Summary of A Data Balancing Approach Towards Design Of An Expert System For Heart Disease Prediction, by Rahul Karmakar et al.
A data balancing approach towards design of an expert system for Heart Disease Prediction
by Rahul Karmakar, Udita Ghosh, Arpita Pal, Sattwiki Dey, Debraj Malik, Priyabrata Sain
First submitted to arxiv on: 26 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed study leverages machine learning techniques to enhance early detection and precise prediction of cardiac diseases. Researchers employed five ML methods – Decision Tree (DT), Random Forest (RF), Linear Discriminant Analysis, Extra Tree Classifier, and AdaBoost – to analyze the “Heart disease health indicators” dataset. To optimize model performance, various feature selection techniques were applied, including Sequential Forward FS, Sequential Backward FS, Correlation Matrix, and Chi2. Additionally, K means SMOTE oversampling was employed to enable further analysis. The findings indicate that ensemble approaches, particularly random forests, outperformed individual classifiers in predicting heart disease. Key predictors included smoking, blood pressure, cholesterol, and physical inactivity. Notably, the Random Forest and Decision Tree models achieved an accuracy of 99.83%. This study demonstrates the potential of machine learning models to improve heart disease prediction, particularly when incorporating ensemble methodologies. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Researchers used machine learning to help predict heart disease earlier and more accurately. They tested five different models on a big dataset about heart health. To make the models better, they tried four different ways to choose which features were most important. Then, they used something called oversampling to get even more accurate results. The best model was a type of forest that combined lots of smaller models together. It did really well at predicting heart disease and found out that smoking, high blood pressure, high cholesterol, and not being physically active were all big risk factors. |
Keywords
» Artificial intelligence » Decision tree » Feature selection » K means » Machine learning » Random forest
