
        • Singer A.J.
        • Shembekar A.
        • Visram F.
        • et al.
        Emergency department activation of an interventional cardiology team reduces door-to-balloon times in ST-segment-elevation myocardial infarction.
        Ann Emerg Med. 2007; 50: 538-544
        • Parikh R.
        • Faillace R.
        • Hamdan A.
        • et al.
        An emergency physician activated protocol, ‘Code STEMI’ reduces door-to-balloon time and length of stay of patients presenting with ST-segment elevation myocardial infarction.
        Int J Clin Pract. 2009; 63: 398-406
        • Kwak M.J.
        • Kim K.
        • Rhee J.E.
        • et al.
        The effect of direct communication between emergency physicians and interventional cardiologists on door to balloon times in STEMI.
        J Korean Med Sci. 2008; 23: 706-710
        • Jacoby J.
        • Axelband J.
        • Patterson J.
        • Belletti D.
        • Heller M.
        Cardiac cath lab activation by the emergency physician without prior consultation decreases door-to-balloon time.
        J Invasive Cardiol. 2005; 17: 154-155
        • Allaqaband S.
        • Jan M.F.
        • Banday W.Y.
        • et al.
        Impact of 24-hr in-hospital interventional cardiology team on timeliness of reperfusion for ST-segment elevation myocardial infarction.
        Catheter Cardiovasc Interv. 2010; 75: 1015-1023
        • Savage M.L.
        • Poon K.K.
        • Johnston E.M.
        • et al.
        Pre-hospital ambulance notification and initiation of treatment of ST elevation myocardial infarction is associated with significant reduction in door-to-balloon time for primary PCI.
        Heart Lung Circ. 2014; 23: 435-443
        • Kobayashi A.
        • Misumida N.
        • Aoi S.
        • et al.
        STEMI notification by EMS predicts shorter door-to-balloon time and smaller infarct size.
        Am J Emerg Med. 2016; 34: 1610-1613
        • Wang Y.C.
        • Lo P.H.
        • Chang S.S.
        • et al.
        Reduced door-to-balloon times in acute ST-elevation myocardial infarction patients undergoing primary percutaneous coronary intervention.
        Int J Clin Pract. 2012; 66: 69-76
        • Schwarzfuchs D.
        • Shashar S.
        • Sagy I.
        • Novack V.
        • Zeldetz V.
        Does the physician in triage strategy improve door-to-balloon time for patients with STEMI?.
        Emerg Med J. 2020; 37: 540-545
        • Zhao Y.
        • Xiong J.
        • Hou Y.
        • et al.
        Early detection of ST-segment elevated myocardial infarction by artificial intelligence with 12-lead electrocardiogram.
        Int J Cardiol. 2020; 317: 223-230
        • Kohan L.C.
        • Nagarajan V.
        • Millard M.A.
        • Loguidice M.J.
        • Fauber N.M.
        • Keeley E.C.
        Impact of around-the-clock in-house cardiology fellow coverage on door-to-balloon time in an academic medical center.
        Vasc Health Risk Manag. 2017; 13: 139-142
        • Nguyen B.
        • Fennessy M.
        • Leya F.
        • et al.
        Comparison of primary percutaneous coronary intervention in patients with ST-elevation myocardial infarction during and prior to availability of an in-house STEMI system: early experience and intermediate outcomes of the HARRT program for achieving routine D2B times <60 minutes.
        Catheter Cardiovasc Interv. 2015; 86: 186-196