1
|
Islam MS, Kalmady SV, Hindle A, Sandhu R, Sun W, Sepehrvand N, Greiner R, Kaul P. Diagnostic and Prognostic Electrocardiogram-Based Models for Rapid Clinical Applications. Can J Cardiol 2024:S0828-282X(24)00523-3. [PMID: 38992812 DOI: 10.1016/j.cjca.2024.07.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2024] [Revised: 07/04/2024] [Accepted: 07/05/2024] [Indexed: 07/13/2024] Open
Abstract
Leveraging artificial intelligence (AI) for the analysis of electrocardiograms (ECGs) has the potential to transform diagnosis and estimate the prognosis of not only cardiac but, increasingly, noncardiac conditions. In this review, we summarize clinical studies and AI-enhanced ECG-based clinical applications in the early detection, diagnosis, and estimating prognosis of cardiovascular diseases in the past 5 years (2019-2023). With advancements in deep learning and the rapid increased use of ECG technologies, a large number of clinical studies have been published. However, most of these studies are single-centre, retrospective, proof-of-concept studies that lack external validation. Prospective studies that progress from development toward deployment in clinical settings account for < 15% of the studies. Successful implementations of ECG-based AI applications that have received approval from the Food and Drug Administration have been developed through commercial collaborations, with approximately half of them being for mobile or wearable devices. The field is in its early stages, and overcoming several obstacles is essential, such as prospective validation in multicentre large data sets, addressing technical issues, bias, privacy, data security, model generalizability, and global scalability. This review concludes with a discussion of these challenges and potential solutions. By providing a holistic view of the state of AI in ECG analysis, this review aims to set a foundation for future research directions, emphasizing the need for comprehensive, clinically integrated, and globally deployable AI solutions in cardiovascular disease management.
Collapse
Affiliation(s)
- Md Saiful Islam
- Canadian VIGOUR Centre, University of Alberta, Edmonton, Alberta, Canada; Department of Medicine, University of Alberta, Edmonton, Alberta, Canada
| | - Sunil Vasu Kalmady
- Canadian VIGOUR Centre, University of Alberta, Edmonton, Alberta, Canada; Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada
| | - Abram Hindle
- Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada
| | - Roopinder Sandhu
- Canadian VIGOUR Centre, University of Alberta, Edmonton, Alberta, Canada; Smidt Heart Institute, Cedars-Sinai Medical Center Hospital System, Los Angeles, California, USA
| | - Weijie Sun
- Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada
| | - Nariman Sepehrvand
- Canadian VIGOUR Centre, University of Alberta, Edmonton, Alberta, Canada; Department of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Russell Greiner
- Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada; Alberta Machine Intelligence Institute, Edmonton, Alberta, Canada
| | - Padma Kaul
- Canadian VIGOUR Centre, University of Alberta, Edmonton, Alberta, Canada; Department of Medicine, University of Alberta, Edmonton, Alberta, Canada.
| |
Collapse
|
2
|
Armoundas AA, Narayan SM, Arnett DK, Spector-Bagdady K, Bennett DA, Celi LA, Friedman PA, Gollob MH, Hall JL, Kwitek AE, Lett E, Menon BK, Sheehan KA, Al-Zaiti SS. Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association. Circulation 2024; 149:e1028-e1050. [PMID: 38415358 PMCID: PMC11042786 DOI: 10.1161/cir.0000000000001201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/29/2024]
Abstract
A major focus of academia, industry, and global governmental agencies is to develop and apply artificial intelligence and other advanced analytical tools to transform health care delivery. The American Heart Association supports the creation of tools and services that would further the science and practice of precision medicine by enabling more precise approaches to cardiovascular and stroke research, prevention, and care of individuals and populations. Nevertheless, several challenges exist, and few artificial intelligence tools have been shown to improve cardiovascular and stroke care sufficiently to be widely adopted. This scientific statement outlines the current state of the art on the use of artificial intelligence algorithms and data science in the diagnosis, classification, and treatment of cardiovascular disease. It also sets out to advance this mission, focusing on how digital tools and, in particular, artificial intelligence may provide clinical and mechanistic insights, address bias in clinical studies, and facilitate education and implementation science to improve cardiovascular and stroke outcomes. Last, a key objective of this scientific statement is to further the field by identifying best practices, gaps, and challenges for interested stakeholders.
