Machine Learning and Feature Selection to SEER Data to Novel Diagnosis Thyroid Cancer

سال انتشار: 1400
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 187

نسخه کامل این مقاله ارائه نشده است و در دسترس نمی باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

IBIS10_030

تاریخ نمایه سازی: 5 تیر 1401

چکیده مقاله:

In this research to create a machine learning prediction model that can be used to predict bone metastasisin thyroid cancer. Demographic and clinicopathologic variables of thyroid cancer patients in theSurveillance, Epidemiology, and End Results database from ۲۰۱۰ to ۲۰۱۶ were retrospectively analyzed.On this basis, we developed a random forest algorithm model based on machine-learning. The area underreceiver operating characteristic curve (AUC), accuracy score, recall rate, and specificity are used toevaluate and compare the prediction performance of the random forestmodel and the other model. A totalof ۱۷,۱۳۸ patients were included in the study, with ۱۶۶ (۰.۹۷%) developed bone metastases. Grade, T stage,histology, race, sex, age, and N stage were the important prediction features of bone metastasis. The randomforestmodel has better predictive performance than the other model (AUC: ۰.۹۱۷, accuracy: ۰.۹۰۴, recallrate: ۰.۸۳۳, and specificity: ۰.۹۰۵). The random forestmodel constructed in this study could accuratelypredict bone metastases in thyroid cancer patients, which may provide clinicians with more personalizedclinical decision-making recommendations. In conclusion, here, we developed a random forest predictionmodel for bone metastases in thyroid cancer patients that outperformed traditional logistic regressionmodels. This facilitates personalized diagnosis and refined clinical decision making for bone metastasis inthyroid cancer patients.

نویسندگان

Ali Abedini

Department of Bioinformatics, Segal biotechnology, Tehran, Iran

Shirin Malehmir

Department of Microbiology, Karaj Branch, Islamic azad university, Karaj, Iran