Identifying Health Factors Leveraging Machine Learning to Uncover Stronger Predictors of Cardiovascular Disease: Clinical Metrics vs. Self-Reports

DOI

10.2991/978-94-6239-674-6_23How to use a DOI?

Keywords

Cardio Vascular Disease; Artificial Intelligence; Health Care

Abstract

Cardio Vascular Disease (CVD) are the major cause of death worldwide; with increasing numbers of individuals in recent days trust on internet-based health quizzes and social media for self-diagnosis. We prove that clinical examination features (blood pressure, cholesterol, glucose levels) will be significantly more predictive of cardiovascular disease than self-reported objective and subjective health information when analyzed using machine learning algorithm. To prove this, we analyzed the publicly available 70,000 clinical records of cardiovascular disease dataset using WEKA’s Random Forest implementation. We segregated the dataset into three feature subsets: all features (n = 11), examination-only features (n = 4), and objective plus subjective features excluding examination data (n = 7). Our results supported our hypothesis, showing that examination-only features achieved 72.26% accuracy in predicting CVD, significantly outperforming self-reported data alone (58% accuracy). The complete feature set accomplished the highest accuracy (83%). These findings emphasis that clinical examination features play a crucial role in CVD diagnosis. In contrast, internet-based health assessments that rely solely on self-reported data show clear limitations in predicting cardiovascular disease. Therefore, to reduce risk and support early detection, individuals are strongly advised to have an annual health check every year.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sandhya Dharshini Sasikumar
AU  - Kavithaa Suresh Kumar
AU  - Siva Sivatha Sindhu
PY  - 2026
DA  - 2026/05/28
TI  - Identifying Health Factors Leveraging Machine Learning to Uncover Stronger Predictors of Cardiovascular Disease: Clinical Metrics vs. Self-Reports
BT  - Proceedings of the International Conference on Sustainable Computing and Artificial Intelligence (ICSCAI 2025)
PB  - Atlantis Press
SP  - 265
EP  - 272
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-674-6_23
DO  - 10.2991/978-94-6239-674-6_23
ID  - Sasikumar2026
ER  -