Machine Learning-Based Heart Disease Prediction: An SVR Approach with Selected Interactions

  • سال انتشار: 1404
  • محل انتشار: کنفرانس بین المللی هوش مصنوعی و فناوری های مرتبط
  • کد COI اختصاصی: ICIRT01_013
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 16
دانلود فایل این مقاله

نویسندگان

M. Zarebnia

Department of Computer Science, University of Mohaghegh Ardabili, Ardabil, Iran

H. Barandak Imcheh

Department of Mathematics and Applications, University of Mohaghegh Ardabili, Ardabil, Iran

D. Mirizadeh

Department of Computer Science, University of Mohaghegh Ardabili, Ardabil, Iran

چکیده

A collection of various ailments that affect the heart and blood vessels is referred to as cardiovascular disease (CVD), also known as heart disease. In the world, heart disease is the main cause of fatality and morbidity, resulting in ۱۸ million deaths per year. Preventing premature death can be achieved by identifying those who are most vulnerable to heart diseases and providing them with the appropriate care. In the medical field, machine learning algorithms are becoming increasingly important, particularly when utilizing medical databases to diagnose diseases. Efficient algorithms and data processing techniques are used to predict different diseases, and there is great potential for accurate prediction of heart disease. Therefore, this study compares the support vector regression (SVR) with selected interaction terms approach with other methods such as random forest, logistic regression, decision tree, k-nearest neighbor (KNN) and support vector machine (SVM). This test comes from two sets of data, both of which are ۱۴ features and from The Cleveland Clinic Heart disease datasets and are obtained from Kaggle, the former with ۳۰۳ instances and the latter containing ۱۰۲۵ cases. It was found that the method presented in this article obtained better results than other algorithms. So that for a data set with many samples, it will bring an acceptable accuracy of ۱۰۰%. This result is achieved through rigorous cross-validation and feature interaction selection without signs of overfitting.

کلیدواژه ها

Support vector regression (SVR), Machine learning, Heart disease, Interaction terms

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.