Machine Learning Models for Early Detection of Cardiovascular Diseases: A Systematic Review

• Author(s): Damilola Osamika ; Bamidele Samuel Adelusi ; MariaTheresa Chinyeaka Kelvin-Agwu ; Ashiata Yetunde Mustapha ; Nura Ikhalea
• Paper ID: 1702780
• Page: 355-368
• Published Date: 30-06-2021
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 4 Issue 12 June-2021

Abstract

Cardiovascular diseases (CVDs) are the leading cause of morbidity and mortality worldwide, emphasizing the need for early detection to improve patient outcomes and reduce healthcare costs. Machine learning (ML) has emerged as a transformative tool for predicting and diagnosing CVDs by leveraging vast datasets, including electronic health records (EHRs), medical imaging, wearable device data, and genomic information. This systematic review explores the latest advancements in ML models for early CVD detection, highlighting key algorithms, data sources, and evaluation metrics. Supervised learning models such as Logistic Regression, Support Vector Machines (SVM), Random Forest, and Gradient Boosting have shown promise in risk prediction, while deep learning techniques, including Convolutional Neural Networks (CNN) for imaging analysis and Long Short-Term Memory (LSTM) networks for time-series data, enhance diagnostic accuracy. Additionally, feature selection and engineering methods improve the predictive performance of ML models by identifying critical risk factors from structured and unstructured data. Despite significant progress, challenges remain, including data quality issues, model interpretability, generalizability across diverse populations, and regulatory compliance with healthcare standards such as GDPR and HIPAA. Bias in ML models and concerns over patient privacy must also be addressed to ensure ethical deployment. Future research should focus on integrating ML with personalized medicine, federated learning for secure data sharing, and real-time monitoring through IoT-enabled devices. Developing explainable AI models and robust regulatory frameworks will further enhance clinical adoption and patient trust. This review underscores the potential of ML in revolutionizing early CVD detection and provides insights for researchers, clinicians, and policymakers to harness AI-driven innovations for improving cardiovascular health outcomes.

Keywords

Machine Learning, Cardiovascular Diseases, Early Detection, Deep Learning, Predictive Analytics, Healthcare AI, Electronic Health Records

Citations

IRE Journals:
Damilola Osamika , Bamidele Samuel Adelusi , MariaTheresa Chinyeaka Kelvin-Agwu , Ashiata Yetunde Mustapha , Nura Ikhalea "Machine Learning Models for Early Detection of Cardiovascular Diseases: A Systematic Review" Iconic Research And Engineering Journals Volume 4 Issue 12 2021 Page 355-368

IEEE:
Damilola Osamika , Bamidele Samuel Adelusi , MariaTheresa Chinyeaka Kelvin-Agwu , Ashiata Yetunde Mustapha , Nura Ikhalea "Machine Learning Models for Early Detection of Cardiovascular Diseases: A Systematic Review" Iconic Research And Engineering Journals, 4(12)