Theoretical and Natural Science
- The Open Access Proceedings Series for Conferences
Theoretical and Natural Science
Vol. 35, 26 April 2024
Open
Access | Article
Predicting heart disease risk using machine learning: A comparative study of multiple algorithms
* Author to whom correspondence should be addressed.
Abstract
Heart disease has consistently ranked among the leading causes of morbidity and mortality globally, causing millions of deaths every year, but early diagnosis and medical intervention are considered effective ways to treat heart disease. Therefore, constructing predictive models through data analysis and machine learning algorithms that significantly improve the accuracy of early diagnosis and medical intervention could potentially save millions of lives. Using Kamil Pytlak’s dataset from Kaggle, which was originally derived from the 2020 annual CDC survey, this study explores the application of six common machine learning techniques in predicting heart disease. It focuses on data preprocessing, balancing the dataset via undersampling, and feature selection, narrowing down to 8 key risk factors from 17. Among the models—Logistic Regression, LDA, QDA, Boosted Tree, Random Forest, and K Nearest Neighbors—Logistic Regression outperformed others with a 74.6% accuracy and an 82.3% AUC. Despite the challenges in prediction accuracy, the results underline the significant potential of machine learning in early diagnosis and intervention, indicating a promising direction for enhancing public health management strategies against heart disease.
Keywords
Heart disease, Machine learning, Logistic regression, Predictive models
References
1. World Health Organization. Cardiovascular diseases (CVDs) [Internet]. World HealthOrganization. World Health Organization; 2021. Available from: https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
2. Amin MS, Chiam YK, Varathan KD. Identification of significant features and data mining techniques in predicting heart disease. Telematics and Informatics [Internet]. 2019 Mar [ cited 2020 Feb 1]; 36:82–93. Available from: https://www.sciencedirect.com/ science/article/pii/S0736585318308876
3. G A, Ganesh B, Ganesh A, Srinivas C, Dhanraj, Mensinkal K. Logistic regression technique for prediction of cardiovascular disease. Global Transitions Proceedings [Internet]. 2022 Jun 1 [ cited 2022 Jun 21 ]; 3(1):127–30. Available from: https://www.sciencedirect. com/science/article/pii/S2666285X22000449
4. Pytlak K. Personal Key Indicators of Heart Disease [Internet]. www.kaggle.com. Available from: https://www.kaggle.com/datasets/kamilpytlak/personal-key-indicators-of-heart-disease
5. ABBOTT RD. LOGISTIC REGRESSION IN SURVIVAL ANALYSIS. American Journal of Epidemiology. 1985 Mar;121(3):465–71.
6. Herman P, Prasad G, McGinnity TM, Coyle D. Comparative Analysis of Spectral Approaches to Feature Extraction for EEG-Based Motor Imagery Classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2008 Aug;16(4):317–26.
7. Mahmodi K, Mostafaei M, Mirzaee-Ghaleh E. Detection and classification of diesel-biodiesel blends by LDA, QDA and SVM approaches using an electronic nose. Fuel. 2019 Dec;258:116114.
8. Bhattacharyya S, Khasnobish A, Chatterjee S, Konar A, Tibarewala DN. Performance analysis of LDA, QDA and KNN algorithms in left-right limb movement classification from EEG data. 2010 International Conference on Systems in Medicine and Biology. 2010 Dec.
9. Speiser JL, Durkalski V, Lee WM. Random forest classification of etiologies for an orphan disease. Statistics in Medicine. 2015 Feb 28;34(5):887–99.
10. Speiser JL, Miller ME, Tooze J, Ip E. A comparison of random forest variable selection methods for classification prediction modeling. Expert Systems with Applications. 2019 Nov;134:93–101.
11. De’ath G. Boosted Trees for Ecological Modeling and Prediction. Ecology [Internet]. 2007 [cited 2023 Dec 20];88(1):243–51. Available from: https://www.jstor.org/stable/27651085
12. Lee S, Kim JC, Jung HS, Lee MJ, Lee S. Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea. Geomatics, Natural Hazards and Risk. 2017 Apr 10;8(2):1185–203.
13. Zhang S, Li X, Zong M, Zhu X, Wang R. Efficient kNN Classification With Different Numbers of Nearest Neighbors. IEEE Transactions on Neural Networks and Learning Systems. 2018 May;29(5):1774–85.
14. Bzdok D, Krzywinski M, Altman N. Machine learning: supervised methods. Nature Methods. 2018 Jan;15(1):5–6.
15. Zhang S, Li X, Zong M, Zhu X, Cheng D. Learning k for kNN Classification. ACM Transactions on Intelligent Systems and Technology. 2017 Apr 22;8(3):1–19.
Data Availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).
- Volume Title
- Proceedings of the 2nd International Conference on Modern Medicine and Global Health
- ISBN (Print)
- 978-1-83558-395-1
- ISBN (Online)
- 978-1-83558-396-8
- Published Date
- 26 April 2024
- Series
- Theoretical and Natural Science
- ISSN (Print)
- 2753-8818
- ISSN (Online)
- 2753-8826
- DOI
- 10.54254/2753-8818/35/20240925
- Copyright
- 26 April 2024
- Open Access
- This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited