Research Article
SmartHeart RF: A Machine Learning Approach to Cardiovascular Disease Detection in Obesity
@INPROCEEDINGS{10.4108/eai.19-12-2025.2362620, author={Abhishek Khanna and Sapna Sapna and Arjun Puri}, title={SmartHeart RF: A Machine Learning Approach to Cardiovascular Disease Detection in Obesity}, proceedings={Proceedings of the 1st International Conference on Computational Techniques in Data Science, IICTDS 2025, 19-20 December 2025, Chandigarh, India}, publisher={EAI}, proceedings_a={IICTDS}, year={2026}, month={11}, keywords={Cardiovascular disease (CVD) obesity Random Forest Machine Learning age height weight ap_high ap_low}, doi={10.4108/eai.19-12-2025.2362620} }- Abhishek Khanna
Sapna Sapna
Arjun Puri
Year: 2026
SmartHeart RF: A Machine Learning Approach to Cardiovascular Disease Detection in Obesity
IICTDS
EAI
DOI: 10.4108/eai.19-12-2025.2362620
Abstract
Cardiovascular disease (CVD) is considered to be the most important reason of death worldwide, resulting enumerous deaths every passing year. Addressing this issue requires a comprehensive research approach. The aim of this paper is to highlight the key mechanisms and variables involved in assessing CVD risk associated with obesity. When these parameters are integrated into established risk assessment tools such as random forest machine learning techniques and combined with modern statistical and machine-learning models, these parameters provide more reliable and accurate prediction levels for individuals aged 10 and above. Additionally, the imaging dataset considered for the PERST study provides deeper insights into cardiac structure and function, complementing traditional risk assessment strategies. Furthermore, learning from the present study shows that lifestyle components such as diet, physical activity, and other associated parameters, including stress levels, play an important role in shaping the CVD risk profile. Finally, the present study suggests that long-term monitoring may help track changes in these factors and aid in early intervention to reduce CVD risk in people with obesity. Overall, this integrated approach that brings together clinical data, predictive models, and lifestyle analysis provides a robust framework to predict and manage obesity-related CVD risk and ultimately contributes to improved cardiovascular health outcomes.