Desarrollo de un clasificador de imágenes con una herramienta Non-Code para procesamiento de electrocardiograma con IAM
Article Sidebar
Main Article Content
Abstract
Acute ST-segment elevation myocardial infarction represents a medical emergency requiring immediate intervention. A multimodal artificial intelligence model that integrated visual data from electrocardiograms and clinical text was evaluated to improve diagnostic accuracy compared to specialist evaluation. The study was retrospective, observational and used previously collected data. Image and text cleaning processes were applied, an architecture based on convolutional and recurrent neural networks was used, and cross-validation was performed with metrics such as area under the curve and F1 score. The results showed a diagnostic accuracy of 90% for the identification of ST-segment elevation myocardial infarction and specialist agreement measured by Cohen's Kappa coefficient of 0.90. These findings indicated that the multimodal model could represent an effective tool to support clinical diagnosis. It was concluded that model optimization is necessary to classify normal electrocardiograms and retrain it with specific population data to avoid overfitting.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Este trabajo tiene la licencia CC BY-NC-ND 4.0
References
Ayyad, M., Albandak, M., Gala, D., Alqeeq, B., Baniowda, M., Pally, J., & Allencherril, J. (2025). Reevaluating STEMI: The Utility of the Occlusive Myocardial Infarction Classification to Enhance Management of Acute Coronary Syndromes. Current Cardiology Reports, 27(1), 75. https://doi.org/10.1007/s11886-025-02217-8 DOI: https://doi.org/10.1007/s11886-025-02217-8
Herman, R., Kisova, T., Belmonte, M., Wilgenhof, A., Toth, G., Demolder, A., Rafajdus, A., Meyers, H. P., Smith, S. W., Bartunek, J., & Barbato, E. (2025). Artificial Intelligence-Powered Electrocardiogram Detecting Culprit Vessel Blood Flow Abnormality: AI-ECG TIMI Study Design and Rationale. Journal of the Society for Cardiovascular Angiography & Interventions, 4(3Part B), 102494. https://doi.org/10.1016/j.jscai.2024.102494 DOI: https://doi.org/10.1016/j.jscai.2024.102494
La, S., Tavella, R., Wu, J., Spertus, J. A., Pasupathy, S., Girolamo, O., Zeitz, C., Worthley, M., Arstall, M., Sinhal, A., & Beltrame, J. F. (2025). The patient journey in chronic coronary syndromes with/without obstructive coronary arteries. European Heart Journal - Quality of Care and Clinical Outcomes, 0, 1–10. https://doi.org/10.1093/EHJQCCO/QCAF012 DOI: https://doi.org/10.1093/eurheartj/ehae666.1330
Saranya, P., & Vennila, C. (2025). Myocardial Infarction Detection using Variational Mode Decomposition with Fuzzy Weight Particle Swarm Optimization and Depthwise Separable Convolutional Network. Computers in Biology and Medicine, 193. https://doi.org/10.1016/J.COMPBIOMED.2025.110329 DOI: https://doi.org/10.1016/j.compbiomed.2025.110329
Shah, T., Kapadia, S., Lansky, A. J., & Grines, C. L. (2022). ST-segment elevation myocardial infarction: sex differences in incidence, etiology, treatment, and outcomes. Springer, 24(5), 529–540. https://doi.org/10.1007/S11886-022-01676-7 DOI: https://doi.org/10.1007/s11886-022-01676-7
Strodthoff, N., Wagner, P., Schaeffter, T., & Samek, W. (2021). Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL. IEEE Journal of Biomedical and Health Informatics, 25(5), 1519–1528. https://doi.org/10.1109/JBHI.2020.3022989 DOI: https://doi.org/10.1109/JBHI.2020.3022989
Tognola, C., Maloberti, A., Varrenti, M., Mazzone, P., Giannattasio, C., & Guarracini, F. (2025). Myocardial Infarction with Nonobstructive Coronary Arteries (MINOCA): Current Insights into Pathophysiology, Diagnosis, and Management. Diagnostics, 15(7), 942. https://doi.org/10.3390/DIAGNOSTICS15070942 DOI: https://doi.org/10.3390/diagnostics15070942
Thygesen, K., Alpert, J. S., Jaffe, A. S., Chaitman, B. R., Bax, J. J., Morrow, D. A., White, H. D., & Executive Group on behalf of the Joint European Society of Cardiology (ESC)/American College of Cardiology (ACC)/American Heart Association (AHA)/World Heart Federation (WHF) Task Force for the Universal Definition of Myocardial Infarction (2018). Fourth Universal Definition of Myocardial Infarction (2018). Journal of the American College of Cardiology, 72(18), 2231–2264. https://doi.org/10.1016/j.jacc.2018.08.1038 DOI: https://doi.org/10.1161/CIR.0000000000000617
Zhang, K., Wang, P., Wu, L., Wang, S., Jia, Y., & Yang, J. (2025). A Soft Patch for Dynamic Myocardial Infarction Monitoring. ACS Applied Materials & Interfaces, 17(11), 16479–16488. https://doi.org/10.1021/acsami.4c18868 DOI: https://doi.org/10.1021/acsami.4c18868