Use of ICT in dementia from assessment to intervention: The Taiwanese contribution to the SafEE project

Purpose: SafEE (Safe and Easy Environment for Alzheimer's disease) is a French-Taiwanese collaborative project on technologies for health and autonomy, aimed at improving safety, autonomy and quality of life of older people diagnosed with Alzheimer's disease (AD) and related disorders. The Alzheimer's disease population is growing dramatically. In 2006, 26.6 million people were afflicted by AD, and the number could quadruple by 20501. Patients with AD and dementia, gait disorders, cognitive frailty, and memory impairments will increasingly become more impaired as the patients' illnesses progress^2,3. Even worse is that AD cannot be cured, and patients rely on the drugs only to postpone the symptoms. Hence, the SafEE project focuses on specific clinical targets in three domains: behavior, motricity and cognition, merges assessment and non-pharmacological help/interventions; and proposes easy ICT device solutions for the end users. Method: SafEE is a 3-year project involving industrial and university partners. In this project, an ICT-based behavior analysis platform had been developed. This platform is able to detect, recognize, and assess walking/balancing capabilities, orientation and procedural memory. A device consisting of a triaxial accelerometer, a uniaxial gyroscope, and a biaxial gyroscope was developed to collect the signals while participants walked and took some balance tests. In this project, participants are patients with Alzheimer's disease and healthy people. We asked participants to complete single-task and dual-task activities while walking. The balance tests included four subtests: (i) basic balance tests, (ii) single-leg balance tests, (iii) Timed Up-and-Go test, and (iv) repeated chair stands test. In the basic balance tests, participants were asked to engage in specific movements, including the side by side stand and semi-tandem stand. Each of the tests was completed open eyed and close eyed. In the single-leg balance tests, participants needed to stand on one foot (right and left, in respective tests) with open eyes, for 10 seconds or less if the patient encountered difficulties. In the Time-Up and Go Test (TUGT), participants were asked to stand up from an armchair, walk 3 meters, turn, walk back, and sit down on the armchair. In the repeated chair stands test, the examiner asked the participant to make the first chair stand, from sit to stand position without using their arms. The examiner then asked the participant to do the same action 5 times in a row. Results & Discussion: Preliminary results show that an automated detection algorithm can accurately detect the patients' stride and gait parameters (e.g., stride length, stride frequency) using the wearable device we developed. The results also show that the AD patients have poor performance in the semitandem stand (both the left foot in front and right foot in front). In the repeated chair stands test and TUGT, AD patients needed more time to complete the tests than healthy people.