The development of the mental health support system at work with artificial intelligence - the decision for return to work-

2022 Fiscal Year Final Research Report

• Project/Area Number: 19K19431
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 58030:Hygiene and public health-related: excluding laboratory approach
• Research Institution: University of Tsukuba
• Principal Investigator: DOKI SHOTARO 筑波大学, 医学医療系, 助教 (60808781)
• Project Period (FY): 2019-04-01 – 2023-03-31
• Keywords: 人工知能 / 産業医学 / 抑うつ状態 / ニューラルネットワーク / 機械学習

Outline of Final Research Achievements

A predictive model of depressive state in the workplace was developed using data from a large cross-sectional survey of workers. The accuracy of detecting employees' depressed mood was approximately 90%, a relatively high value. We examined the performance of this model in comparison with the judgment of psychiatrists, and found that it was as accurate as that of psychiatrists. Based on the results of the above research, we identified the features for constructing an interview assistance system for mental health supporters that automatically determines when to return to work.

Free Research Field

産業精神医学

Academic Significance and Societal Importance of the Research Achievements

うつ病の質問紙の多くは主観的な気分で判定されるが、研究成果により開発した本モデルでは、客観的な評価項目のみを利用してうつ病を判定するため、偏見のせいで心理的な質問への回答を避けることを排除できる。これにより、本モデルはうつ病のスクリーニングとして利用できる可能性がある。