Predicting Cardiovascular Risk Using Machine Learning Models

EasyChair Preprint 14928

Abstract

Predicting Cardiovascular Risk Using Machine Learning Models

Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide, making early risk prediction crucial for prevention and treatment. Traditional risk prediction methods, such as the Framingham Risk Score, are limited by their static nature and inability to account for complex interactions among risk factors. In recent years, machine learning (ML) models have emerged as powerful tools to enhance the accuracy and efficiency of cardiovascular risk prediction. By leveraging large datasets, including clinical, genetic, lifestyle, and wearable device data, ML models can identify patterns and interactions that traditional methods may overlook.

This paper provides a comprehensive overview of the application of various ML techniques—such as logistic regression, random forests, support vector machines, and deep learning—in predicting cardiovascular risk. We discuss the data sources used in model development, including electronic health records, public health datasets, and real-time data from wearables. Additionally, we explore the challenges associated with implementing ML models, such as data quality, overfitting, ethical considerations, and clinical integration.

Keyphrases: cardiovascular risk prediction, deep learning, machine learning, predictive modeling, risk stratification

@booklet{EasyChair:14928,
  author    = {Docas Akinyele and Godwin Olaoye},
  title     = {Predicting Cardiovascular Risk Using Machine Learning Models},
  howpublished = {EasyChair Preprint 14928},
  year      = {EasyChair, 2024}}