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

2021 Fiscal Year Final Research Report

Machine learning using neuroimaging dataset around the onset of schizophrenia and the proposal for the optimal MRI protocol: An Asian multicenter study

Research Project

  • PDF
Project/Area Number 19H03579
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 52030:Psychiatry-related
Research InstitutionThe University of Tokyo

Principal Investigator

Koike Shinsuke  東京大学, 大学院総合文化研究科, 准教授 (10633167)

Co-Investigator(Kenkyū-buntansha) 笹林 大樹  富山大学, 学術研究部医学系, 助教 (80801414)
平野 羊嗣  九州大学, 大学病院, 講師 (90567497)
Project Period (FY) 2019-04-01 – 2022-03-31
Keywords初発統合失調症 / 統合失調症ハイリスク群 / アジア精神病MRI研究コンソーシアム / マルチモダリティ / 機械学習
Outline of Final Research Achievements

The objectives of this study are to coordinate the Asian Consortium on MRI in Psychosis (ACMP) to establish a large-scale brain imaging analysis scheme for first-episode schizophrenia and ultra-high risk for psychosis (Early clinical staging of schizophrenia, ECS) (Study 1, Koike), to elucidate the pathophysiology of ECS using large-scale multimodality brain structural imaging (Study 2, Sasabayashi), to elucidate the pathophysiology of ECS using MRI and EEG MMN/GBO (Study 3, Hirano), and to apply to machine learning for prognosis prediction of ECS (Study 4, Koike). Study 1) was delayed significantly due to the spread of COVID-19 infection. Studies 2) - 4) were able to proceed as originally planned, partially exceeding the plan, and many academic achievements were obtained.

Free Research Field

精神医学

Academic Significance and Societal Importance of the Research Achievements

本研究成果により、国内の共同研究体制が強化できただけでなく、アジア諸国との連携体制、実際のデータ共有に際する国別の状況把握、研究倫理など、問題点が洗い出せた。新型コロナウイルス感染症の影響はいまだ残っており、人的交流に大きな制限を受けているが、データ共有が開始できたことは意義深い。一方、すでに共有できたMRI, 脳波データについては、十分な学術成果を出すことができており、今後ACMPデータを使った大規模解析に容易に移行できる体制が整っている。機械学習解析も臨床応用可能な状況に着実に進められており、社会的な波及効果も十分期待できる。

URL: 

Published: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi