New publication in a collaborative study with the University Politehnica of Bucharest
We are happy to announce a new publication in a collaborative study with the University Politehnica of Bucharest, Romania. This is the first step in a larger work progressing in the next months/years.
Main content
Heart rate response to physical activity is widely investigated in clinical and training practice, as it provides information on a person鈥檚 physical state. For emerging digital phenotyping approaches, there is a need for individualized model estimation.聽In this study, we propose a zero-poles model and a data-driven evolutionary learning method for identification. We also perform a comparison with existing first and second order models and gradient descent identification methods.
Highlights
- Zero-poles heart rate dynamic models provide clinically meaningful digital biomarkers.
- Evolutionary learning shows excellent results for raw data model identification.
- Heart rate dynamic analysis offers insights into physiological states.
- New digital biomarkers for heart rate response are compatible with wearable devices.
The proposed model is based on a five-phase description of heart rate dynamics. Data was collected from 30 healthy participants using a treadmill and a thoracic sensor in two protocols (static and dynamic), for increasing and decreasing activity. Results show that the zero-poles model is a good fit for heart rate response to exercise (Pearson鈥檚 coefficient p > .95), while first and second order models are also suitable (p > .92). The evolutionary learning method shows excellent results for fast model identification, in comparison with least-squares methods (p >.03). We surmise that the parameters of investigated linear dynamic models make good candidates for digital biomarkers and continuous monitoring.
See the article: