Development of cardiovascular disease prediction model with non-invasive biomarkers

There is existing literature about the correlation between Advanced glycation end-product (AGE) and cardiovascular disease (CVD) occurrence and the use of Heart rate variability (HRV) in predicting CVD risk factors. There is also extensive research in developing Machine Learning (ML) models to predict CVD from laboratory and detailed variables that professionals can gather only in controlled/laboratory environments. The gap we aim to fill is developing predictive models for CVD from non-invasive AGE and HRV sensor data, along with questionnaire data.