Acute Myocardial Infarction Prediction Using Artificial Intelligence Applied to Electrocardiogram Images
NCT ID: NCT07163767
Last Updated: 2025-12-18
Study Results
Results pending
The study team has not published outcome measurements, participant flow, or safety data for this trial yet. Check back later for updates.
Basic Information
Get a concise snapshot of the trial, including recruitment status, study phase, enrollment targets, and key timeline milestones.
Recruitment Status
ACTIVE_NOT_RECRUITING
Total Enrollment
150000 participants
Study Classification
OBSERVATIONAL
Study Start Date
2025-08-01
Study Completion Date
2028-12-31
Brief Summary
Review the sponsor-provided synopsis that highlights what the study is about and why it is being conducted.
The goal of this observational study is to develop and validate an artificial intelligence(AI)-based prediction model for new-onset acute myocardial infarction(AMI) using electrocardiogram(ECG) data. The main question it aims to answer is whether the AI-based ECG accurately forecast new-onset AMI by previous ECG data with 'normal' diagnosis?
Detailed Description
Dive into the extended narrative that explains the scientific background, objectives, and procedures in greater depth.
Myocardial infarction (MI), as one of the most critical acute clinical events in cardiovascular diseases, has high morbidity and mortality, imposing a significant burden on public health and medical resources. Traditional risk assessment for MI relies on clinical indicators (e.g., lipids, blood pressure, diabetes status, family history) and cardiac imaging, but these methods often suffer from invasive procedure, high cost, or limited predictive accuracy. Electrocardiography (ECG), a non-invasive, widely available, and low-cost modality, captures rich electrophysiological signals reflecting cardiac function. However, conventional analysis methods struggle to detect subtle, progressive patterns in ECG signals, leading to sub-optimal sensitivity and specificity in predicting new-onset MI.
Recent advancements in deep learning and big data have enabled significant progress in ECG-based prediction models. For example, deep convolutional neural networks (CNNs) for automatic feature extraction and pattern recognition from 12-lead ECGs have demonstrated promise in predicting cardiovascular events such as atrial fibrillation, left ventricular hypertrophy, and heart failure re-hospitalization. AI algorithms have also been shown to extract subtle information from ECGs that traditional methods miss, such as dynamic changes in ventricular electrical activity and early signs of micro-myocardial injury, enabling early risk warning of cardiac events. While numerous ECG-based AI models exist for predicting arrhythmia , heart failure, and other cardiovascular outcomes, research on predicting new-onset MI-particularly using non-invasive ECG data and deep learning to extract latent predictive markers-remains in its infancy. Traditional risk models, though successful in MI prevention, lack precision in individual-level prediction and early intervention.
This study aims to leverage large-scale electronic health records and ECG datasets with advanced deep learning to explore the quantitative relationship between fine-grained ECG signal features and MI incidence, thereby developing a clinical tool for early risk assessment. Inspirations also derive from recent attempts to build multi-modal prediction models combining ECG with physiological, genetic, and biochemical markers. Additionally, studies have highlighted ECG's unique advantages in evaluating myocardial compensatory mechanisms and early injury. Despite existing ECG-AI applications, direct prediction of new-onset MI remains a critical unmet need and a key direction for precision medicine using AI.
This is a multi-center observational cohort study. Large-scale in-hospital ECG data will be integrated to develop a deep learning model for MI prediction using an end-to-end deep neural network approach, with the goal of deriving a high-performance model for new-onset MI prediction. The ECG data from 5 multicenter Cardiorenal ImprovemeNt II (CIN-II) sites between 2010-2023 will be assessed.
Recent advancements in deep learning and big data have enabled significant progress in ECG-based prediction models. For example, deep convolutional neural networks (CNNs) for automatic feature extraction and pattern recognition from 12-lead ECGs have demonstrated promise in predicting cardiovascular events such as atrial fibrillation, left ventricular hypertrophy, and heart failure re-hospitalization. AI algorithms have also been shown to extract subtle information from ECGs that traditional methods miss, such as dynamic changes in ventricular electrical activity and early signs of micro-myocardial injury, enabling early risk warning of cardiac events. While numerous ECG-based AI models exist for predicting arrhythmia , heart failure, and other cardiovascular outcomes, research on predicting new-onset MI-particularly using non-invasive ECG data and deep learning to extract latent predictive markers-remains in its infancy. Traditional risk models, though successful in MI prevention, lack precision in individual-level prediction and early intervention.
