Measurement instrument for assessing functional abilities of elderly people with and without dementia using a video monitoring system

This study presents the application of computer vision to health monitoring elderly people, improving the valuable diagnostic of person suffering from dementia symptoms. We propose a framework based on a video monitoring system (VMS) for assessing physical and cognitive abilities of elderly people during a clinical experiment. Recording sessions were divided into two steps: the first for assessing the gait, and the second for assessing cognitive abilities in daily life situations. Results of gait assessment show that patients with Alzheimer Disease (n=16, age =76.7years±4.0, %/W=11(68.75%)) had lower both walking speed and step length than Healthy Control (HC) participants (n=10, age=73.9years±4.5, %/W=5(50%)). From quantitative and qualitative data extracted from the VMS during the second step, a VMS-functional index was computed, validated and compared with current clinical rating scales. Results show that VMSfunctional index was correlated strongly with standard cognitive and functional measurements (MMSE, Rho=.81, and IADL-E scores, Rho=-.65), thus accurately differentiating from healthy control (HC) participants. Results of this pilot study are promising, and need to be substantiated with a larger sample, and in another assessment room for assessing their reproducibility. KeywordsGerontechnology; Alzheimer Disease; Evaluation tool.

[1]  Weimin Huang,et al.  Sensor based micro context for mild dementia assistance , 2010, PETRA '10.

[2]  P. S. Mathuranath,et al.  Instrumental activities of daily living scale for dementia screening in elderly people , 2005, International Psychogeriatrics.

[3]  Friedrich Foerster,et al.  Motion pattern and posture: Correctly assessed by calibrated accelerometers , 2000, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[4]  Alex Pentland,et al.  Auditory Context Awareness via Wearable Computing , 1998 .

[5]  Matthai Philipose,et al.  Common Sense Based Joint Training of Human Activity Recognizers , 2007, IJCAI.

[6]  S. Folstein,et al.  "Mini-mental state". A practical method for grading the cognitive state of patients for the clinician. , 1975, Journal of psychiatric research.

[7]  Irfan A. Essa,et al.  Exploiting human actions and object context for recognition tasks , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  P. Robert,et al.  Automatic video monitoring system for assessment of Alzheimer's disease symptoms. , 2012, The journal of nutrition, health & aging.