Design of tablet-based dementia examination system
碩士 === 國立臺北科技大學 === 電機工程研究所 === 105 === Aging is one of the main reasons in Taiwanese society for increasing dementia in elderly’s people. By the report of global dementia investigation Society, 46 million people around the world were dementia patients in the year of 2016. In Taiwan, more than 260,0...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2017
|
Online Access: | http://ndltd.ncl.edu.tw/handle/s8zv59 |
id |
ndltd-TW-105TIT05442042 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-105TIT054420422019-05-15T23:53:23Z http://ndltd.ncl.edu.tw/handle/s8zv59 Design of tablet-based dementia examination system 植基於平板電腦之失智症檢測系統設計 Sheng Chen 陳聖 碩士 國立臺北科技大學 電機工程研究所 105 Aging is one of the main reasons in Taiwanese society for increasing dementia in elderly’s people. By the report of global dementia investigation Society, 46 million people around the world were dementia patients in the year of 2016. In Taiwan, more than 260,000 people have suffered from dementia according to Taiwan Alzheimer’s Disease Association and the number is expected to increase by one in every five by the year 2030. There are so many examinations to evaluate or identify dementia, among them Mini-Mental State Examination(MMSE), Clinical Dementia Rating (CDR) and CERAD Immediate-delay recall are the widely used methods for detecting dementia, including five main test items: orientation, message registration, attention and calculation, memory, language comprehension and visual graphing. But these methods are mainly focusing on the questionnaire with a drawing which is used only a few part of our brain to evaluate dementia, rather than using all part of the human brain. So, in our study, we integrated well known traditional methods MMSE, CDR, and Immediate-delay recalls with our newly approach android based cognitive examinations which are used to evaluate all the human brain parts to examined dementia. In our approach, we designed 13 difference examinations that subdivided into 21 difference evaluations to collect various dataset and give real-time results of the evaluation. The average examination time was designed for 10 minute. I have construct Confirmation Factory analysis (CFA) was used for all different examination to assess the goodness of fit factor structure using four different examination. Receiver Operation Characteristic (ROC) analysis was used to evaluate the sensitivity and specificity of our approach. Area under the curve (AUC) was used the primary results for ROC analysis. The Mann-Whitney U test and Spearman’s was used to demonstrate discriminate validity of the approach method and traditional approach. Next, 12 most significant data predicted by gray correlation and neural networks were selected to predict dementia degree. Finally, the results showed that there is a significant difference between test item“Memory”and “Reaction Speed” among groups of Normal Control, Mild Cognitive Impairment (MCI) and Alzheimers Disease (AD). Among these three groups, there was also a difference in test item“Motion control” , while no difference in“Visuospatial”. The accuracy rate of dementia degree prediction is 96.3%. The results of the study is hoped to be used as an extra reference for doctors to determine the degree of disability in patients in the future. Yo-Ping Huang 黃有評 2017 學位論文 ; thesis 72 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺北科技大學 === 電機工程研究所 === 105 === Aging is one of the main reasons in Taiwanese society for increasing dementia in elderly’s people. By the report of global dementia investigation Society, 46 million people around the world were dementia patients in the year of 2016. In Taiwan, more than 260,000 people have suffered from dementia according to Taiwan Alzheimer’s Disease Association and the number is expected to increase by one in every five by the year 2030. There are so many examinations to evaluate or identify dementia, among them Mini-Mental State Examination(MMSE), Clinical Dementia Rating (CDR) and CERAD Immediate-delay recall are the widely used methods for detecting dementia, including five main test items: orientation, message registration, attention and calculation, memory, language comprehension and visual graphing. But these methods are mainly focusing on the questionnaire with a drawing which is used only a few part of our brain to evaluate dementia, rather than using all part of the human brain. So, in our study, we integrated well known traditional methods MMSE, CDR, and Immediate-delay recalls with our newly approach android based cognitive examinations which are used to evaluate all the human brain parts to examined dementia. In our approach, we designed 13 difference examinations that subdivided into 21 difference evaluations to collect various dataset and give real-time results of the evaluation. The average examination time was designed for 10 minute. I have construct Confirmation Factory analysis (CFA) was used for all different examination to assess the goodness of fit factor structure using four different examination. Receiver Operation Characteristic (ROC) analysis was used to evaluate the sensitivity and specificity of our approach. Area under the curve (AUC) was used the primary results for ROC analysis. The Mann-Whitney U test and Spearman’s was used to demonstrate discriminate validity of the approach method and traditional approach.
Next, 12 most significant data predicted by gray correlation and neural networks were selected to predict dementia degree. Finally, the results showed that there is a significant difference between test item“Memory”and “Reaction Speed” among groups of Normal Control, Mild Cognitive Impairment (MCI) and Alzheimers Disease (AD). Among these three groups, there was also a difference in test item“Motion control” , while no difference in“Visuospatial”. The accuracy rate of dementia degree prediction is 96.3%. The results of the study is hoped to be used as an extra reference for doctors to determine the degree of disability in patients in the future.
|
author2 |
Yo-Ping Huang |
author_facet |
Yo-Ping Huang Sheng Chen 陳聖 |
author |
Sheng Chen 陳聖 |
spellingShingle |
Sheng Chen 陳聖 Design of tablet-based dementia examination system |
author_sort |
Sheng Chen |
title |
Design of tablet-based dementia examination system |
title_short |
Design of tablet-based dementia examination system |
title_full |
Design of tablet-based dementia examination system |
title_fullStr |
Design of tablet-based dementia examination system |
title_full_unstemmed |
Design of tablet-based dementia examination system |
title_sort |
design of tablet-based dementia examination system |
publishDate |
2017 |
url |
http://ndltd.ncl.edu.tw/handle/s8zv59 |
work_keys_str_mv |
AT shengchen designoftabletbaseddementiaexaminationsystem AT chénshèng designoftabletbaseddementiaexaminationsystem AT shengchen zhíjīyúpíngbǎndiànnǎozhīshīzhìzhèngjiǎncèxìtǒngshèjì AT chénshèng zhíjīyúpíngbǎndiànnǎozhīshīzhìzhèngjiǎncèxìtǒngshèjì |
_version_ |
1719156325675433984 |