Abstract

With the aging of the global population, the number of people with chronic diseases is also increasing, and cardiac disease has become the main cause of human deaths worldwide. In this study, we propose an integrated detection system for measuring the blood pressure (BP), blood glucose (BG), blood lipids (BL), and heart rate (HR). Next, we employ five commonly used machine-learning-based (ML-based) data classification methods, namely, support vector machine (SVM), random forests (RF), k-nearest neighbors (KNN), XGBoost, and LightGBM, for predicting chronic cardiac disease. These five classification methods use the data of BP, BG, BL, and HR, to predict the chronic cardiac disease, whose result shows that RF and KNN have the highest prediction accuracy (88.52%) as compared to the new ML methods, such as XGBoost and LightGBM. In addition, the proposed system should serve as a platform for the long-term detection and tracking of users’ physical health.

Keywords:

Chronic disease; Cardiac disease; Machine learning; Data analysis

Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License

Share

COinS
 
Aug 11th, 12:00 AM

A Health Care Platform Design: Applying Novel Machine Learning Methods to Predict Chronic Cardiac Disease

With the aging of the global population, the number of people with chronic diseases is also increasing, and cardiac disease has become the main cause of human deaths worldwide. In this study, we propose an integrated detection system for measuring the blood pressure (BP), blood glucose (BG), blood lipids (BL), and heart rate (HR). Next, we employ five commonly used machine-learning-based (ML-based) data classification methods, namely, support vector machine (SVM), random forests (RF), k-nearest neighbors (KNN), XGBoost, and LightGBM, for predicting chronic cardiac disease. These five classification methods use the data of BP, BG, BL, and HR, to predict the chronic cardiac disease, whose result shows that RF and KNN have the highest prediction accuracy (88.52%) as compared to the new ML methods, such as XGBoost and LightGBM. In addition, the proposed system should serve as a platform for the long-term detection and tracking of users’ physical health.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.