Collapse
|
3
|
Goebel M, Westafer LM, Ayala SA, Ragone E, Chapman SJ, Mohammed MR, Cohen MR, Niemann JT, Eckstein M, Sanko S, Bosson N. A Novel Algorithm for Improving the Prehospital Diagnostic Accuracy of ST-Segment Elevation Myocardial Infarction. Prehosp Disaster Med 2024; 39:37-44. [PMID: 38047380 PMCID: PMC10922545 DOI: 10.1017/s1049023x23006635] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/05/2023]
Abstract
INTRODUCTION Early detection of ST-segment elevation myocardial infarction (STEMI) on the prehospital electrocardiogram (ECG) improves patient outcomes. Current software algorithms optimize sensitivity but have a high false-positive rate. The authors propose an algorithm to improve the specificity of STEMI diagnosis in the prehospital setting. METHODS A dataset of prehospital ECGs with verified outcomes was used to validate an algorithm to identify true and false-positive software interpretations of STEMI. Four criteria implicated in prior research to differentiate STEMI true positives were applied: heart rate <130, QRS <100, verification of ST-segment elevation, and absence of artifact. The test characteristics were calculated and regression analysis was used to examine the association between the number of criteria included and test characteristics. RESULTS There were 44,611 cases available. Of these, 1,193 were identified as STEMI by the software interpretation. Applying all four criteria had the highest positive likelihood ratio of 353 (95% CI, 201-595) and specificity of 99.96% (95% CI, 99.93-99.98), but the lowest sensitivity (14%; 95% CI, 11-17) and worst negative likelihood ratio (0.86; 95% CI, 0.84-0.89). There was a strong correlation between increased positive likelihood ratio (r2 = 0.90) and specificity (r2 = 0.85) with increasing number of criteria. CONCLUSIONS Prehospital ECGs with a high probability of true STEMI can be accurately identified using these four criteria: heart rate <130, QRS <100, verification of ST-segment elevation, and absence of artifact. Applying these criteria to prehospital ECGs with software interpretations of STEMI could decrease false-positive field activations, while also reducing the need to rely on transmission for physician over-read. This can have significant clinical and quality implications for Emergency Medical Services (EMS) systems.
Collapse
Affiliation(s)
- Mat Goebel
- University of Massachusetts Chan Medical School – Baystate, Department of Emergency Medicine, Springfield, Massachusetts USA
| | - Lauren M. Westafer
- University of Massachusetts Chan Medical School – Baystate, Department of Emergency Medicine, Springfield, Massachusetts USA
| | - Stephanie A. Ayala
- University of Massachusetts Chan Medical School – Baystate, Department of Emergency Medicine, Springfield, Massachusetts USA
| | - El Ragone
- Fairview Hospital, Emergency Department, Barrington, Massachusetts USA
| | - Scott J. Chapman
- Belchertown Fire Rescue, Belchertown, Massachusetts USA
- Greenfield Community College, Greenfield, Massachusetts USA
| | | | - Marc R. Cohen
- Los Angeles City Fire Department, Emergency Medical Services Bureau, Los Angeles, California USA
| | - James T. Niemann
- University of California Los Angeles, Los Angeles, California USA
- Harbor-UCLA Medical Center, Department of Emergency Medicine, Torrance, California USA
- The Lundquist Institute at Harbor-UCLA Medical Center, Torrance, California USA
| | - Marc Eckstein
- Los Angeles City Fire Department, Emergency Medical Services Bureau, Los Angeles, California USA
- Keck School of Medicine of the University of Southern California, Department of Emergency Medicine, Los Angeles, California USA
| | - Stephen Sanko
- Keck School of Medicine of the University of Southern California, Department of Emergency Medicine, Los Angeles, California USA
- Los Angeles County EMS Agency, Los Angeles, California USA
| | - Nichole Bosson
- University of California Los Angeles, Los Angeles, California USA
- Harbor-UCLA Medical Center, Department of Emergency Medicine, Torrance, California USA
- Los Angeles County EMS Agency, Los Angeles, California USA
| |
Collapse
|
4
|
Nyström A, Olsson de Capretz P, Björkelund A, Lundager Forberg J, Ohlsson M, Björk J, Ekelund U. Prior electrocardiograms not useful for machine learning predictions of major adverse cardiac events in emergency department chest pain patients. J Electrocardiol 2024; 82:42-51. [PMID: 38006763 DOI: 10.1016/j.jelectrocard.2023.11.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2023] [Revised: 09/07/2023] [Accepted: 11/02/2023] [Indexed: 11/27/2023]
Abstract
At the emergency department (ED), it is important to quickly and accurately determine which patients are likely to have a major adverse cardiac event (MACE). Machine learning (ML) models can be used to aid physicians in detecting MACE, and improving the performance of such models is an active area of research. In this study, we sought to determine if ML models can be improved by including a prior electrocardiogram (ECG) from each patient. To that end, we trained several models to predict MACE within 30 days, both with and without prior ECGs, using data collected from 19,499 consecutive patients with chest pain, from five EDs in southern Sweden, between the years 2017 and 2018. Our results indicate no improvement in AUC from prior ECGs. This was consistent across models, both with and without additional clinical input variables, for different patient subgroups, and for different subsets of the outcome. While contradicting current best practices for manual ECG analysis, the results are positive in the sense that ML models with fewer inputs are more easily and widely applicable in practice.
