2020 Fiscal Year Final Research Report
Nursing-care Quality Improvement using Artificial Intelligence with Multimodal Information
| Project/Area Number |
17K12090
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Fundamental nursing
|
|---|
| Research Institution | University of Hyogo |
|---|
Principal Investigator |
Nii Manabu 兵庫県立大学, 工学研究科, 准教授 (80336833)
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Keywords | 看護の質 / 多層ニューラルネットワーク |
|---|
| Outline of Final Research Achievements |
In order to improve the quality of nursing care, an AI-based evaluation system was proposed to evaluate nursing-care texts describing the nursing process practiced. The AI-based evaluation system is utilized multimodal information. The developed evaluation system is based on a multilayer neural network pre-trained with information from electronic medical records. Then, the developed system was fine-tuned using the nursing-care texts which have already been evaluated by nursing-care experts. The evaluation performance has been improved compared to the conventional systems. The result of this study is that the system can now correctly evaluate about 74% of the nursing-care texts used as benchmarks.
|
| Free Research Field |
計算知能工学，看護工学
|
| Academic Significance and Societal Importance of the Research Achievements |
今後の超高齢化社会において，看護・介護の質評価・向上は必須であるが，評価を行うことのできる専門家の数は少ない．このような状況でPDCAのサイクルを円滑に回すためには，人工知能などの技術を活用した支援システムが必要である．本研究では人工知能技術を用いた看護の質評価支援システムを構築して，良好な評価性能を得られることを示した．また，従来の看護ケアテキストのみを利用するのではなく多様式の医療情報を学習に利用することにより評価性能が向上することを示した．
|