This study aims to leverage large-scale electronic health records and ECG datasets with advanced deep learning to explore the quantitative relationship between fine-grained ECG signal features and MI incidence, thereby developing a clinical tool for early risk assessment. Inspirations also derive from recent attempts to build multi-modal prediction models combining ECG with physiological, genetic, and biochemical markers. Additionally, studies have highlighted ECG's unique advantages in evaluating myocardial compensatory mechanisms and early injury. Despite existing ECG-AI applications, direct prediction of new-onset MI remains a critical unmet need and a key direction for precision medicine using AI.
This is a multi-center observational cohort study. Large-scale in-hospital ECG data will be integrated to develop a deep learning model for MI prediction using an end-to-end deep neural network approach, with the goal of deriving a high-performance model for new-onset MI prediction. The ECG data from 5 multicenter Cardiorenal ImprovemeNt II (CIN-II) sites between 2010-2023 will be assessed.
Conditions
See the medical conditions and disease areas that this research is targeting or investigating.
Acute Myocardial Infarction (AMI)
Electrocardiography
Artifical Intelligence
Study Design
Understand how the trial is structured, including allocation methods, masking strategies, primary purpose, and other design elements.
Observational Model Type
COHORT
Study Time Perspective
RETROSPECTIVE
Study Groups
Review each arm or cohort in the study, along with the interventions and objectives associated with them.
Cardiorenal ImprovemeNt II (CIN-II)
This is a multi-center, retrospective observation study collecting data on 184855 coronary angiography patients from January 2000 to Decemeber 2020.
Deep learning approach of ECG for AMI detection
Intervention Type
OTHER
AMIdECG was trained to perform AMI detection in a supervised manner as a classification task. And the classification labels of AMI subtypes (" STEMI "or" NSTEMI ") or non-AMI states used during the training phase are real-world diagnostic results
Interventions
Learn about the drugs, procedures, or behavioral strategies being tested and how they are applied within this trial.
Deep learning approach of ECG for AMI detection
AMIdECG was trained to perform AMI detection in a supervised manner as a classification task. And the classification labels of AMI subtypes (" STEMI "or" NSTEMI ") or non-AMI states used during the training phase are real-world diagnostic results
Intervention Type
OTHER
Eligibility Criteria
Check the participation requirements, including inclusion and exclusion rules, age limits, and whether healthy volunteers are accepted.
Inclusion Criteria
* Hospitalized in cardiology department with myocardial injury marker testing (troponin T/I).
* In-hospital patients with ECG records.
* In-hospital patients with ECG records.
Exclusion Criteria
* First ECG obtained in emergency department.
* ACS diagnosis within 1 month of first ECG.
* ACS diagnosis within 1 month of first ECG.
Minimum Eligible Age
18 Years
Eligible Sex
ALL
Accepts Healthy Volunteers
Yes
Sponsors
Meet the organizations funding or collaborating on the study and learn about their roles.
Guangdong Provincial People's Hospital
OTHER
Sponsor Role
lead
Responsible Party
Identify the individual or organization who holds primary responsibility for the study information submitted to regulators.
Liu yong
Professor
Responsibility Role
PRINCIPAL_INVESTIGATOR
Locations
Explore where the study is taking place and check the recruitment status at each participating site.
Guangdong Provincial People's Hospital
Guangzhou, Guangdong, China
Site Status
Countries
Review the countries where the study has at least one active or historical site.
China
References
Explore related publications, articles, or registry entries linked to this study.
Grech ED, Ramsdale DR. Acute coronary syndrome: unstable angina and non-ST segment elevation myocardial infarction. BMJ. 2003 Jun 7;326(7401):1259-61. doi: 10.1136/bmj.326.7401.1259. No abstract available.
Reference Type
BACKGROUND
Sadasivuni S, Saha M, Bhatia N, Banerjee I, Sanyal A. Fusion of fully integrated analog machine learning classifier with electronic medical records for real-time prediction of sepsis onset. Sci Rep. 2022 Apr 5;12(1):5711. doi: 10.1038/s41598-022-09712-w.
Reference Type
BACKGROUND
Jawade P, Khillare KM, Mangudkar S, Palange A, Dhadwad J, Deshmukh M. A Comparative Study of Ischemia-Modified Albumin: A Promising Biomarker for Early Detection of Acute Coronary Syndrome (ACS). Cureus. 2023 Aug 30;15(8):e44357. doi: 10.7759/cureus.44357. eCollection 2023 Aug.
Reference Type
BACKGROUND
Swenne CA, Ter Haar CC. Context-independent identification of myocardial ischemia in the prehospital ECG of chest pain patients. J Electrocardiol. 2024 Jan-Feb;82:34-41. doi: 10.1016/j.jelectrocard.2023.10.009. Epub 2023 Nov 7.
Reference Type
BACKGROUND
Akbilgic O, Butler L, Karabayir I, Chang PP, Kitzman DW, Alonso A, Chen LY, Soliman EZ. ECG-AI: electrocardiographic artificial intelligence model for prediction of heart failure. Eur Heart J Digit Health. 2021 Oct 9;2(4):626-634. doi: 10.1093/ehjdh/ztab080. eCollection 2021 Dec.
Reference Type
BACKGROUND
Aufiero S, Bleijendaal H, Robyns T, Vandenberk B, Krijger C, Bezzina C, Zwinderman AH, Wilde AAM, Pinto YM. A deep learning approach identifies new ECG features in congenital long QT syndrome. BMC Med. 2022 May 3;20(1):162. doi: 10.1186/s12916-022-02350-z.
Reference Type
BACKGROUND
Serhal H, Abdallah N, Marion JM, Chauvet P, Oueidat M, Humeau-Heurtier A. Overview on prediction, detection, and classification of atrial fibrillation using wavelets and AI on ECG. Comput Biol Med. 2022 Mar;142:105168. doi: 10.1016/j.compbiomed.2021.105168. Epub 2022 Jan 1.
Reference Type
BACKGROUND
Elul Y, Rosenberg AA, Schuster A, Bronstein AM, Yaniv Y. Meeting the unmet needs of clinicians from AI systems showcased for cardiology with deep-learning-based ECG analysis. Proc Natl Acad Sci U S A. 2021 Jun 15;118(24):e2020620118. doi: 10.1073/pnas.2020620118.
Reference Type
BACKGROUND
Liu YL, Lin CS, Cheng CC, Lin C. A Deep Learning Algorithm for Detecting Acute Pericarditis by Electrocardiogram. J Pers Med. 2022 Jul 15;12(7):1150. doi: 10.3390/jpm12071150.
Reference Type
BACKGROUND
Pignolo RJ. AI-ECG and the Prediction of Accelerated Aging. Mayo Clin Proc. 2023 Apr;98(4):502-503. doi: 10.1016/j.mayocp.2023.02.016. No abstract available.
Reference Type
BACKGROUND
Wang X, Khurshid S, Choi SH, Friedman S, Weng LC, Reeder C, Pirruccello JP, Singh P, Lau ES, Venn R, Diamant N, Di Achille P, Philippakis A, Anderson CD, Ho JE, Ellinor PT, Batra P, Lubitz SA. Genetic Susceptibility to Atrial Fibrillation Identified via Deep Learning of 12-Lead Electrocardiograms. Circ Genom Precis Med. 2023 Aug;16(4):340-349. doi: 10.1161/CIRCGEN.122.003808. Epub 2023 Jun 6.
Reference Type
BACKGROUND
Attia ZI, Friedman PA. Explainable AI for ECG-based prediction of cardiac resynchronization therapy outcomes: learning from machine learning? Eur Heart J. 2023 Feb 21;44(8):693-695. doi: 10.1093/eurheartj/ehac733. No abstract available.
Reference Type
BACKGROUND
Martinez-Selles M, Marina-Breysse M. Current and Future Use of Artificial Intelligence in Electrocardiography. J Cardiovasc Dev Dis. 2023 Apr 17;10(4):175. doi: 10.3390/jcdd10040175.
Reference Type
BACKGROUND
Butler L, Ivanov A, Celik T, Karabayir I, Chinthala L, Tootooni MS, Jaeger BC, Patterson LT, Doerr AJ, McManus DD, Davis RL, Herrington D, Akbilgic O. Time-Dependent ECG-AI Prediction of Fatal Coronary Heart Disease: A Retrospective Study. J Cardiovasc Dev Dis. 2024 Dec 8;11(12):395. doi: 10.3390/jcdd11120395.
