Benefits and risks of implementing the Neuromed AI medical decision support system in the cardiology service of the Republic of Uzbekistan.
Abstract
Aim: Clinical testing of the NeuromedAI Cardio intelligent system, designed to automate routine tasks of cardiologists and improve the quality of medical care;
Materials and methods. The study used the NeuromedAI Cardio intelligent system and a questionnaire, including 28 questions aimed at expert assessment of the potential benefits of the system for doctors. The questionnaire helped to define the main requirements for the system, as well as formulate recommendations for improving the model. In particular, areas were identified for enriching the training dataset and further training the model in order to improve the accuracy of responses;
Results. As part of a pilot study of the Neuromed system conducted in 2024, an anonymous survey of 21 cardiologists was organized. The average experience of the participants was 17 ± 11.1 years. Analysis of the questionnaires showed that during interaction with the system, specialists asked a total of 400 questions, which reflects a high level of interest in the technology and its active testing in the professional environment;
Conclusion. Based on the obtained results, it is planned to develop recommendations for adapting the system for implementation in the practice of primary health care in the Republic of Uzbekistan. It is expected that the adapted system will improve the accuracy of diagnosis and the effectiveness of treatment at the primary level, which will be reflected in the improvement of key indicators of public health and will receive positive feedback from health workers.
About the Authors
List of references
M. Lindstrom, «Global Burden of Cardiovascular Diseases and Risks Collaboration, 1990-2021», J Am Coll Cardiol, т. 80, issue. 25, сс. 2372–2425, Dec. 2022, https://doi.org/10.1016/j.jacc.2022.11.001.
F. L. J. Visseren, «2021 ESC Guidelines on cardiovascular disease prevention in clinical practice», Eur Heart J, т. 42, issue. 34, сс. 3227–3337, september. 2021, https://doi.org/10.1093/eurheartj/ehab484.
K. Kotseva, «Lifestyle and impact on cardiovascular risk factor control in coronary patients across 27 countries: Results from the European Society of Cardiology ESC-EORP EUROASPIRE V registry», Eur J Prev Cardiol, т. 26, issue. 8, сс. 824–835, May 2019, https://doi.org/10.1177/2047487318825350.
M. J. Boonstra, D. Weissenbacher, J. H. Moore, G. Gonzalez-Hernandez, and F. W. Asselbergs, «Artificial intelligence: revolutionizing cardiology with large language models», Eur Heart J, т. 45, issue. 5, сс. 332–345, February. 2024, https://doi.org/10.1093/eurheartj/ehad838.
Perepech NB, Tregubov AV, Mikhaylova IE. Analysis of factors influencing physicians’ knowledge of clinical guidelines for treating chronic heart failure. Russian Journal of Cardiology. 2024;29(1S):Art. 1S. https://doi.org/10.15829/1560-4071-2024-5722. In Russian: Н. Б. Перепеч, А. В. Трегубов, и И. Е. Михайлова, «Анализ факторов, влияющих на знание врачами положений клинических рекомендаций по лечению хронической сердечной недостаточности», Российский кардиологический журнал, т. 29, вып. 1S, Art. вып. 1S, фев. 2024, https://doi.org/10.15829/1560-4071-2024-5722.
S. Parsa, S. Somani, R. Dudum, S. S. Jain, and F. Rodriguez, «Artificial Intelligence in Cardiovascular Disease Prevention: Is it Ready for Prime Time?», Curr Atheroscler Rep, т. 26, issue. 7, сс. 263–272, Jul. 2024, https://doi.org/10.1007/s11883-024-01210-w.
E. K. Oikonomou and R. Khera, «Artificial intelligence-enhanced patient evaluation: bridging art and science», Eur Heart J, т. 45, issue. 35, сс. 3204–3218, september. 2024, https://doi.org/10.1093/eurheartj/ ehae415.
A. Nolin-Lapalme, «Maximising Large Language Model Utility in Cardiovascular Care: A Practical Guide», Can J Cardiol, т. 40, issue. 10, сс. 1774–1787, Oct. 2024, https://doi.org/10.1016/j.cjca.2024.05.024.
A. J. Thirunavukarasu, D. S. J. Ting, K. Elangovan, L. Gutierrez, T. F. Tan, и D. S. W. Ting, «Large language models in medicine», Nat Med, т. 29, issue. 8, сс. 1930–1940, Aug. 2023, https://doi.org/10.103 8/s41591-023-02448-8.
H. Ji, «Large language model comparisons between English and Chinese query performance for cardiovascular prevention», Commun Med, т. 5, issue. 1, сс. 1–8, May 2025, https://doi.org/10.1038/s43856-025-00802-0.
S. Law, B. Oldfield, W. Yang, and Global Obesity Collaborative, «ChatGPT/GPT-4 (large language models): Opportunities and challenges of perspective in bariatric healthcare professionals», Obes Rev, т. 25, issue. 7, с. e13746, Jul. 2024, https://doi.org/10.1111/obr.13746.
Y. Kaneda, «Assessing the Performance of GPT-3.5 and GPT-4 on the 2023 Japanese Nursing Examination», Cureus, т. 15, вып. 8, с. e42924, авг. 2023, https://doi.org/10.7759/cureus.42924.
T. K. W. Hung, «Performance of Retrieval-Augmented Large Language Models to Recommend Head and Neck Cancer Clinical Trials», J Med Internet Res, т. 26, с. e60695, окт. 2024, https://doi.org/10.2196/60 695.
L. Y. Jiang, «Health system-scale language models are all-purpose prediction engines», Nature, т. 619, вып. 7969, сс. 357–362, июл. 2023, https://doi.org/10.1038/s41586-023-06160-y.
«(PDF) Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications», ResearchGate, https://doi.org/10.1109/JPROC.2021.3060483.
A. Nolin-Lapalme, «Maximising Large Language Model Utility in Cardiovascular Care: A Practical Guide», Can J Cardiol, т. 40, вып. 10, сс. 1774–1787, окт. 2024, https://doi.org/10.1016/j.cjca.2024.05.024.
E. Goh, «Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial», JAMA Netw Open, т. 7, вып. 10, с. e2440969, окт. 2024, https://doi.org/10.1001/jamanetworkopen.2024.40969.
«9781003539483 | PDF | Artificial Intelligence | Intelligence (AI) Semantics». Просмотрено: 11 июнь 2025 г. [Онлайн]. Доступно на: https://ru.scribd.com/document/860159908/9781003539483.
Copyright (c) 2025 Х.Г. Фозилов, Р.Х. Тригулова (Автор)
This work is licensed under a Creative Commons Attribution 4.0 International License.