2023 Fiscal Year Final Research Report

Creasion of innovative occupational health services for small and medium-sized enterprises

Research Project

PDF

Project/Area Number	21K19672
Research Category	Grant-in-Aid for Challenging Research (Exploratory)
Allocation Type	Multi-year Fund
Review Section	Medium-sized Section 58:Society medicine, nursing, and related fields
Research Institution	Tokai University
Principal Investigator	Tatemichi Masayuki 東海大学, 医学部, 教授 (00318263)
Co-Investigator(Kenkyū-buntansha)	深井航太東海大学, 医学部, 講師 (00813966) 堤明純北里大学, 医学部, 教授 (10289366) 山内武紀昭和大学, 医学部, 准教授 (40576287) 古屋佑子東海大学, 医学部, 助教 (80880260)
Project Period (FY)	2021-07-09 – 2024-03-31
Keywords	産業保健 / 生成系AI / 中小零細企業
Outline of Final Research Achievements	Health Japan 21 calls for correcting this health disparity in order to extend healthy life expectancy. Even under the Industrial Safety and Health Act, workplaces with 50 or more employees can appoint an industrial physician and receive industrial health services, but workplaces with fewer than 50 employees are not required to conduct even stress checks, and are not required to do so under the law. (5.5 million establishments have fewer than 50 employees: 97% of all establishments, and the number of employees is 34 million. Ministry of Internal Affairs and Communications). We believe that building innovative industrial health services for small and medium-sized enterprises where large populations work will lead to rectifying health disparities and ultimately extending healthy life expectancy. Developed an industrial health provision service platform for small and medium-sized businesses
Free Research Field	産業保健
Academic Significance and Societal Importance of the Research Achievements	職域での健康格差を是正するため、加速化しているAI技術を利用し、産業保健の知的データベース（DB）を構築することにより、AIによる解決策の提供を行う「中小零細事業所向け産業保健提供サービスエンジン」の開発を行った。このAIエンジンには、昨今急速に進化したChatGPTを初めとする大規模言語モデル（Large Language Model）をベースに生成系AIを開発した。これまで生成系AIは専門性が高い内容や精度が要求される分野での回答はまだ不十分で、特に「ハルシネーション」という誤情報を生成する問題が発生していたが、この課題を解決して社会実装レベルにしたことは社会的意義が大きいと考える。