We aim to reduce the burden of heart disease for patients, healthcare workers and society by the early detection of heart disease deterioration. We shall develop a data collection platform integrating off-the-shelf and state of the art self-tracking technologies to enable patients:
To make measurements at home which would otherwise require visiting the clinic
To collect longitudinal data pertaining to daily life activity, emotions, and other relevant aspects.
To ensure higher adherence in self-tracking through gamification.
We shall develop and evaluate novel diagnostic and prognosis methods in two trials, each addressing groups where improvements are readily obtainable and highly relevant:
For elderly heart patients, we strive to reduce re-hospitalization rates, currently leading to serious health deterioration and substantial costs.
For all comers at cardiac outpatient clinics, to lower costs and improve the quality of diagnosing heart disease.
The mainstay of our two trials is two-fold:
A lasting and connectable data set for studying performance of a variety of digitalized old and new techniques in relation to other health records. Our heterogeneous data set comprises of electrocardiography, audio files derived from stethoscopes, activity levels measurement from wrist-worn devices, data of electronic nose, and self-report data and sensor data collected using IoT technologies, which pertain to water consumption, sleep patterns, experience sampling of feelings, physiological data relating to emotions (galvanic skin response and face expression recordings) and the well-being of the patient.
Novel analysis and early diagnosis methods that rely on this heterogeneous data set.
- e-Science Center
- Hangzhou BOBO
- Cardiron B.V.
- Heart Sciences
- SBTL
- Games Solutions Lab
- Reinier de Graaf Gasthuis
- Werkgroep Cardiologische Centra Nederland:
- Smart Building Tech Lab B.V.
- Game Solutions Lab
- Onmi
Nikitha is participating in the renowned Physionet Challenge of 2021, The challenge poses a question, if multiple Cardiac Arrhythmias can be classified using the signals acquired from minimal leads of Electrocardiography. She has successfully made a submission in the first round of the challenge and is working towards the next round of the challenge. She has developed algorithms for classification of cardiac Arrhythmia using Machine learning techniques.