Collapse
Affiliation(s)
- Axel Nyström
- Lund University, Department of Laboratory Medicine, Lund, Sweden.
| | - Pontus Olsson de Capretz
- Skåne University Hospital, Department of Internal and Emergency Medicine, Lund, Sweden; Lund University, Department of Clinical Sciences, Lund, Sweden
| | - Anders Björkelund
- Lund University, Center for Environmental and Climate Science, Lund, Sweden
| | - Jakob Lundager Forberg
- Lund University, Department of Clinical Sciences, Lund, Sweden; Helsingborg Hospital, Department of Emergency Medicine, Helsingborg, Sweden
| | - Mattias Ohlsson
- Lund University, Center for Environmental and Climate Science, Lund, Sweden; Halmstad University, Center for Applied Intelligent Systems Research (CAISR), Halmstad, Sweden
| | - Jonas Björk
- Lund University, Department of Laboratory Medicine, Lund, Sweden; Clinical Studies Sweden, Forum South, Skåne University Hospital, Lund, Sweden
| | - Ulf Ekelund
- Skåne University Hospital, Department of Internal and Emergency Medicine, Lund, Sweden; Lund University, Department of Clinical Sciences, Lund, Sweden
| |
Collapse
|
5
|
Shusterman V, London B. Personalized ECG monitoring and adaptive machine learning. J Electrocardiol 2024; 82:131-135. [PMID: 38128158 PMCID: PMC10843583 DOI: 10.1016/j.jelectrocard.2023.12.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2023] [Revised: 10/17/2023] [Accepted: 12/05/2023] [Indexed: 12/23/2023]
Abstract
This non-technical review introduces key concepts in personalized ECG monitoring (pECG), which aims to optimize the detection of clinical events and their warning signs as well as the selection of alarm thresholds. We review several pECG methods, including anomaly detection and adaptive machine learning (ML), in which learning is performed sequentially as new data are collected. We describe a distributed-network multiscale pECG system to show how the computational load and time associated with adaptive ML could be optimized. In this architecture, the limited analysis of ECG waveforms is performed locally (e.g., on a smart phone) to determine a small number of clinically important ECG elements, and an adaptive ML engine is located on a remote server (Internet cloud) to determine an individual's "fingerprint" basis patterns and to detect anomalies in those patterns.
Collapse
Affiliation(s)
- Vladimir Shusterman
- The University of Iowa, United States of America; PinMed, Inc., United States of America.
| | - Barry London
- The University of Iowa, United States of America
| |
Collapse
|
6
|
Swenne CA, Ter Haar CC. Context-independent identification of myocardial ischemia in the prehospital ECG of chest pain patients. J Electrocardiol 2024; 82:34-41. [PMID: 38006762 DOI: 10.1016/j.jelectrocard.2023.10.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2023] [Revised: 10/14/2023] [Accepted: 10/23/2023] [Indexed: 11/27/2023]
Abstract
Non-traumatic chest pain is a frequent reason for an urgent ambulance visit of a patient by the emergency medical services (EMS). Chest pain (or chest pain-equivalent symptoms) can be innocent, but it can also signal an acute form of severe pathology that may require prompt intervention. One of these pathologies is cardiac ischemia, resulting from a disbalance between blood supply and demand. One cause of a diminished blood supply to the heart is acute coronary syndrome (ACS, i.e., cardiac ischemia caused by a reduced blood supply to myocardial tissue due to plaque instability and thrombus formation in a coronary artery). ACS is dangerous due to the unpredictable process that drives the supply problem and the high chance of fast hemodynamic deterioration (i.e., cardiogenic shock, ventricular fibrillation). This is why an ECG is made at first medical contact in most chest pain patients to include or exclude ischemia as the cause of their complaints. For speedy and adequate triaging and treatment, immediate assessment of this prehospital ECG is necessary, still during the ambulance ride. Human diagnostic efforts supported by automated interpretation algorithms seek to answer questions regarding the urgency level, the decision if and towards which healthcare facility the patient should be transported, and the indicated acute treatment and further diagnostics after arrival in the healthcare facility. In the case of an ACS, a catheter intervention room may be activated during the ambulance ride to facilitate the earliest possible in-hospital treatment. Prehospital ECG assessment and the subsequent triaging decisions are complex because chest pain is not uniquely associated with ACS. The differential diagnosis includes other cardiac, pulmonary, vascular, gastrointestinal, orthopedic, and psychological conditions. Some of these conditions may also involve ECG abnormalities. In practice, only a limited fraction (order of magnitude 10%) of the patients who are urgently transported to the hospital because of chest pain are ACS patients. Given the relatively low prevalence of ACS in this patient mix, the specificity of the diagnostic ECG algorithms should be relatively high to prevent overtreatment and overflow of intervention facilities. On the other hand, only a sufficiently high sensitivity warrants adequate therapy when needed. Here, we review how the prehospital ECG can contribute to identifying the presence of myocardial ischemia in chest pain patients. We discuss the various mechanisms of myocardial ischemia and infarction, the typical patient mix of chest pain patients, the shortcomings of the ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI) ECG criteria to detect a completely occluded culprit artery, the OMI ECG criteria (including the STEMI-equivalent ECG patterns) in detecting completely occluded culprit arteries, and the promise of neural networks in recognizing ECG patterns that represent complete occlusions. We also discuss the relevance of detecting any ACS/ischemia, not necessarily caused by a total occlusion, in the prehospital ECG. In addition, we discuss how serial prehospital ECGs can contribute to ischemia diagnosis. Finally, we discuss the diagnostic contribution of a serial comparison of the prehospital ECG with a previously made nonischemic ECG of the patient.
Collapse
Affiliation(s)
- Cees A Swenne
- Cardiology Department, Leiden University Medical Center, Leiden, the Netherlands.
| | - C Cato Ter Haar
- Cardiology Department, Amsterdam University Medical Center, Amsterdam, the Netherlands
| |
Collapse
|
7
|
Ter Haar CC, Swenne CA. Post hoc labeling an acute ECG as ischemic or non-ischemic based on clinical data: A necessary challenge. J Electrocardiol 2023; 81:75-79. [PMID: 37639936 DOI: 10.1016/j.jelectrocard.2023.08.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Revised: 07/25/2023] [Accepted: 08/10/2023] [Indexed: 08/31/2023]
Abstract
The ECG is crucial in the prehospital (and early inhospital) phase of patients with symptoms suggestive of myocardial ischemia. Therefore, new algorithms for ECG-based myocardial ischemia detection are continuously being researched. Development and validation of these algorithms require a database of acute ECGs (from the prehospital or emergency department setting) including a representative mix of cases (ischemia present) and controls (no ischemia present). Therefore, for every patient in this mix, the "truth" regarding the actual presence or absence of myocardial ischemia during the recording of the acute ECG has to be determined to compare the newly developed algorithm against. This post hoc adjudication process of determining whether an acute (either prehospitally acquired or acquired in the emergency department) ECG was made under ischemic conditions should use all available clinical data (the clinical diagnosis, cardiac imaging data, and laboratory values) of the subsequent patient's admission. Even with all data at hand, post hoc labeling a patient and their acute ECG as a myocardial ischemia case or control cannot be forced into a binary division between definite cases and definite controls. More specifically, to be used for the development of a new algorithm, the patients' ECG has to be scored for the presence or absence of myocardial ischemia at the exact moment of its recording, which renders the classification even more difficult. For instance, even though it may be plausible that myocardial ischemia was present at a given moment during the patient's admission, this is not necessarily proof that the prehospital (or early inhospital) ECG was also made in ischemic conditions: ischemia can be a fluctuating process (as is, e.g., the case in unstable angina pectoris). Therefore, post hoc classification of an acute ECG in terms of the absence or presence of ischemia requires a multipoint scale ranging between definite ischemic to definite non-ischemic, for instance using a 5-point scale (presumed non-ischemic, probably non-ischemic, uncertain, probably ischemic, presumed ischemic). To summarize, the post hoc adjudication process of ECGs of ambulance (and emergency department) patients cannot result in a binary division into definite cases and controls (i.e., patients with or without myocardial ischemia during the recording of the acute ECG), as myocardial ischemia is often dynamic rather than constant. ECGs could be labeled on a multi-point scale, in which the label represents the probability of the actual presence (or absence) of myocardial ischemia at the exact moment of the recording of that ECG. Further development of algorithms for myocardial ischemia detection should consider this concept.
