“Wearable tech itself isn’t very crucial, but algorithms are’’
ACCELStars, a medical sleep tech startup from the University of Tokyo, Japan is developing the world’s highest level of sleep measurement technology and treatment support services for psychiatric disorders, neurodegenerative diseases, and developmental disorders that are known to be accompanied by sleep disorders. In an email interaction with BioSpectrum Asia, Masayuki Asano, Executive Officer of ACCELStars discussed more about the company and wearable technology for the diagnosis of sleep disorders. Edited excerpts; How does ACCELStars approach the science of sleep disorders?
You must undergo a PSG test (polysomnography) for one night in a hospital to detect sleep with 100 per cent accuracy. ECG, diaphragmatic and nasal breathing, as well as EEG measurement, are all included in PSG. So our goal instead, is to use wearable technology on the wrist to detect sleep disturbances. Today, the most precise sleep detection is available for home sleep testing, health promotion, and diagnosing disorders that may affect sleep. Our device would monitor both the diagnosis and treatment of sleep and dyskinesia. We are also developing a device for sleep apnea syndrome and schizophrenia.
Please give us an overview of the wearable technology that ACCELStars is developing to detect sleep disorders and how they work.
Arm acceleration data have been used to measure sleep-wake rhythmicity. Although several methods have been developed for the accurate classification of sleep-wake episodes, a method with both high sensitivity and specificity has not been fully established. We have developed an algorithm, named ACceleration-based Classification and Estimation of Long-term sleep-wake cycles (ACCEL) that classifies sleep and wake episodes using only raw accelerometer data, without relying on devicespecific functions. The algorithm uses a derivative of triaxial acceleration (jerk), which can reduce individual differences in the variability of acceleration data.
How important are wearables in this space?
The development of sleep, mental, and neurodegenerative illness-related disease detection took over fifty years. We might be able to strike in the sleep field, though, now that the technology and censors have been established. Additionally, wearable technology itself isn’t very crucial, but algorithms that go into it are.
What are the challenges in developing such solutions?
One of the major challenges is applying it as a medical device for regulatory approval. The other one is expanding outside of Japan.