Development and evaluation of an innovative CBT stress management program for prevention of depressive and anxiety disorders

2021 Fiscal Year Final Research Report

• Project/Area Number: 18H04072
• Research Category: Grant-in-Aid for Scientific Research (A)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Medium-sized Section 58:Society medicine, nursing, and related fields
• Research Institution: The University of Tokyo
• Principal Investigator: Kawakami Norito 東京大学, 大学院医学系研究科(医学部), 教授 (90177650)
• Co-Investigator(Kenkyū-buntansha): 小山 博史 東京大学, 大学院医学系研究科(医学部), 教授 (30194640) ; 西 大輔 東京大学, 大学院医学系研究科(医学部), 准教授 (40450605) ; 今村 幸太郎 東京大学, 大学院医学系研究科(医学部), 特任講師 (80722793)
• Project Period (FY): 2018-04-01 – 2022-03-31
• Keywords: 産業精神保健 / 人工知能 / 認知行動療法 / 健康教育 / 無作為化比較試験

Outline of Final Research Achievements

We developed a fully-automated AI-based Internet cognitive behavioral therapy (iCBT) program and tested its effectiveness for reducing depression among workers in a randomized controlled trial. We assigned 648 participants for each of intervention and control groups. The intervention group studied the AI-guided iCBT program "Mr Smart" for 10 weeks. The primary outcome is Beck Depression Inventory II score at 3- and 6-months. Eighty-five percent of the intervention group studied at least part of the program; and 54% studied all the program. The intervention effects at 3- and 6-month follow-ups were both significant (p=0.038 and 0.020, respectively). We concluded that the AI-guided iCBT program "Mr Smart" was effective in reducing depression among workers.

Free Research Field

精神保健学

Academic Significance and Societal Importance of the Research Achievements

学習内容の定着のためのワークの支援をAIにより自動化したSMART-CBTプログラムでは、労働者における抑うつ軽減効果は３ヶ月、６ヶ月時点で有意であり、専門家支援型iCBTプログラムの効果量と同等であった。SMART-CBTは低コストで効果的なiCBTプログラムとして労働者の抑うつの予防・改善に活用できる可能性がある。