JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

KO‘KRAK SARATONI KASALLIGINI TASHHISLASHDA MASHINALI O‘RGATISH MODELLARINING QIYOSIY TAHLILI

Tursunmurotov Davrbek Xudayorovich1, Normamatov Xayriddin Mengniyevich2, Karimova Dilfiya Shuxratovna2

1 Axborot texnologiyalari va menejment universiteti

2 Osiyo texnologiyalari universiteti

Zenodo DOI: 10.5281/zenodo.19725117

Keywords

mashinali o‘rgatish ko‘krak saratoni sun’iy intellekt tasniflash algoritmlari erta tashhislash

Abstract

Ushbu maqolada ko‘krak saratonini erta tashhislash masalasi mashinali o‘rganish algoritmlaridan foydalanish asosida tadqiq etiladi. Tadqiqotning asosiy maqsadi ko‘krak bezidagi o‘smalarning xavfli (malignant) yoki xavfsiz (benign) ekanligini hujayra yadrolarining morfologik xususiyatlarini ifodalovchi miqdoriy belgilar yordamida aniqlash imkoniyatlarini baholashdan iborat[2]. Tadqiqot uchun Breast Cancer Wisconsin (Diagnostic) ma’lumotlar to‘plamidan foydalanildi. Ushbu tanlanmada har bir obyekt hujayra radiusi, perimetri, maydoni, silliqligi, simmetriyasi va fraktal o‘lchami kabi ko‘rsatkichlar bilan tavsiflanadi.
Eksperiment jarayonida Logistic Regression[5], K-Nearest Neighbors[4] va Support Vector Machine (RBF yadrosi asosida)[3] algoritmlari qo‘llanilib, ularning tasniflash samaradorligi qiyosiy tahlil qilindi. Ma’lumotlar oldindan normallashtirilib, modellar bir xil sharoitda o‘rgatildi hamda test tanlanmada sinovdan o‘tkazildi. Modellarning samaradorligi aniqlik (accuracy), aniqlik koeffitsienti (precision), to‘liq qamrov (recall) va F1-o‘lchovi mezonlari asosida baholandi.
Olingan natijalar mashinali o‘rgatish modellarining yuqori aniqlik bilan ishlashini hamda ko‘krak saratonini tashhislash jarayonida tibbiy mutaxassislar uchun qaror qabul qilishni qo‘llab-quvvatlovchi samarali vosita bo‘lishi mumkinligini ko‘rsatdi. Tadqiqot sun’iy intellekt texnologiyalarining diagnostika jarayonlarini takomillashtirishdagi amaliy ahamiyatini tasdiqlaydi.

Views: 95 Published: 2026-04-28 Pages: 58-64 Volume: 4 Issue: 2

References

  1. Dua D., Graff C. UCI Machine Learning Repository. – Irvine, CA: University of California, School of Information and Computer Science, 2019.
  2. Scikit-learn Documentation:https://scikit-learn.org
  3. Goodfellow I., Bengio Y., Courville A. Deep Learning. – Cambridge: MIT Press, 2016.
  4. Wolberg W. H., Street W. N., Mangasarian O. L. Machine learning techniques to diagnose breast cancer from fine-needle aspirates // Cancer Letters. – 1994. – Vol. 77. – pp. 163–171.
  5. Van der Maaten L., Hinton G. Visualizing data using t-SNE // Journal of Machine Learning Research. – 2008. – Vol. 9. – pp. 2579–2605.
  6. Cortes C., Vapnik V. Support-vector networks // Machine Learning. – 1995. – Vol. 20. – pp. 273–297.
  7. Cover T., Hart P. Nearest neighbor pattern classification // IEEE Transactions on Information Theory. – 1967. – Vol. 13. – pp. 21–27.
  8. Hosmer D. W., Lemeshow S., Sturdivant R. X. Applied Logistic Regression. – 3rd ed. – New York: Wiley, 2013.
  9. Kaggle – Breast Cancer Dataset: https://www.kaggle.com/datasets