On Modeling the Cardiovascular System and Predicting the Human Heart Rate under Strain

What is it about?

Heart rate models are often used to simulate heart rate or to predict only a few seconds into the future. In this paper, we conduct a joint evaluation of existing approaches to model the cardiovascular system under a certain strain, and compare their predictive performance. For this purpose, we investigated some analytical models as well as some machine learning approaches in two scenarios: prediction over a certain time horizon into the future, and estimation of the relation between work load and heart rate over a whole training session.

Featured Image

Why is it important?

Learning more about heart rate and the ability to predict heart rate is highly important to aid in training and to avoid overstrain. There are many models for heart rate simulation out there, but are usually presented using new data. In this paper, we used a bunch of data from running protocol tests to really compare models and to see how they behave on the same data set each. Furthermore, we compared the usefullness in heart rate prediction of mathematical / analytical models to machine learning approaches over different shoirt time horizons as well as over a complete training.