Early Detection Approaches for Cognitive Impairment in Aging Population

Budapest Budapest University of Technology and University of Technology and Economics Economics 04 Dec, 2015

Motivation Possible approaches Conceptual model Challenges How to assess the cognitive state Proof of the concept ICT architecture and components Conclusion and future work 2 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

Primary Impairment (MCI) Dementia is one of the main causes of dependency MCI: conversion rate to dementia is much higher Detection and treatment in the early phase can delay the progression Hard to identify when the natural decline becomes abnormal MCI is not a specific disease problems with memory, attention, visuospatial skills (the ability to interpret objects and shapes) 3 Primary g goal Impairment (MCI) oal: early detection : early detection of Mild Cognitive (+ of Mild Cognitive (+ training training) ) WHY WHY? ? planning language 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

Cognitive tests: only when there are clear signs of cognitive deficit early detection is rare Traditional, validated, paper-based clinical tests require specialist centres and highly trained professionals Growing special monitoring and training purposes interest computer in the games development for of cognitive 4 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

Game Adapting well-known, popular games Transforming special clinical tests (Paired Associates Learning, Corsi block-tapping) Developing new games specially designed for this purpose Monitoring policy: Voluntary Controlled Game development development policy policy: : Monitoring policy: 5 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

Assessment On an absolute scale O Only Reference Comparison to a reference group (inter- personal) Comparison reference Assessment of of the the mental mental state state nly significant Reference for significant change for change change is is to change detection to be be detected detected detection Comparison reference performance to to a a previously of the previously the same measured same person measured person performance of 6 22 May, 2015

With regular but voluntary use of computer games developed or modified specifically for older adults, we may be able to measure the mental changes and tendencies over time in an entertaining way. 7 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

Typical performance series of a player measured with a given computer game 8 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

How using computer games? How to cope with the typically heavy caused measurement environment? How to motivate long run? How to compare different games, which is basically a special sensor-fusion problem? to measure measure cognitive cognitive performance performance heavy noise (home) noise by the uncontrolled motivate people to take part in the compare performance performance shown in 9 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

entertainment power (contradictory requirements ) capability measurement NUM. OF NUM. OF CORRECT LOGS (NO GIVEN UP) MOST FREQUENT SUBTYPE NUM. OF GAMELOGS OPENED (June 01, 2014- March 31, 2015) NUM. OF PLAYERS (MOST FREQ.SUBTYPE) STDPlaytime / AVGPlayTime (BASED ON TOP 10 PLAYERS) GAMELOGS (GIVEN UP NOT INCL.) (June 01, 2014- March 31, 2015) NUM. OF SUBTYPES PLAYED GIVEN UP GIVEN UP % GAME PLANAR 17 495 1 535 8.8 15 960 10 10 736 225 0.84 MEMORY 16 408 1 700 10.4 14 708 22 7 864 257 0.30 65 WGUESS 14 194 629 4.4 13 564 8 167 162 0.57 BLOCKS 10 415 830 8.0 9 585 5 6 358 202 0.49 CONNECT HIDDEN PUZZLE ROTATE FREECELL 10 276 14 563 9 214 7 504 16 059 1 519 6 002 1 650 719 9 768 14.8 41.2 17.9 9.6 60.8 8 757 8 561 7 564 6 785 6 291 12 1 10 18 1 6 079 8 561 1 379 5 662 6 290 167 227 2 198 132 0.65 0.65 ? 0.69 0.39 10 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

H Heavy Outliers omitted. Short term fluctuations between environmental disturbances, by tiredness, etc. ) Short-term independent random variables Performance measured on a reference compared to performance on the current comparison performance) 11 eavy noise noise present (usually caused by interrupts) are (random puzzles, differences minor consecutive fluctuations: zero-mean, stable reference set current set on set will be set (no single is based game 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

Performance measure of a player during nearly one year Noisy distribution of reference and current data sets are to be compared 12 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

Lilliefors test: the normality hypothesis is rejected Nonparametric Kolmogorov-Smirnoff signed-rank test, etc. statistical hypothesis test, tests: two-sample Wilcoxon 13 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

No direct proof - due to the long time needed to detect a critical cognitive change Studies have shown that MCI patients performed poorly on Paired Associates Learning (PAL) computerized cognitive test. Players were asked to perform it. The performance shown in the computer games correlates to their performance measured by the PAL test. 14 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015

M3W playground with games M3W playground with games 15 22 May, 2015

16 22 May, 2015

https://m3w https://kognito.eu https://m3w- -project.eu https://kognito.eu project.eu 17 22 May, 2015 ICT4AgeingWell ICT4AgeingWell Conference Conference, 20 , 20- -22 May, 2015 22 May, 2015