Collapse
Affiliation(s)
- C Cato Ter Haar
- Cardiology Department, Amsterdam University Medical Center, Amsterdam, The Netherlands; Cardiology Department, Leiden University Medical Center, Leiden, The Netherlands.
| | - Cees A Swenne
- Cardiology Department, Leiden University Medical Center, Leiden, The Netherlands
| |
Collapse
|
8
|
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. Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction. Nat Med 2023; 29:1804-1813. [PMID: 37386246 PMCID: PMC10353937 DOI: 10.1038/s41591-023-02396-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Accepted: 05/11/2023] [Indexed: 07/01/2023]
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.
Collapse
Affiliation(s)
- Salah S Al-Zaiti
- Department of Acute & Tertiary Care Nursing, University of Pittsburgh, Pittsburgh, PA, USA.
- Department of Emergency Medicine, University of Pittsburgh, Pittsburgh, PA, USA.
- Department of Electrical & Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA.
- Division of Cardiology, University of Pittsburgh, Pittsburgh, PA, USA.
| | - Christian Martin-Gill
- Department of Emergency Medicine, University of Pittsburgh, Pittsburgh, PA, USA
- University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| | | | - Zeineb Bouzid
- Department of Electrical & Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA
| | - Ziad Faramand
- Department of Emergency Medicine, Northeast Georgia Health System, Gainesville, GA, USA
| | - Mohammad O Alrawashdeh
- School of Nursing, Jordan University of Science and Technology, Irbid, Jordan
- Department of Population Medicine, Harvard Medical School and Harvard Pilgrim Health Care Institute, Boston, MA, USA
| | - Richard E Gregg
- Advanced Algorithm Development Center, Philips Healthcare, Cambridge, MA, USA
| | - Stephanie Helman
- Department of Acute & Tertiary Care Nursing, University of Pittsburgh, Pittsburgh, PA, USA
| | - Nathan T Riek
- Department of Electrical & Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA
| | | | - Gilles Clermont
- Department of Critical Care Medicine, University of Pittsburgh, Pittsburgh, PA, USA
| | - Murat Akcakaya
- Department of Electrical & Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA
| | - Susan M Sereika
- Department of Acute & Tertiary Care Nursing, University of Pittsburgh, Pittsburgh, PA, USA
| | - Peter Van Dam
- Division of Cardiology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Stephen W Smith
- Department of Emergency Medicine, Hennepin Healthcare, Minneapolis, MN, USA
- Department of Emergency Medicine, University of Minnesota, Minneapolis, MN, USA
| | - Yochai Birnbaum
- Division of Cardiology, Baylor College of Medicine, Houston, TX, USA
| | - Samir Saba
- Division of Cardiology, University of Pittsburgh, Pittsburgh, PA, USA
- University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| | - Ervin Sejdic
- Department of Electrical & Computer Engineering, University of Toronto, Toronto, ON, Canada
- Artificial Intelligence for Health Outcomes at Research & Innovation, North York General Hospital, Toronto, ON, Canada
| | - Clifton W Callaway
- Department of Emergency Medicine, University of Pittsburgh, Pittsburgh, PA, USA
- University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| |
Collapse
|
9
|
Al-Zaiti S, Martin-Gill C, Zégre-Hemsey J, Bouzid Z, Faramand Z, Alrawashdeh M, Gregg R, Helman S, Riek N, Kraevsky-Phillips K, Clermont G, Akcakaya M, Sereika S, Van Dam P, Smith S, Birnbaum Y, Saba S, Sejdic E, Callaway C. Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact. RESEARCH SQUARE 2023:rs.3.rs-2510930. [PMID: 36778371 PMCID: PMC9915770 DOI: 10.21203/rs.3.rs-2510930/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/31/2023]
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.
Collapse
|