Machine Learning-Based Predictive Models for Cardiovascular Risk Assessment in Data Analysis - Data Processing, Model Development, and Clinical Implications

Aug 5, 2026

Cardiovascular diseases remain a major source of morbidity and mortality, making timely identification of at-risk individuals critical for prevention and effective interventions. This research develops machine learning approaches to predict initial cardiovascular risk using patient demographics, medical history, lifestyle factors, and clinical indicators such as blood pressure, cholesterol, and glucose. Multiple algorithms—including logistic regression, decision trees, random forests, linear SVC, naive Bayes, and neural networks—are trained and evaluated with accuracy, precision, recall, F1 score, and AUC-ROC. Early high-risk detection supports preventive strategies and personalized healthcare, aiming to reduce CVD burden.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Introduction

Research Objectives and Methods

Dataset preprocessing and analysis

Feature selection and engineering

Model training and optimization

Performance evaluation metrics

Singarathnam, Dharshika, Ganesan, Swathi ORCID: [https://orcid.org/0000-0002-6278-2090](https://orcid.org/0000-0002-6278-2090) , Pokhrel, Sangita ORCID: [https://orcid.org/0009-0008-2092-7029 and](https://orcid.org/0009-0008-2092-7029 and)[ ](https://orcid.org/0009-0008-2092-7029 and)Somasiri, Nalinda ORCID: [https://orcid.org/0000-0001-6311-2251](https://orcid.org/0000-0001-6311-2251)[ ](https://orcid.org/0000-0001-6311-2251)(2023) Machine learning-based predictive models for cardiovascular risk assessment in data analysis, model development, and clinical implications. International Journal of Recent Advances in Multidisciplinary Research, 10 (10) . pp. 9084-9089. Downloaded from: [http://ray.yorksj.ac.uk/id/eprint/9066/](http://ray.yorksj.ac.uk/id/eprint/9066/) The version presented here may differ from the published version or version of record. If you intend to cite from the work you are advised to consult the publisher's version: [https://www.ijramr.com/sites/default/files/issues-pdf/4750.pdf](https://www.ijramr.com/sites/default/files/issues-pdf/4750.pdf) Research at York St John (RaY) is an institutional repository. It supports the principles of open access by making the research outputs of the University available in digital form. Copyright of the items stored in RaY reside with the authors and/or other copyright owners. Users may access full text items free of charge, and may download a copy for private study or non-commercial research. For further reuse terms, see licence terms governing individual outputs. Institutional Repository Policy Statement RaY Research at the University of York St John For more information please contact RaY at [ray@yorksj.ac.uk](ray@yorksj.ac.uk) | [www.ijramr.com](www.ijramr.com)
International Journal of Recent Advances in Multidisciplinary Research | | --- | | Vol. 10, Issue 10, pp.9084-9089, October, 2023 | | | RESEARCH ARTICLE | | | --- | | | MACHINE LEARNING-BASED PREDICTIVE MODELS FOR CARDIOVASCULAR RISK ASSESSMENT IN DATA ANALYSIS, MODEL DEVELOPMENT, AND CLINICAL IMPLICATIONS Dharshika Singarathnam, *SwathiGanesan, Sangita Pokhrel and Nalinda Somasiri Department of Computer Science, York St John University, United Kingdom ABSTRACT Cardiovascular diseases (CVDs) remain a leading global cause of morbidity and mortality. Timely identification of individuals at risk is paramount for effective interventions and prevention. This study endeavors to develop machine learning approaches for predicting the initial cardiovascular risk level analyzing the dataset encompassing patient demographics, medical history, lifestyle factors, and clinical indicators. Patient characteristics, including age, gender, diabetes or hypertension presence, smoking status, and physical activity level, along with medical indicators such as blood pressure, cholesterol, and glucose levels, are considered. Diverse machine learning algorithms—logistic regression, decision tree classifier, random forests, linear SVC, naive bayes, and neural network—are employed to train and optimize predictive models. Evaluation metrics (accuracy, precision, recall, F1 score, and AUC-ROC) assess model performance. Accurate risk prediction models hold significance in aiding healthcare decisions, optimizing resource allocation, and enhancing patient outcomes. Identifying high-risk individuals early enables preventive strategies and personalized interventions, reducing the CVD burden. Study objectives encompass dataset preprocessing, exploratory analysis, feature selection and engineering, model training and optimization, and performance evaluation. Findings contribute to cardiovascular risk prediction, presenting a robust model for accurate risk assessment and improved patient outcomes. INTRODUCTION Cardiovascular diseases (CVDs) posed a significant global health burden, responsible for numerous deaths and disabilities worldwide (Roth et al., 2017) . According to the World Health Organization (WHO), C

FAQs

What is the main goal of the study?

To develop machine learning approaches that predict an individual’s initial cardiovascular risk level using patient characteristics and clinical indicators.

Which machine learning algorithms are used to train the predictive models?

Logistic regression, decision tree classifier, random forests, linear SVC, naive Bayes, and neural network models are employed.

How is model performance evaluated in this research?

Performance is assessed using accuracy, precision, recall, F1 score, and AUC-ROC metrics.

Aug 5, 2026

Upload by Olivia Brown