New feature selection method based on random forest for cancer classification

  • سال انتشار: 1402
  • محل انتشار: دوازدهمین همایش ملی و سومین همایش بین المللی بیوانفورماتیک
  • کد COI اختصاصی: IBIS12_187
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 77
دانلود فایل این مقاله

نویسندگان

Nima Mahmoudi

Department of Electrical and Computer Engineering, University of Science and Technology of Mazandaran, Behshahr, Iran

Mohammad Reza Jafari

Department of Electrical and Computer Engineering, University of Science and Technology of Mazandaran, Behshahr, Iran

Jamshid Pirgazi

Department of Electrical and Computer Engineering, University of Science and Technology of Mazandaran, Behshahr, Iran

چکیده

Cancer diagnosis based on gene expression data is a critical area of research, offering insightsinto molecular mechanisms and aiding personalized medicine. In this study, we employed machinelearning algorithms to classify cancer types using a gene expression dataset [۱]. The highdimensionality, noise, and interpretability are challenges addressed in this research.Understanding gene expression patterns in cancer is vital for advancing cancer biology and treatmentstrategies. Machine learning models, such as SVM, kNN, MLP, Decision Tree, Naive Bayes, andRandom Forest, were applied for accurate cancer type prediction, showcasing potential applications inclinical settings [۲].High-dimensional gene expression data poses challenges, addressed through preprocessing and featureselection. Label encoding and dataset splitting were performed, and Random Forest identified top genes.Results indicated improved performance, particularly in SVM, MLP, and Random Forest models,showcasing enhanced classification accuracy [۱][۳].The study emphasizes the potential of machine learning in cancer type classification. Models achievedhigh accuracy, with SVM, MLP, and Random Forest outperforming others [۱][۲]. Feature selection withRandom Forest contributed to improved interpretability. Further research should focus on addressinginterpretability challenges and validating results in clinical contexts .Machine learning models offer promising results in cancer type classification based on gene expressiondata [۱][۲][۳]. SVM, MLP, and Random Forest demonstrated enhanced accuracy. Addressinginterpretability challenges is crucial for translating these findings into clinical applications. Notably, thestudy showcases improvements in detection rates, highlighting the significance of these models inadvancing cancer diagnostics [۱].

کلیدواژه ها

Diagnosis , Interpretability , Classification , Random Forest , Detection rates

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.