CSE523 Machine Learning 2022 Abraca-data

Coronary Artery Disease Prediction using Machine Learning Classifiers

Problem Statement

The aim of this project is to train a best-fit supervised machine learning model based on the selected training dataset, that predicts whether an individual has 10-years future risk of Coronary Artery Disease, given the details (input features) of that individual.

The dataset is accessed from here

Introduction

Machine Learning is used in a variety of areas all around the world. The healthcare industry is no different. Coronary Artery Disease (CAD) is the formation of plaque in the arteries that provide your heart with oxygen-rich blood. Plaque produces a blockage, which can lead to a heart attack. CAD is an extremely widespread illness all over the world, it is impacted by several modifiable risk factors. Predictive models built using machine learning (ML) algorithms may assist doctors to diagnose CAD at an early stage and improve results and in turn, also save many lives.

Results

The results of this project are as follows:

Pre PCA Performance Measures

Pre PCA AUC/ROC for kNN

Pre PCA AUC/ROC for Logistic Regression

Post PCA AUC/ROC for kNN

Post PCA AUC/ROC for Logistic Regression

References

• [1] M. Giardina, F. Azuaje, P. McCullagh and R. Harper, "A Supervised Learning Approach to Predicting Coronary Heart Disease Complications in Type 2 Diabetes Mellitus Patients," Sixth IEEE Symposium on BioInformatics and BioEngineering (BIBE'06), 2006, pp. 325-331, DOI: 10.1109/BIBE.2006.253297.
• [2] H. H. Duan, “Applying supervised learning algorithms and a new feature selection method to predict coronary artery disease,” arXiv.org,03-Feb-2014[OnlineAvailable: https://arxiv.org/abs/1402.0459. [Accessed: 20-Mar-2022].
• [3]H. Vasquez-Gonzaga and J. Gutierrez-Cardenas, ‘Comparison of Supervised Learning Models for the Prediction of Coronary Artery Disease’, 2021 5th International Conference on Artificial Intelligence and Virtual Reality (AIVR). ACM, Jul. 23, 2021. doi: 10.1145/3480433.3480451
• [4]Dataset- Framinghamheartstudy.org. n.d. Cardiovascular Disease (10-year risk) | Framingham Heart Study. [online] Available at: https://framinghamheartstudy.org/fhs-risk-functions/cardiovascular-disease-10-year-risk/ [Accessed 27 March 2022].
• [5]K. P. Murphy, Machine learning: A probabilistic perspective. Cambridge, MA: MIT Press, 2021
• [6]A. Akella and S. Akella, ‘Machine learning algorithms for predicting coronary artery disease: efforts toward an open source solution’, Future Science OA, vol. 7, no. 6. Future Science Ltd, Jul. 2021. doi: 10.2144/fsoa-2020-0206
• [7]R. Gupta, I. Mohan, and J. Narula, ‘Trends in Coronary Heart Disease Epidemiology in India’, Annals of Global Health, vol. 82, no. 2. Ubiquity Press, Ltd., p. 307, Jun. 29, 2016. doi: 10.1016/j.aogh.2016.04.002.
• [8]M. P. Deisenroth, A. A. Faisal, and C. S. Ong, Mathematics for Machine Learning. Cambridge: Cambridge University Press, 2020. "Cardiovascular diseases", Who.int, 2022. [Online]. Available: https://www.who.int/health-topics/cardiovascular-diseases/#tab=tab_1. [Accessed: 20- Mar- 2022]
• [9]"Understanding the ROC Curve and AUC", Medium, 2022. [Online]. Available: https://towardsdatascience.com/understanding-the-roc-curve-and-auc-dd4f9a192ecb. [Accessed: 20- Mar- 2022]
• [10]R. Bharti, A. Khamparia, M. Shabaz, G. Dhiman, S. Pande, and P. Singh, ‘Prediction of Heart Disease Using a Combination of Machine Learning and Deep Learning’, Computational Intelligence and Neuroscience, vol. 2021. Hindawi Limited, pp. 1–11, Jul. 01, 2021. doi: 10.1155/2021/8387680.
• [11]S. Kumar, "Chi-Square Test for Feature Selection in Machine learning", Medium, 2022. [Online]. Available: https://towardsdatascience.com/chi-square-test-for-feature-selection-in-machine-learning-206b1f0b8223. [Accessed: 20- Mar- 2022].
• [12]“Coronary artery disease: Causes, symptoms, diagnosis & treatments,” Cleveland Clinic. [Online]. Available: https://my.clevelandclinic.org/health/diseases/16898-coronary-artery-disease. [Accessed: 20-Mar-2022].
• [13]Heart.org, 2022. [Online]. Available: https://www.heart.org/-/media/phd-files-2/science-news/2/2021-heart-and-stroke-stat-update/2021_heart_disease_and_stroke_statistics_update_fact_sheet_at_a_glance.pdf?la=en. [Accessed: 20- Mar- 2022]
• [14]Y. Elor and H. Averbuch-Elor, "To SMOTE, or not to SMOTE?", arXiv.org,2022.[Online].Available:https://doi.org/10.48550/arXiv.2201.08528. [Accessed: 24- Apr- 2022.