Author:
Tasnim Nishat,Tanvir Kazi,Sezan Sanjid Bin Karim
Abstract
Predicting cardiac conditions remains one of the most formidable tasks within the medical field today, with heart disease claiming a life every minute in the contemporary landscape. The data-rich healthcare industry necessitates the application of data science for efficient data processing. Given the intricate nature of prognosticating heart-related disorders, the automation of this process becomes a necessity, aiming to mitigate potential risks and offer timely alerts to patients. In this research endeavor, the heart disease dataset extracted from the UCI machine learning repository is employed. The proposed study embraces an array of data mining strategies, encompassing Logistic Regression, Decision Tree, Support Vector Machine (SVM), and Naive Bayes algorithm, to anticipate the likelihood of Heart Disease and stratify patient risk levels. This article undertakes a comparative analysis of various machine learning algorithms to assess their effectiveness. The trial outcomes indicate that, compared to other utilized ML algorithms, Support Vector Machine (SVM) emerges with the highest accuracy, registering at 90.48%.
Reference13 articles.
1. A. Golande, “Heart Disease Prediction Using Effective Machine Learning Techniques,” vol. 8, no. 1, 2019.
2. T. Nagamani, S. Logeswari, and B. Gomathy, “Heart Disease Prediction using Data Mining with Mapreduce Algorithm,” vol. 8, no. 3, 2019.
3. M. Shahreyar, R. Fahhoum, O. Akinseye, S. Bhandari, G. Dang, and R. N. Khouzam, “Severe sepsis and cardiac arrhythmias,” Ann. Transl. Med., vol. 6, no. 1, Jan. 2018, doi: 10.21037/atm.2017.12.26.
4. W. S. Andras Janosi, “Heart Disease.” UCI Machine Learning Repository, 1989. doi: 10.24432/C52P4X.
5. “Design And Implementing Heart Disease Prediction Using Naives Bayesian | Semantic Scholar.” https://www.semanticscholar.org/paper/Design-And-Implementing-Heart-Disease-Prediction-Repaka-Ravikanti/d1038f406d8662d07b4d95c22ff008f9307043c0 (accessed Aug. 14, 2023).