^PAPER_TITLE^

^AUTHOR_NAME^

International Journal of Computer Techniques

ISSN 2394-2231

DOI Registered

Volume 12, Issue 6 | Published: November – December 2025

Author

Adnan Akbar Bandarkar

Abstract

Heart disease has become one of the most worrying health problems today. Many people lose their lives because the signs are often ignored or discovered too late. In this research, I tried to explore how machine learning can help in predicting heart disease before it becomes serious. The main idea behind this work is to make use of real medical data that includes basic information such as age, gender, cholesterol, blood pressure, and heart rate to find patterns that might indicate a higher risk. I collected the data from open sources like Kaggle and the UCI Repository and then trained different machine learning models such as Logistic Regression, Random Forest, Support Vector Machine, and XGBoost. Each model was tested carefully to see which one gives the most accurate and stable results. Among all, Random Forest and XGBoost gave the best predictions. This study also helped me understand which health factors affect the chances of heart disease the most. The goal of my work is not just to make predictions, but also to show how technology can be used in a simple and helpful way to support doctors and raise awareness about early heart care and prevention.

Keywords

Heart Disease Prediction, Machine Learning, Healthcare Analytics, Random Forest, XGBoost, Early Diagnosis, Medical Data, Preventive Healthcare

Conclusion

To be honest, when I began this project, I didn’t really expect it to come this far. I just wanted to try out something small with machine learning, and heart disease prediction felt like a good topic. But while working on it, I kind of started to see how deep and important this field is. It’s not only about data and numbers, it’s also about real people and real lives. At first, I was just testing a few models to see what happens. I used Logistic Regression, SVM, Random Forest, and XGBoost. I’d say the first two were okay but not that strong. When I ran Random Forest and XGBoost, though, I could see the difference. They gave better accuracy and didn’t change much even when I trained them again. That felt good — it showed that the model was learning something real.

References

[1]A. K. Dubey, et al., “Prediction of Heart Disease Based on Machine Learning Using Cleveland Heart Disease Dataset,” PMC, 2023. [2]UCI Machine Learning Repository, “Heart Disease Dataset,” 2025. [3]“Predicting Coronary Heart Disease with Advanced Machine Learning,” Nature Scientific Reports, 2025. [4]“Optimizing Heart Disease Diagnosis with Advanced Machine Learning,” BMC Cardiovascular Disorders, 2025. [5]“Machine Learning Algorithms for Heart Disease Diagnosis,” ScienceDirect, 2025. [6]“A Novel Approach for the Effective Prediction of Cardiovascular Disease,” PMC, 2024. [7]“Heart Disease Detection Using Machine Learning Methods,” Journal of Medical Artificial Intelligence, 2024. [8]“Effective Heart Disease Prediction Using Machine Learning,” MDPI Algorithms, 2024. [9]“Prediction of Heart Disease UCI Dataset Using Machine Learning Algorithms,” ResearchGate, 2022. [10]“Feature-Limited Prediction on the UCI Heart Disease Dataset,” TechScience Computer Modeling and Engineering, 2024. [11]“A Comprehensive Review of Machine Learning for Heart Disease,” Frontiers in Artificial Intelligence, 2025. [12]“Mixed Machine Learning Approach for Efficient Prediction of Human Cardiovascular Diseases,” MDPI Applied Sciences, 2022. [13] “Centralized and Federated Heart Disease Classification Models,” arXiv Preprint, 2024. [14]“A Data Balancing Approach Towards Design of an Expert System for Heart Disease Prediction,” arXiv Preprint, 2024. [15]“An Efficient Convolutional Neural Network for Coronary Heart Disease Prediction,” arXiv Preprint, 2019. [16]“A Comparative Study of Heart Disease Prediction Using Machine Learning,” ResearchGate, 2023. [17]“Machine Learning-Based Model to Predict Heart Disease in Early Stage Employing Several Feature Selection Techniques,” Wiley Online Library, 2023. [18]“Cardiovascular Diseases Prediction by Machine Learning,” PMC, 2023. [19]“A Proposed Technique for Predicting Heart Disease Using Machine Learning,” Nature Scientific Reports, 2024. [20]“Optimizing Stability of Heart Disease Prediction Across Imbalanced Datasets,” ScienceDirect, 2025.

How to Cite This Paper

Adnan Akbar Bandarkar (2025). Heart Disease Prediction Using Machine Learning: A Comparative Study of Classification Models and Feature Importance Analysis. International Journal of Computer Techniques, 12(6). ISSN: 2394-2231.