Machine Learning Based Feature Optimization and Early Detection System in Heart Diseases - Paper

Aug 3, 2026

Upload by Violet

Heart diseases are a leading cause of mortality, making early diagnosis essential to reduce death rates and improve quality of life. This study applies machine learning to strengthen early detection of heart disease using records from 253,680 patients and evaluates five algorithms: Logistic Regression, K-Nearest Neighbors, Decision Tree, Naïve Bayes, and Linear SVM. The dataset is split 80% for training and 20% for testing, assessed with accuracy, precision, recall, and F1-measure. Feature reduction using correlation optimization improves resource use, with Logistic Regression achieving the highest accuracy of 90.67%.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Introduction

Literature Review

2023 7th International Symposium on Innovative Approaches in Smart Technologies (ISAS) | 979-8-3503-8306-5/23/$31.00 ©2023 IEEE | DOI: 10. 1 109/ISAS60782.2023. 10391754 MACHINE LEARNING BASED FEATURE OPTIMIZATION AND EARLY DETECTION SYSTEM IN HEART DISEASES Erman Özer Deparment of Computer Engineering Recep Tayyip Erdogan University Rize, Turkey [erman.ozer@erdogan.edu.tr](erman.ozer@erdogan.edu.tr) Hasan Aydos Department of Computer Engineering Recep Tayyip Erdogan University Rize, Turkey [hasan_aydos20@erdogan.edu.tr](hasan_aydos20@erdogan.edu.tr) Abstract: In today's world, humanity faces a myriad of challenges, many of which pose significant threats to our well-being. Chief among these challenges are health-related issues. Among these health problems, heart diseases stand out as the leading cause of mortality. Consequently, the early diagnosis of heart diseases plays a pivotal role in mitigating mortality rates and enhancing people's overall quality of life. This study aims to employ machine learning algorithms to enhance the early detection capabilities of heart disease. A dataset comprising the health records of 253,680 patients with heart disease is analyzed using five distinct machine learning algorithms: Logistic Regression, K-Nearest Neighbors Classifier, Decision Tree Classifier, Naïve Bayes, and Linear Support Vector Machine (Linear SVM). The dataset is partitioned, with 80% allocated for training the algorithms and the remaining 20% for testing. Furthermore, the study's evaluation employs four different metrics: accuracy, precision, recall, and the F1-measure. Initially, early diagnosis of heart disease is attempted using the complete set of features in the dataset. However, this approach results in excessive costs and time consumption. Subsequently, a feature reduction process is implemented to optimize resource utilization, yielding an improved early detection rate. The research findings indicate that Logistic Regression outperforms the other algorithms, achieving the highest success rate with an accuracy score of 90.67%. These research results underscore the substantial contribution of machine learning algorithms to the early detection of heart disease, ultimately enhancing the quality of life for individuals. Keywords—heart disease, machine learning, corr function. I. INTRODUCTION In the developing world of today, the influence and position of computer software on people's lives cannot be ignored. It is well known that artificial intelligence is one of the most important components of computer programs. This has attracted the attention of many researchers, educators and even many companies. Today, the integration of artificial intelligence into healthcare is the subject of research [1,2] . In general, it is believed that artificial intelligence can be used for early diagnosis of diseases, which is one of the major concerns of people today [3] . This research is about using machine learning algorithms for early diagnosis of heart diseases that could cost many lives by 2050 [4] . For training machine learning algorithms, a dataset consisting of individuals who have already had heart disease in their medical history and individuals who have never had heart problems before will be used. Data from more than 250,000 people will be used for the proposed research, and the accuracy of the results will be compared against the most popular machine learning algorithms. Corr function will be used to reduce data features in the dataset to save time and unit costs. Agile project development methods will be used during the project. Sprint planning and processes are dynamically managed to control the project process. Fig. 1. The developed system 979-8-3503-8306-5/23/$31 .00 ©2023 IEEE Authorized licensed use limited to: Recep Tayyip Erdogan Universitesi. Downloaded on March 20,2024 at 06:44:03 UTC from IEEE Xplore. Restrictions apply. As a method for early detection of heart attack risk, the sy

FAQs

What is the main goal of the study on heart diseases?

The study aims to use machine learning to improve the early detection capability for heart disease, helping mitigate mortality and enhance quality of life.

Which machine learning algorithms are evaluated in the research?

Five algorithms are used: Logistic Regression, K-Nearest Neighbors, Decision Tree, Naïve Bayes, and Linear Support Vector Machine (Linear SVM).

How does feature reduction affect the system’s performance?

The approach first attempts diagnosis using all features, which is costly in time and resources. A feature reduction step using correlation-based analysis optimizes resource utilization and improves early detection outcomes.

Aug 3, 2026

Upload by Violet