| Project/Area Number |
18K10194
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 58050:Fundamental of nursing-related
|
|---|
| Research Institution | Gunma Prefectural College of Health Sciences |
|---|
Principal Investigator |
Toshihiro Ogura 群馬県立県民健康科学大学, 診療放射線学部, 教授 (40369369)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
林 則夫 群馬県立県民健康科学大学, 診療放射線学部, 准教授 (50648459)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 人口知能 / 脳卒中 / 脳波 / 人工知能 / ディープラーニング / ディ－プラーニング / 看護 / 言語障害 |
|---|
| Outline of Final Research Achievements |
One of the aftereffects of a stroke is a language disorder. Nurses need to accurately recognize the patient's thoughts and feelings. Therefore、 we analyzed electroencephalograms obtained from a simple electroencephalograph to consider the development of a system that would capture the intentions of patients who have difficulty expressing their thoughts. We taught EEGs of various stimulation to an artificial intelligence (AI) and examined whether the AI could discriminate EEGs caused by unknown stimulation. Using EEG 226800 data from 20 healthy subjects, 21 stimulus types, 60 times each per person, and 9 frequency bands, the results showed that 18 types of stimuli had a discrimination accuracy of 60% or better for various stimuli compared to the resting data for each individual. However, when the data from all 20 subjects were combined, there were 4 types of stimuli. It was found that only when individual EEG data were educated, it was possible to discriminate to some extent.
|
| Academic Significance and Societal Importance of the Research Achievements |
脳卒中は日本人の死因の第４位を占め、後遺症に悩む患者が非常に多いのが現状である。特に構音障害と呼ばれる、のどや呼吸器、舌、あご、唇など発語、発音器官が麻痺する運動機能障害により、言葉が全く話せなくなったり、不明瞭になったり、会話の調子が乱れたりし、言語障害となることも多い。そこで、ベッドサイドで手軽な簡易脳波計を用いることにより、人工知能を用いて脳波を解析し、意思表示の困難な患者の意思を容易にくみ取る装置開発が可能かどうかを考えた。そして、患者のベッドサイドで意思表示の困難な構音障害患者等の患者の意思をくみ取り、日常生活での機能障害からの回復を通じて、生活の質の向上を図る。
|
