Sensor for a wearable device for early detection of symptoms of possible neurodegenerative diseases
Auf einen Blick
We propose to develop and implement a sensor for a wearable
device with the functionality of early detection of symptoms
associated with the following neurodegenerative diseases:
Alzheimer's Disease (AD) and Parkinson's Disease (PD).
Specifically, we focus on the detection and quantification of
symptoms associated with the alteration of the circadian rhythm,
which have been reported to be indicative of AD and PD. In this
project, we will develop a sensor for a wearable device and
accompanying software for detection of differences in the circadian
rhythm between healthy individuals and persons affected by
neurodegenerative diseases under ambulatory, free living conditions at home.
The envisioned wearable device will incorporate physical sensors such as skin temperature and GreenTEG's proprietary heat flux sensors. In the predecessor project, 25392.2 PFLS-LS “Non-invasive core body temperature sensor for wearable sleep monitoring devices”, a similar configuration of wearable sensors was shown to allow accurate estimation of core body temperature (CBT). The circadian rhythm manifests itself in cyclic changes in CBT. Continuous and accurate CBT monitoring functionality in a continuously-worn consumer device will allow following the user's circadian rhythm. In this project, we will collect a database of circadian rythm recordings collected from both healthy individuals, and patients
affected by PD and AD. Using machine learning approach, we will build models of circadian rhythm for both groups of individuals.
In the intended use mode, the developed wearable device will collect circadian rhythm data from the user, and the extracted information will be compared with the developed models. Similarity with the AD/PD models will trigger a warning of a possible onset of neurodegenerative disease and an early warning of possible health condition will be issued, prompting the wearer to consult a healthcare expert for clinical diagnosis.