ACUTE CORONARY SYNDROME WITHOUT ST-SEGMENT ELEVATION ON ELECTROCARDIOGRAM: SELECTION OF MANAGEMENT STRATEGY USING NEURAL NETWORK TECHNOLOGIES
DOI:
https://doi.org/10.4238/k60j2z07Keywords:
acute coronary syndrome, multi-stage diagnostics, evidence-based medicine, treatment strategy algorithm, neural network technologies, Bayesian networks, medical school students.Abstract
Objective. The implementation of neural network modeling will enable the integration of a recommendation system (algorithm) based on Bayesian network analysis into the clinical practice and pedagogical training of medical school students in developing a clinical decision-making strategy in cases of suspected coronary artery pathology.
Methods. The development of an artificial intelligence model with integrated Bayesian networks is based on probability estimation across a combination of symptoms and laboratory-instrumental findings, with time-series analysis (frequency distribution across various forms of coronary artery disease and evidence-based medicine data).
Discussion. The proposed diagnostic methodology in cardiology, utilizing neural network technologies built on a probabilistic Bayesian architecture, is driven primarily by the complexity of the diagnostic workup and the determination of treatment strategy in acute coronary syndrome without ST-segment elevation on electrocardiogram. The application of a clinical decision support system has made it possible — drawing on the most robust evidence from randomized controlled trials grounded in the principles of evidence-based medicine — to differentiate latent coronary artery disease in atypical anginal presentations within a large clinical information field.
Conclusions. The use of artificial intelligence allows for the continuous updating of diagnostic and treatment protocols for cardiovascular diseases, taking into account the high comorbidity of cardiac and general internal medicine pathology. The evidence-based paradigm of scientific and clinical inquiry in cardiology, augmented by neural network analytical tools, will enable the development of structured clinical thinking in future specialists from the undergraduate stage of medical education, and facilitate the extrapolation of fundamental knowledge to the interpretation of tactical approaches in suspected coronary artery disease in each individual case.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

