SUN’IY INTELLEKT YORDAMIDA YURAK YETISHMOVCHILIGINI ERTA ANIQLASH VA TURLARINI AJRATISH (HFPEF VA HFREF)

Authors

  • Shakirova Lobar Mavlon qizi Author
  • Mahmudova Sadoqat Muxtorjon qizi Author

Keywords:

yurak yetishmovchiligi, sun’iy intellekt, mashinaviy o‘rganish, chuqur o‘rganish, HFpEF, HFrEF, ejeksiya fraksiyasi, ekokardiyografiya, elektrokardiografiya, magnit-rezonans tomografiya, fenotiplash, erta diagnostika, shaxsiylashtirilgan davolash

Abstract

Ushbu maqolada sun’iy intellekt (SI) yordamida yurak yetishmovchiligini (YY) erta aniqlash va uning ikki asosiy turi — HFpEF (saqlangan ejeksiya fraksiyali yurak yetishmovchiligi — yurakning qon haydash qobiliyati normal saqlangan, ammo to‘ldirilishi buzilgan holat) va HFrEF (pasaytirilgan ejeksiya fraksiyali yurak yetishmovchiligi — yurak qonni yetarli darajada hayday olmaydigan holat) o‘rtasida farqlashning zamonaviy usullari ko‘rib chiqiladi. An’anaviy diagnostika usullari, xususan HFpEFni aniqlashda, sezilarli cheklovlarga ega. SI, ayniqsa mashinaviy o‘rganish (MO — ma’lumotlardan mustaqil ravishda o‘rganadigan algoritmlar) va chuqur o‘rganish (ChO — ko‘p qatlamli neyron tarmoqlar asosida murakkab ma’lumotlarni tahlil qilish) texnologiyalari, ekokardiyografiya (EchoKG — yurak ultratovush tekshiruvi), elektrokardiografiya (EKG — yurak elektr faolligini yozib olish) va magnit-rezonans tomografiya (MRT) ma’lumotlarini qayta ishlash orqali diagnostika aniqligini oshirish imkoniyatiga ega. Tadqiqotlar shuni ko‘rsatadiki, SI-ECG modellari HFpEFni aniqlashda sezgirlik (sensitivity — kasallikni to‘g‘ri aniqlash ehtimoli) 0.89 va o‘ziga xoslik (specificity — sog‘lomlarni to‘g‘ri aniqlash ehtimoli) 0.80 ko‘rsatkichlariga erishadi. SI yordamida HFpEF va HFrEFni ajratish fenotiplash — kasallikning klinik va biologik xususiyatlariga ko‘ra kichik guruhlarga bo‘lish orqali shaxsiylashtirilgan davolash strategiyalarini ishlab chiqishga imkon beradi. Maqolada SI ning klinik natijalarga ta’siri va kelajakdagi istiqbollari ham muhokama qilinadi.

References

1. Alyacoub R. Artificial intelligence in heart failure — a comprehensive literature review. Cardiology Journal. 2025

32(6):655-665. DOI: 10.5603/cj.104365.

2. Arora S, et al. Artificial Intelligence in the Management of Heart Failure. Journal of Cardiac Failure. 2025

31(10):1561-1573. DOI: 10.1016/j.cardfail.2025.01.005.

3. Chang PH, Liao FC, Wu YC, et al. Machine Learning Enhanced Acute Heart Failure Phenotype Prediction using Natural Language Processing and Random Forest. Frontiers in Artificial Intelligence. 2025

8:1664627. DOI: 10.3389/frai.2025.1664627.

4. Hinds DA, et al. Translating Mechanistic Insights Into Action and Revealing New Pathways: Machine Learning Approaches in Heart Failure With Preserved Ejection Fraction. Journal of the American Heart Association. 2026. DOI: 10.1161/JAHA.125.043617.

5. Tison G, et al. Multiview deep learning for detection of major cardiac conditions from echocardiography. Nature Cardiovascular Research. 2026. DOI: 10.1038/s44161-026-00786-7.

6. Redfield MM, Borlaug BA. Heart Failure With Preserved Ejection Fraction: A Review. JAMA. 2023. DOI: 10.1001/jama.2023.2020.

7. Diagnostic Performance of Artificial Intelligence-Driven Electrocardiogram Algorithms in Detecting HFpEF: A Systematic Review and Meta-Analysis. International Journal of Cardiovascular Sciences. 2026

39:e20250091..

8. Duffy G, et al. External validation of artificial intelligence for detection of heart failure with preserved ejection fraction. Nature Communications. 2025

16:2915. DOI: 10.1038/s41467-025-58283-7.

9. Soe HT, Iwata H. Deep Learning-Based Echocardiography Wall Thickness Analysis for Heart Failure Detection. IEEE Access. 2026

14:36924-36932. DOI: 10.1109/ACCESS.2026.3670331.

10. Ballena-Caicedo JJ, Zuzunaga-Montoya FE, Valladolid-Sandoval LA, et al. Global heart failure incidence rate: an updated systematic review and meta-analysis. Frontiers in Cardiovascular Medicine. 2026. DOI: 10.3389/fcvm.2026.1714070.

11. STRATIFYHF Study Group. Clinical validation of an artificial intelligence-based decision support system for diagnosis and risk stratification of heart failure (STRATIFYHF): a protocol for a prospective, multicentre longitudinal study. BMJ Open. 2025

15(1):e091793. DOI: 10.1136/bmjopen-2024-091793.

12. Bhatia A, et al. Impact of Artificial Intelligence on Cardiovascular Disease Diagnosis, Risk Assessment, and Treatment: A Meta-Analysis of 45 Studies. Circulation. 2025. Abstract 4371686..

13. Kather JN. Artificial Intelligence in Medicine (textbook). 2025..

14. Mann DL, ed. Heart Failure: A Companion to Braunwald‘s Heart Disease. 5th ed. Elsevier

2024..

15. Zipes DP, Libby P, Bonow RO, Mann DL, Tomaselli GF, eds. Braunwald’s Heart Disease: A Textbook of Cardiovascular Medicine. 12th ed. Elsevier

2025.

Published

2026-05-08