MASHINALI O‘RGANISH ALGORITMLARINING YURAK KASALLIKLARINI KLASSIFIKATSIYALASHDAGI ROLI
Keywords:
Mashinali o‘rganish, yurak kasalliklari, klassifikatsiya, diagnostika, logistik regressiya, qaror daraxti, K yaqin qo‘shnilar (KNN), tasodifiy o‘rmon (Random Forest), gradient boosting, sun’iy neyron tarmoqlar, aniqlik, sezuvchanlik, F1-mezon, ROC-AUC, sog‘liqni saqlash tizimi, O‘zbekiston, raqamli texnologiyalar, sun’iy intellekt.Abstract
Maqolada mashinali o‘rganish algoritmlarining yurak kasalliklarini erta aniqlash va ularni klassifikatsiyalashdagi roli chuqur o‘rganilgan. Yurak-qon tomir kasalliklari global miqyosda o‘limning yetakchi sababi hisoblanishi tufayli, ularni zamonaviy texnologiyalar yordamida tashxislash dolzarb masala sifatida qaralmoqda. Tadqiqotda logistik regressiya, qaror daraxtlari, K yaqin qo‘shnilar, tasodifiy o‘rmonlar, gradient boosting va sun’iy neyron tarmoqlar algoritmlaridan foydalanilib, ularning samaradorligi solishtirilgan. Ma’lumotlar UCI Machine Learning Repository platformasidan olingan yurak kasalliklari datasetlari asosida tayyorlangan bo‘lib, ular tahlil qilinib, tozalash va normalizatsiya jarayonlaridan o‘tkazilgan. Natijalar shuni ko‘rsatdiki, gradient boosting algoritmi aniqlik, sezuvchanlik va F1-mezonlar bo‘yicha eng yuqori ko‘rsatkichlarga ega bo‘lib, yurak kasalligini aniqlashda eng istiqbolli model sifatida baholandi. Random forest modeli barqarorligi va atributlar ahamiyatini tahlil qilish imkoniyati bilan ajralib turgan bo‘lsa, sun’iy neyron tarmoqlar murakkab bog‘lanishlarni aniqlashda yuqori samaradorlik ko‘rsatdi. Shu bilan birga, logistik regressiya va qaror daraxtlari oddiyligi va izohlanish imkoniyati sababli klinik amaliyotda qo‘llash uchun qulay bo‘lishi mumkinligi ta’kidlangan. Maqolada O‘zbekistonda sog‘liqni saqlash tizimini raqamlashtirish siyosati bilan bog‘liq holda ushbu algoritmlarni joriy etishning amaliy ahamiyati ham yoritilgan.
References
1. O‘zbekiston Respublikasi Prezidentining 2022-yil 28-fevraldagi PQ–140-son qarori
2. Alaa, A. M., & van der Schaar, M. (2019). AutoPrognosis: Automated clinical prognostic modeling via Bayesian optimization with structured kernel learning. Artificial Intelligence in Medicine, 99, 101680. https://doi.org/10.1016/j.artmed.2019.101680
3. Dey, N., Ashour, A. S., & Balas, V. E. (2018). Smart medical data sensing and IoT systems design in healthcare. Springer. https://doi.org/10.1007/978-3-319-77685-9
4. Gudadhe, M., Wankhade, K., & Dongre, S. (2010). Decision support system for heart disease based on support vector machine and artificial neural network. In 2010 International Conference on Computer and Communication Technology (pp. 741–745). IEEE. https://doi.org/10.1109/ICCCT.2010.5640439
5. Krittanawong, C., Zhang, H., Wang, Z., Aydar, M., & Kitai, T. (2017). Artificial intelligence in precision cardiovascular medicine. Journal of the American College of Cardiology, 69(21), 2657–2664. https://doi.org/10.1016/j.jacc.2017.03.571
6. Mohan, S., Thirumalai, C., & Srivastava, G. (2019). Effective heart disease prediction using hybrid machine learning techniques. IEEE Access, 7, 81542–81554. https://doi.org/10.1109/ACCESS.2019.2923707
7. Rajpurkar, P., Hannun, A. Y., Haghpanahi, M., Bourn, C., & Ng, A. Y. (2017). Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv preprint arXiv:1707.01836.
8. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144). https://doi.org/10.1145/2939672.2939778
9. Shouman, M., Turner, T., & Stocker, R. (2012). Using data mining techniques in heart disease diagnosis and treatment. In Japan-Egypt Conference on Electronics, Communications and Computers (pp. 173–177).
10. Tison, G. H., Sanchez, J. M., Ballinger, B., Singh, A., Olgin, J. E., Pletcher, M. J., & Marcus, G. M. (2018). Passive detection of atrial fibrillation using a commercially available smartwatch. JAMA Cardiology, 3(5), 409–416. https://doi.org/10.1001/jamacardio.2018.0136
