Potential of piano playing as digital biomarker for detecting prodromal phases of dementia and feasibility of computational model establishment for its better understanding and predictive markers development
There are limited availabilities of disease course-altering drugs for early-stage Alzheimer’s disease at this time. One probable reason may be the difficulties of stratifying and recruiting the cohort with those who are healthy and/or with prodromal stages of Alzheimer’s dementia to effectively test the drug with. It can be hypothesized that the traditional biomarkers may be more surrogate markers-like when it comes to cognitive functionalities, rather indicating the correlations of notable disease characteristics to the cognitive symptoms but not direct quantification of cognitive functions for evaluation. Cognitive functionalities are also fluid and can be easily impacted by environment and other contributing factors. Thus, specific physiological markers and their ranges may not explain the drug’s cognitive endpoints in full. While there are some gold standard cognitive tests, their sensitivity in detecting and evaluating prodromal stages of dementia is relatively low. It is crucial to establish easy-to-use and self-administered digital biomarkers which are capable of quantifying and measuring actual cognitive functionalities for successful stratification of the testing cohort, evaluating treatment response and monitor changes over long term.

Ipsilon System is a gamified cognitive screening and monitoring tablet application targeted for prodromal stages of dementia, utilizing simplified music notes as visuospatial stimuli to elicit motor responses. It collects time-stamped finger tapping response and its accuracy to generate parameters for assessment. Single cognitive task of visuospatial-motor encoding effectively activates the cortico-basal ganglia- thalamo-cortical circuit which has close relationship with motor control and cognition and can generate valuable data over cognitive domains often impacted among early dementia patients. We will discuss about the feasibility of music playing as cognitive task, validations of Ipsilon System as digital biomarker candidate thus far and potential computational model establishment for better understanding of dementia and predictive markers development in the future.
Date: 15 February 2022, 15:00
Venue: Venue to be announced
Speaker: Yayoi Sakaki, CEO (Project Ipsilon B.V.)
Organising department: Department of Psychiatry
Organiser: Dr Andrey Kormilitzin (University of Oxford)
Organiser contact email address: andrey.kormilitzin@psych.ox.ac.uk
Host: Dr Andrey Kormilitzin (University of Oxford)
Part of: Artificial Intelligence for Mental Health Seminar Series
Booking required?: Not required
Booking email: andrey.kormilitzin@psych.ox.ac.uk
Audience: Public
Editor: Andrey Kormilitzin