• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2021 Fiscal Year Final Research Report

Study on Causal Inference Technology for Personalized Lifestyle Recommendation to Prevent Chronic Diseases

Research Project

  • PDF
Project/Area Number 20K23160
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeMulti-year Fund
Review Section 0908:Society medicine, nursing, and related fields
Research InstitutionOsaka University

Principal Investigator

Shirakawa Toru  大阪大学, 医学系研究科, 特任研究員 (60829357)

Project Period (FY) 2020-09-11 – 2022-03-31
Keywords公衆衛生学 / 生活習慣病 / 疫学 / 因果推論 / 縦断研究 / 機械学習
Outline of Final Research Achievements

Based on data from the health app, an algorithm was developed to automatically select health guidance comments that would optimize the user's health behavior. Preliminary analysis of the data showed a 9% improvement in health behavior. However, because a co-researcher from the joint research institute, Kobe City, was employed by the joint research company and involved in this study, the possibility of a conflict of interest arose. The university to which the researcher belonged pointed out the possibility of a conflict of interest and requested an ethical review by the Kobe City’s institutional ethical review board in accordance with the Japanese government’s ethical guidelines for medical studies. However, the response from the person in charge at Kobe city was inadequate. In light of this situation, the research was discontinued in consideration of the possibility of violating the national guidelines.

Free Research Field

公衆衛生学

Academic Significance and Societal Importance of the Research Achievements

本研究において、保健指導を個人の属性および反応に基づいて精密に選択するアルゴリズムを開発した。生活習慣は多様であり、長期的な将来を見越した、最適な生活習慣の形成を促す提案への反応は人それぞれである可能性があるが、本アルゴリズムはこの多様性を考慮した保健指導を部分的に可能とする技術である。共同研究に関わる倫理的問題が生じたために方向修正が必要となったが、継続して本技術の応用と実証を、国の制度設計の根拠となる医学研究における重要な知識の抽出に対して用いることで、生活習慣病の低減に継続的に応用していく予定である。

URL: 

Published: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi