Heart and respiratory rate is an important indicator for the health status of preterm infants. It can help identify potential health risks like bradycardia which is caused by slow heart rate, in early stages of life. Current methods of obtaining heart rate are rather intrusive due to it requiring multiple devices attached to the infant for a long period of time, which will cause skin damage, especially in the delicate skin of infants. To tackle this problem, we propose to predict heart rate with machine learning algorithms, Random Forest Regression and Support Vector Regression, with respiratory rate and time as an input, considering its close relationship with heart rate.
Dataset used in this project is the Preterm Infant Cardio-Respiratory Signals Database from Physionet.