A study on dementia detection method with stroke data using anomaly detection

Increasing the number of elderly persons who have dementia, this is one of the severe social problems in Japan. According to the report published by the Ministry of Health, Labor and Welfare, the number of elderly persons with dementia will be around five million in 2015. This report indicates that early detection and prevention of dementia is essential. From viewpoints of early detection of dementia, the most problem is the limitation of test contents and the difficulty of taking a dementia check test on a daily basis. To solve these problems, the authors focus on drawing test using a tablet terminal to develop a dementia detection system, which can be adapted to various drawing contents including digits, characters, and pictures for increasing of dementia screening opportunity. It is, however, difficult to collect sufficient data to build the system because there are many subtypes of dementia. From this background, this position paper discusses an unsupervised anomaly detection method using healthy data only, and also aim to propose a system that gives the probability of being dementia (or other sicknesses) based on the differences from the data of healthy cases. As the first step of this study, we discuss the possibility of a dementia detection method using Variational Autoencoder.

[1]  Rossitza Setchi,et al.  Cascade classification for diagnosing dementia , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[2]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[3]  Koji Yamamoto,et al.  A Study on Conversational Content Recognition Method Using Japanese WordNet for Robot-Assisted Therapies , 2012, J. Adv. Comput. Intell. Intell. Informatics.

[4]  D. Aarsland,et al.  A systematic review of prevalence studies of dementia in Parkinson's disease , 2005, Movement disorders : official journal of the Movement Disorder Society.

[5]  Y. Mitsuyama.  Presenile dementia with motor neuron disease in Japan: clinico-pathological review of 26 cases. , 1984, Journal of neurology, neurosurgery, and psychiatry.

[6]  S. Albert,et al.  Cognitive Status and Physical Function in Older African Americans , 2008, Journal of the American Geriatrics Society.

[7]  Ming-Jang Chiu,et al.  Behavioral and psychologic symptoms in different types of dementia. , 2006, Journal of the Formosan Medical Association = Taiwan yi zhi.

[8]  Rossitza Setchi,et al.  Dementia Detection Using Weighted Direction Index Histograms and SVM for Clock Drawing Test , 2016, KES.

[9]  Sungzoon Cho,et al.  Variational Autoencoder based Anomaly Detection using Reconstruction Probability , 2015 .

[10]  Lovekesh Vig,et al.  Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[11]  Rossitza Setchi,et al.  Feature Selection based on Information Theory in the Clock Drawing Test , 2013, KES.

[12]  Kenji Kimura,et al.  Examination of Practicability of Communication Robot-Assisted Activity Program for Elderly People , 2011, J. Robotics Mechatronics.

[13]  Rossitza Setchi,et al.  Segmentation of Clock Drawings Based on Spatial and Temporal Features , 2015, KES.

[14]  Justin Bayer,et al.  Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series , 2016, ArXiv.

[15]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[16]  Rossitza Setchi,et al.  Clock Drawing Test Digit Recognition Using Static and Dynamic Features , 2016, KES.