Predicting Cardiovascular Events Through Skin Blood Flow Analysis

Cardiovascular events, such as heart attacks, strokes, and heart failure, pose a significant global health challenge. Early detection is crucial for reducing mortality and improving patient outcomes. Traditional predictive models primarily focus on generalized clinical parameters like cholesterol levels, blood pressure, and lifestyle factors. While these indicators are useful, they often overlook the role of microvascular function, which can provide deeper insights into cardiovascular health. This study explores the predictive power of skin blood flow analysis as a non-invasive biomarker for assessing cardiovascular risk. Utilizing K-Means, Hierarchical Clustering, Gaussian Mixture Model (GMM), and Self Organizing Maps (SOMs) on photo-plethysmography (PPG) and electrocardiography (ECG) data, this study examines variations in skin perfusion and explores their correlation with systemic vascular health. By leveraging machine learning algorithms, the proposed model aims to identify early warning patterns that could indicate cardiovascular events. The integration of microvascular perfusion data with predictive analytics enhances early diagnosis which are noninvasive and inexpensive.