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
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
• Keywords: 看護の質 / 多層ニューラルネットワーク / 看護ケアテキスト / 事前学習モデル / 看護の質評価 / Word2Vec / 畳み込みニューラルネットワーク / Bi-directional LSTM / ベクトル空間表現 / 看護技術 / 人工知能

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.

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．

Research Products

• [Presentation] 係り受け関係を考慮した Continuous Bag of Words の検討 (2020)
  • Author(s): 村本 大誠，新居 学，小橋 昌司
  • Organizer: 第 64 回システム制御情報学会 研究発表講演
• [Presentation] Estimation of AHuman Activities by Fuzzy Classification Systems for Understanding Subject Persons' Situation (2019)
  • Author(s): S. Ahmed, T. Kishi, M. Nii, K. Higuchi and S. Kobashi
  • Organizer: 2019 International Conference on Machine Learning and Cybernetics (ICMLC)
  • Int'l Joint Research
• [Presentation] A Convolution Neural Network Based Nursing-Care Text Classification Model with a New Filter for Expressing Dependency Relations of Words (2018)
  • Author(s): Yusuke Kato
  • Organizer: 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
  • Int'l Joint Research
• [Presentation] Analysis of classification results for the nursing-care text evaluation using convolutional neural networks (2017)
  • Author(s): Manabu Nii, Yuta Tsuchida, Yusuke Kato, Atsuko Uchinuno, Reiko Sakashita
  • Organizer: The 6th International Conference on Informatics, Electronics & Vision(ICIEV)
  • Int'l Joint Research
• [Presentation] Nursing-care Text Classification using Word Vector Representation and Convolutional Neural Network (2017)
  • Author(s): Manabu Nii,Yuya Tsuchida,Yusuke Kato,Atsuko Uchinuno and Reiko Sakashita
  • Organizer: Joint 17th World Congress of International Fuzzy Systems Association
  • Int'l Joint Research