Reference Type
BACKGROUND
Sekhri N, Feder GS, Junghans C, Hemingway H, Timmis AD. How effective are rapid access chest pain clinics? Prognosis of incident angina and non-cardiac chest pain in 8762 consecutive patients. Heart. 2007 Apr;93(4):458-63. doi: 10.1136/hrt.2006.090894. Epub 2006 Jun 21.
Reference Type
BACKGROUND
Stubbs P, Collinson P, Moseley D, Greenwood T, Noble M. Prospective study of the role of cardiac troponin T in patients admitted with unstable angina. BMJ. 1996 Aug 3;313(7052):262-4. doi: 10.1136/bmj.313.7052.262.
Reference Type
BACKGROUND
Farkouh ME, Smars PA, Reeder GS, Zinsmeister AR, Evans RW, Meloy TD, Kopecky SL, Allen M, Allison TG, Gibbons RJ, Gabriel SE. A clinical trial of a chest-pain observation unit for patients with unstable angina. Chest Pain Evaluation in the Emergency Room (CHEER) Investigators. N Engl J Med. 1998 Dec 24;339(26):1882-8. doi: 10.1056/NEJM199812243392603.
Reference Type
BACKGROUND
Fox KA, Goodman SG, Klein W, Brieger D, Steg PG, Dabbous O, Avezum A. Management of acute coronary syndromes. Variations in practice and outcome; findings from the Global Registry of Acute Coronary Events (GRACE). Eur Heart J. 2002 Aug;23(15):1177-89. doi: 10.1053/euhj.2001.3081.
Reference Type
BACKGROUND
Pollack CV Jr, Sites FD, Shofer FS, Sease KL, Hollander JE. Application of the TIMI risk score for unstable angina and non-ST elevation acute coronary syndrome to an unselected emergency department chest pain population. Acad Emerg Med. 2006 Jan;13(1):13-8. doi: 10.1197/j.aem.2005.06.031. Epub 2005 Dec 19.
Reference Type
BACKGROUND
Sinha MK, Roy D, Gaze DC, Collinson PO, Kaski JC. Role of "Ischemia modified albumin", a new biochemical marker of myocardial ischaemia, in the early diagnosis of acute coronary syndromes. Emerg Med J. 2004 Jan;21(1):29-34. doi: 10.1136/emj.2003.006007.
Reference Type
BACKGROUND
de Beer FC, Hind CR, Fox KM, Allan RM, Maseri A, Pepys MB. Measurement of serum C-reactive protein concentration in myocardial ischaemia and infarction. Br Heart J. 1982 Mar;47(3):239-43. doi: 10.1136/hrt.47.3.239.
Reference Type
BACKGROUND
Katus HA, Remppis A, Neumann FJ, Scheffold T, Diederich KW, Vinar G, Noe A, Matern G, Kuebler W. Diagnostic efficiency of troponin T measurements in acute myocardial infarction. Circulation. 1991 Mar;83(3):902-12. doi: 10.1161/01.cir.83.3.902.
Reference Type
BACKGROUND
Yagi R, Goto S, Himeno Y, Katsumata Y, Hashimoto M, MacRae CA, Deo RC. Artificial intelligence-enabled prediction of chemotherapy-induced cardiotoxicity from baseline electrocardiograms. Nat Commun. 2024 Mar 21;15(1):2536. doi: 10.1038/s41467-024-45733-x.
Reference Type
BACKGROUND
Shen CP, Muse ED. Towards an artificial intelligence-augmented, ECG-enabled physical exam. Lancet Digit Health. 2022 Feb;4(2):e78-e79. doi: 10.1016/S2589-7500(21)00281-8. Epub 2022 Jan 5. No abstract available.
Reference Type
BACKGROUND
Lincoff AM, Brown-Frandsen K, Colhoun HM, Deanfield J, Emerson SS, Esbjerg S, Hardt-Lindberg S, Hovingh GK, Kahn SE, Kushner RF, Lingvay I, Oral TK, Michelsen MM, Plutzky J, Tornoe CW, Ryan DH; SELECT Trial Investigators. Semaglutide and Cardiovascular Outcomes in Obesity without Diabetes. N Engl J Med. 2023 Dec 14;389(24):2221-2232. doi: 10.1056/NEJMoa2307563. Epub 2023 Nov 11.
