BIOKIMYOVIY TAHLILLARDA SUN’IY INTELLEKTNING O‘RNI: MA’LUMOTLARGA ASOSLANGAN DIAGNOSTIKA VA PROGNOZ
Keywords:
Big Data, Sun’iy intellekt (SI), Biomarkerlar / Biokimyoviy ko‘rsatkichlar, Kasallik xavfini bashorat qilish, Mashinali oʻrganish, Explainable AI (xAI), Integrativ ma’lumotlar (multi-omics), Tibbiyotda raqamlashtirishAbstract
Katta ma’lumotlar (Big Data) va sun’iy intellekt tibbiyot sohasida biokimyoviy ko‘rsatkichlarning murakkab va yuqori oʻlchovli tuzilishini tahlil qilishda yangi paradigmani taklif qiladi. Ushbu maqola SI va mashinali oʻrganish metodlarini qoʻllagan holda biokimyoviy markerlar (metabolitlar, fermentlar, yalligʻlanish indikatorlari va boshqa) asosida kasallik xavfini bashorat qilish imkoniyatlarini koʻrib chiqadi. Maqolada oldindan ishlov berish, xususiyatlar tanlovi, nazoratli modellash, shuningdek, izohli (explainable) AI usullari muhokama qilinadi. Tadqiqotlar, masalan, neyron tarmoqlar, Random Forest va gradient boosting modellari orqali yurak-qon tomir kasalliklari, Parkinson kasalligi va boshqa surunkali kasalliklar xavfini bashorat qilishda yuqori aniqlik ko‘rsatganini bildiradi. Bundan tashqari, izohli AI metodlari (masalan, SHAP) orqali AI qarorlari tushunarli bo‘lib, klinik integratsiya va shaffoflikni oshiradi. Ushbu yondashuvning afzalliklari orasida erta diagnostika, shaxsiylashtirilgan profilaktika va resurslarni samarali taqsimlash mavjud; ammo ma’lumotlarning sifati, etik masalalar va regulyator cheklovlari muammolari ham ko‘tariladi. Kelajakda multimodal ma’lumotlar (genom, metabolom, proteom) va real-vaqt monitoring (biosensorlar, wearables) integratsiyasi ushbu sohani yanada rivojlantirishga xizmat qilishi mumkin.
References
1. Cai, Y., Cai, Y.Q., Tang, L.Y. va boshqalar. “Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review.” BMC Medicine, 22:56, 2024. BioMed Central
2. Qureshi, M. D. A., Ramzan, M. F., Amjad, F., Haider, N. “Artificial Intelligence in Metabolomics for Disease Profiling: A Machine Learning Approach to Biomarker Discovery.” Indus Journal of Bioscience Research. induspublishers.com
3. Role of Artificial Intelligence in Identifying Vital Biomarkers with Greater Precision in Emergency Departments During Emerging Pandemics. International Journal of Molecular Sciences, MDPI. MDPI
4. Ghasemi, A., Hashtarkhani, S., Schwartz, D. L., Shaban-Nejad, A. “Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review.” arXiv, 2024. arXiv
5. Rudroff, T., Rainio, O., Klén, R. “AI for the prediction of early stages of Alzheimer’s disease from neuroimaging biomarkers — A narrative review.” arXiv, 2024. arXiv
6. Abzaliyev, K., Suleimenova, M., Abzaliyeva, S., Mansurova, M., Shomanov, A., Bugibayeva, A., Tolemisova, A., Kurmanova, A., Nassyrova, N. “Multidimensional Visualization and AI-Driven Prediction Using Clinical and Biochemical Biomarkers in Premature Cardiovascular Aging.” Biomedicines, 13(10):2482, 2025. MDPI
7. Machine learning enhances biomarker discovery: From multi-omics to functional genomics. Medical Research Archives. European Society of Medicine -
8. AI-Powered Biomarker Discovery: Identifying Novel Biomarkers for Early Disease Detection and Drug Development. Journal of Machine Learning in Pharmaceutical Research. pharmapub.org
