THE USE INTEGRATION OF MACHINE LEARNING FOR CARDIOVASCULAR DISEASE DIAGNOSIS
Main Article Content
Abstract
The aim of the research – the possibility of using deep learning neural networks for diagnosing cardiovascular diseases with remote access to the global Internet investigated.
Materials and methods. The method of comparative analysis of devices for conducting electronic auscultation and the corresponding software was used. Transfer learning provided by the Teachable Machine web service to obtain a predictive model used. The JavaScript programming language, the TensorFlow.js machine learning library, and the Speech Command Recognizer to develop the web application were used.
Results. The proposed model on test datasets in the remote diagnostics mode on the global Internet was developed and tested. In real time with connecting the electronic stethoscope to the audio input of a personal computer was performed. The proposed model on the datatset of audio showed the possibility of diagnosing cardiac abnormalities with an accuracy of more than 90% were tested.
Keywords
Article Details
Information about financing and conflict of interests
The authors declare that they have no apparent or potential conflicts of interest related to the publication of this article.
This work is licensed under a Creative Commons Attribution 4.0 License.
How to Cite
References
Sadr H, Salari A, Ashoobi MT, Nazari M. Cardiovascular disease diagnosis: a holistic approach using the integration of machine learning and deep learning models. Eur J Med Res. 2024; 29(1): 455. doi: 10.1186/s40001-024-02044-7
Garanin AA, Aydumova OY, Rubanenko AO, Bibikova EG. Digital stethoscope: a new era of auscultation. Digital Diagnostics. 2024; 5(4): 808-818. Russian (Гаранин А.А., Айдумова О.Ю., Рубаненко А.О., Бибикова Е.Г. Цифровой стетоскоп – новая эра аускультации //Digital Diagnostics. 2024. Т. 5, № 4. C. 808-818.) doi: 10.17816/DD632499
Huang J, Cai Y, Wu X, Huang X, Liu J, Hu D. Prediction of mortality events of patients with acute heart failure in intensive care unit based on deep neural network. Comput Methods Programs Biomed. 2024; 256: 108403. doi: 10.1016/j.cmpb.2024.108403
Mohamed N, Lafi Almutairi R, Abdelrahim S, Alharbi R, Alhomayani FM, Alsulami A, Alkhalaf S. Deep convolutional fuzzy neural networks with stork optimization on chronic cardiovascular disease monitoring for pervasive healthcare services. Sci Rep. 2025; 15(1): 19008. doi: 10.1038/s41598-025-02924-w
Prosvirkina EV, Sakharchuk AYu. The the use of artificial intelligence in the processing of audiograms were researched. Strategic Directions for the Development of Science, Medicine, Digital and Educational Technologies: Collection of Scientific Articles. Kemerovo, 2024. P. 197-200. Russian (Просвиркина Е.В., Сахарчук А.Ю. Исследование работы искусственного интеллекта при обработке аудиограмм //Стратегические векторы развития науки, медицины, цифровых и образовательных технологий: Сборник научных статей. Кемерово, 2024. С. 197-200)
Sakhibgareeva MV, Zaozersky AYu. Developing an artificial intelligence-based system for medical prediction. Bulletin of Russian State Medical University. 2017; 6: 42-46. Russian (Сахибгареева М.В., Заозерский А.Ю. Разработка системы прогнозирования диагнозов заболеваний на основе искусственного интеллекта //Вестник РГМУ. 2017. № 6. C. 42-46)