Reference Type
BACKGROUND
Dhingra LS, Aminorroaya A, Sangha V, Pedroso AF, Asselbergs FW, Brant LCC, Barreto SM, Ribeiro ALP, Krumholz HM, Oikonomou EK, Khera R. Heart failure risk stratification using artificial intelligence applied to electrocardiogram images: a multinational study. Eur Heart J. 2025 Mar 13;46(11):1044-1053. doi: 10.1093/eurheartj/ehae914.
Reference Type
BACKGROUND
Biscaglia S, Guiducci V, Escaned J, Moreno R, Lanzilotti V, Santarelli A, Cerrato E, Sacchetta G, Jurado-Roman A, Menozzi A, Amat Santos I, Diez Gil JL, Ruozzi M, Barbierato M, Fileti L, Picchi A, Lodolini V, Biondi-Zoccai G, Maietti E, Pavasini R, Cimaglia P, Tumscitz C, Erriquez A, Penzo C, Colaiori I, Pignatelli G, Casella G, Iannopollo G, Menozzi M, Varbella F, Caretta G, Dudek D, Barbato E, Tebaldi M, Campo G; FIRE Trial Investigators. Complete or Culprit-Only PCI in Older Patients with Myocardial Infarction. N Engl J Med. 2023 Sep 7;389(10):889-898. doi: 10.1056/NEJMoa2300468. Epub 2023 Aug 26.
Reference Type
BACKGROUND
Kromhout D, Giltay EJ, Geleijnse JM; Alpha Omega Trial Group. n-3 fatty acids and cardiovascular events after myocardial infarction. N Engl J Med. 2010 Nov 18;363(21):2015-26. doi: 10.1056/NEJMoa1003603. Epub 2010 Aug 28.
Reference Type
BACKGROUND
Dupulthys S, Dujardin K, Anne W, Pollet P, Vanhaverbeke M, McAuliffe D, Lammertyn PJ, Berteloot L, Mertens N, De Jaeger P. Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm. Europace. 2024 Feb 1;26(2):euad354. doi: 10.1093/europace/euad354.
Reference Type
BACKGROUND
Nechita LC, Nechita A, Voipan AE, Voipan D, Debita M, Fulga A, Fulga I, Musat CL. AI-Enhanced ECG Applications in Cardiology: Comprehensive Insights from the Current Literature with a Focus on COVID-19 and Multiple Cardiovascular Conditions. Diagnostics (Basel). 2024 Aug 23;14(17):1839. doi: 10.3390/diagnostics14171839.
Reference Type
BACKGROUND
Chen HY, Lin CS, Fang WH, Lee CC, Ho CL, Wang CH, Lin C. Artificial Intelligence-Enabled Electrocardiogram Predicted Left Ventricle Diameter as an Independent Risk Factor of Long-Term Cardiovascular Outcome in Patients With Normal Ejection Fraction. Front Med (Lausanne). 2022 Apr 11;9:870523. doi: 10.3389/fmed.2022.870523. eCollection 2022.
Reference Type
BACKGROUND
Lee HS, Kang S, Jo YY, Son JM, Lee MS, Kwon JM, Kim KH. AI-Enabled Smartwatch ECG: A Feasibility Study for Early Prediction and Prevention of Heart Failure Rehospitalization. JACC Basic Transl Sci. 2025 Mar;10(3):250-252. doi: 10.1016/j.jacbts.2025.01.005. Epub 2025 Feb 11. No abstract available.
Reference Type
BACKGROUND
Khurshid S, Friedman S, Reeder C, Di Achille P, Diamant N, Singh P, Harrington LX, Wang X, Al-Alusi MA, Sarma G, Foulkes AS, Ellinor PT, Anderson CD, Ho JE, Philippakis AA, Batra P, Lubitz SA. ECG-Based Deep Learning and Clinical Risk Factors to Predict Atrial Fibrillation. Circulation. 2022 Jan 11;145(2):122-133. doi: 10.1161/CIRCULATIONAHA.121.057480. Epub 2021 Nov 8.
Reference Type
BACKGROUND
Other Identifiers
Review additional registry numbers or institutional identifiers associated with this trial.
KY2025-514
Identifier Type: -
Identifier Source: org_study_id