AI-Driven Heart Disease Prediction: A Step Towards Smarter Healthcare

• Author(s): Shreya Shingate ; Sakshi Shimpi ; Zeeshaan Shaikh
• Paper ID: 1707394
• Page: 155-162
• Published Date: 07-03-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 9 March-2025

Abstract

Heart disease is one of the top causes of death globally, accounting for nearly 17.9 million deaths each year, according to the World Health Organization. Early identification of cardiac disease is critical for lowering death rates and improving patient outcomes. Traditional diagnostic procedures, on the other hand, frequently need comprehensive medical exams, specialist expertise, and modern healthcare infrastructure, rendering them out of reach for many people, particularly in low- and middle-income countries. Machine learning-based prediction models have emerged as a possible answer to these difficulties, utilizing big datasets to automatically find trends and offer risk evaluations. This paper describes a detailed investigation of heart disease prediction using machine learning approaches. The suggested system classifies patients based on their chance of acquiring heart disease using a variety of machine learning methods such as Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and Neural Networks. The dataset utilized in this study was obtained from the Cleveland Heart Disease Dataset, which is accessible in the UCI Machine Learning Repository and includes health indicators such as age, cholesterol levels, blood pressure, smoking behaviors, diabetes status, and family medical history. The technique includes data preprocessing, feature selection, model training, and performance evaluation. Data cleaning, normalization, one-hot encoding, and statistical imputation are used to prepare the dataset for machine learning algorithms. The models are trained by k-fold cross-validation, and hyperparameter adjustment is used to improve prediction performance. Model performance is assessed using evaluation criteria such as accuracy, precision, recall, F1 score, and the ROC-AUC curve.

Keywords

Heart Disease, Machine Learning, Prediction, Classification, Data Mining, Artificial Intelligence, Risk Assessment, Healthcare Analytics, Predictive Modeling, Medical Diagnosis, Feature Selection

Citations

IRE Journals:
Shreya Shingate , Sakshi Shimpi , Zeeshaan Shaikh "AI-Driven Heart Disease Prediction: A Step Towards Smarter Healthcare" Iconic Research And Engineering Journals Volume 8 Issue 9 2025 Page 155-162

IEEE:
Shreya Shingate , Sakshi Shimpi , Zeeshaan Shaikh "AI-Driven Heart Disease Prediction: A Step Towards Smarter Healthcare" Iconic Research And Engineering Journals, 8(9)