Raqamli Transformatsiya va Sun’iy Intellekt
BARIATRIK JARROHLIKKA TAYYORLIKNI BAHOLASHDA SUNʼIY INTELLEKT MODELLARINING QIYOSIY TAHLILI VA OPTIMAL MODELNI TANLASH
1 O‘zbekiston Respublikasi Oliy ta’limfan va innovatsiyalar vazirligi huzuridagi Oliy attestatsiya komissiyasi
2 Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti
3 Davr bank
Zenodo DOI: 10.5281/zenodo.20136739
Keywords
Abstract
Ushbu maqolada bariatrik jarrohlikka bemorlarning tayyorlik darajasini baholashda sunʼiy intellektga asoslangan klassifikatsiya algoritmlarining samaradorligi qiyosiy tahlil qilinadi. Tadqiqotning asosiy maqsadi klinik qaror qabul qilish jarayonini qoʻllab-quvvatlovchi va yuqori aniqlikka ega bo‘lgan optimal modelni aniqlashdan iborat. Tadqiqotda 1000 nafar bemorning anonimlashtirilgan tibbiy maʼlumotlari asosida Random Forest, K-Nearest Neighbors (K-NN) va Support Vector Machine (SVM) algoritmlarining ishlash samaradorligi o‘rganildi. Maʼlumotlar bazasi klinik, metabolik va fiziologik ko‘rsatkichlardan iborat bo‘lib, unda sezilarli darajadagi sinflar balanssizligi mavjudligi hisobga olindi. Modellar aniqlik (Accuracy), ROC-AUC, barqarorlik va interpretatsiya qulayligi mezonlari asosida baholandi. Eksperimental natijalar shuni ko‘rsatdiki, Random Forest algoritmi 98% test aniqligi va 0.97 ROC-AUC ko‘rsatkichi bilan eng yuqori natijani namoyon etdi hamda balanssiz maʼlumotlar bilan ishlashda yuqori barqarorlikka ega ekanligi aniqlandi. SVM algoritmi o‘rta darajadagi natijalarni ko‘rsatgan bo‘lsa, K-NN algoritmi o‘ta moslashishga moyilligi sababli pastroq samaradorlikni namoyon etdi. Tadqiqot natijalari asosida ko‘p modelli yondashuvga asoslangan tizim arxitekturasi ishlab chiqildi va unda Random Forest asosiy qaror qabul qiluvchi model sifatida, SVM esa tasdiqlovchi model sifatida qo‘llanilishi tavsiya etildi. Shuningdek, tizimda tushuntiriladigan sunʼiy intellekt (XAI) tamoyillarini qo‘llash orqali model qarorlarini izohlash imkoniyati yaratildi. Mazkur tadqiqot natijalari bariatrik jarrohlik amaliyotida bemorlarni to‘g‘ri saralash, operatsion xavflarni kamaytirish va klinik qaror qabul qilish samaradorligini oshirishga xizmat qiladi hamda tibbiyotda sunʼiy intellekt texnologiyalarini qo‘llashning muhim yo‘nalishlaridan biri sifatida ahamiyat kasb etadi.
References
- J. Esteva et al., “A guide to deep learning in healthcare,” Nature Medicine, vol. 25, pp. 24–29, 2019.
- L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
- T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed. New York, NY, USA: Springer, 2009.
- D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score,” BMC Genomics, vol. 21, no. 6, 2020.
- I. Guyon and A. Elisseeff, “An introduction to variable and feature selection,” Journal of Machine Learning Research, vol. 3, pp. 1157–1182, 2003.
- G. James et al., An Introduction to Statistical Learning. New York, NY, USA: Springer, 2013.
- J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Elsevier, 2011.
- C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995.
- N. V. Chawla et al., “SMOTE: Synthetic Minority Over-sampling Technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002.
- V. Vapnik, Statistical Learning Theory. New York, NY, USA: Wiley, 1998.
- M. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” Proceedings of the 22nd ACM SIGKDD, pp. 1135–1144, 2016.
- American Society for Metabolic and Bariatric Surgery, “Bariatric Surgery Procedures,” 2023. [Online]. Available: https://asmbs.org/patients/bariatric-surgery-procedures
- World Health Organization, “Obesity and overweight,” 2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/obesity-and-overweight
- B. Miotto et al., “Deep learning for healthcare: review, opportunities and challenges,” Briefings in Bioinformatics, vol. 19, no. 6, pp. 1236–1246, 2018.
- A. Rajkomar, J. Dean, and I. Kohane, “Machine learning in medicine,” New England Journal of Medicine, vol. 380, pp. 1347–1358, 2019.
- D. Dua and C. Graff, “UCI Machine Learning Repository,” University of California, Irvine, 2019. [Online]. Available: https://archive.ics.uci.edu
- T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967.
- B. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” Advances in Neural Information Processing Systems (NeurIPS), pp. 4765–4774, 2017.
- E. Topol, “High-performance medicine: the convergence of human and artificial intelligence,” Nature Medicine, vol. 25, pp. 44–56, 2019.
- S. Kotsiantis, “Supervised machine learning: A review of classification techniques,” Informatica, vol. 31, pp. 249–268, 2007.