Keywords
Abstract
Ushbu ilmiy ishda buyrak toshlari (nefrolitiaz)ning mineral tarkibi asosida individual parhez algoritmini ishlab chiqish uchun sun’iy intellekt yondashuvi qo‘llanildi. Tadqiqot davomida 250 nafar bemor tahlil qilinib, ular orasida kalsiy oksalat, fosfat va urat toshlari eng ko‘p uchrashi aniqlandi. Ma’lumotlar mashina o‘rganish algoritmlari (Random Forest, Neural Network, KNN va Gradient Boosting) yordamida qayta ishlanib, bemorlarga mos parhez tavsiyalarini ishlab chiqish uchun model yaratildi. Natijada individual parhez algoritmi buyrak toshlari qaytalanishini 37% ga kamaytirishi bashorat qilindi.
References
Türk C., Petřík A., Sarica K. et al. EAU Guidelines on Diagnosis and Conservative
Management of Urolithiasis. Eur Urol. 2021.
2. Sorokin I., Mamoulakis C., Miyazawa K. Epidemiology of stone disease across the world. World J Urol. 2022.
3. He J., Zeng G., et al. Artificial intelligence in urology. World J Urol. 2023.
4. Liu Y., Chen Y. Machine learning-based dietary recommendations for nephrolithiasis. J Med Syst. 2024.
5. WHO Global Health Data on Urolithiasis, 2023.
6. Alelign T., Petros B. Kidney stone disease: an update on current concepts. Adv Urol. 2022.
7. Choy W., et al. Artificial intelligence and diet in clinical medicine. Front Nutr. 2023.
8. O‘zbekiston Respublikasi SSV statistika bo‘limi. 2023 yil hisobot.