2023 Fiscal Year Final Research Report

Investigation of automated method of identifying latent needs by secondary use of a patient registry

Research Project

PDF

Project/Area Number	20K07206
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Review Section	Basic Section 47060:Clinical pharmacy-related
Research Institution	National Institutes of Biomedical Innovation, Health and Nutrition
Principal Investigator	Tanemura Nanae 国立研究開発法人医薬基盤・健康・栄養研究所, 国立健康・栄養研究所食品保健機能研究部, 室長 (50790630)
Co-Investigator(Kenkyū-buntansha)	佐藤淳子慶應義塾大学, 薬学部(芝共立), 客員教授 (10231341) 漆原尚巳慶應義塾大学, 薬学部(芝共立), 教授 (10511917) 佐々木剛千葉大学, 医学部附属病院, 准教授 (90507378)
Project Period (FY)	2020-04-01 – 2024-03-31
Keywords	ヘルスコミュニケーション / 患者市民参画 / 潜在ニーズ / 口語テキスト / 機械学習モデル / Word2Vecモデル / Zスコア / 同義語辞書
Outline of Final Research Achievements	In this research, two AI-related technological developments were conducted. (１）Prediction and Visualization of Latent Needs：Improving the accuracy of machine learning models using the Word2Vec model：This study examined how to improve the accuracy of the model using the Word2Vec model, that used a neural network to transform words into vectors. The adaptation of the synonym dictionary using the Word2Vec model can improve the accuracy of the model.(２）Extracting the latent needs of dementia patients and caregivers from transcribed interviews in Japanese: an initial assessment of the availability of morpheme selection as input data with Z-scores in machine learning：A new scheme based on Z-score adaptation for machine learning models was developed to predict the latent needs of dementia patients and their caregivers by extracting data from interviews in Japanese.
Free Research Field	ヘルスコミュニケーション
Academic Significance and Societal Importance of the Research Achievements	〇　学術的意義：発話者の潜在ニーズを口語テキストから予測するにあたり、Word2Vecモデルを用いた同義語辞書の適応、又はZスコアを用いた特徴量選択技術が、機械学習モデルの精度に寄与した。〇　社会的意義：本研究で開発したAI技術により、一般市民の潜在的なニーズを自動抽出の上、政策等の意思決定の場に「ボイス」として反映させるための社会システムへの活用等が今後、期待される。