Search for prevalence of eye diseases in the very elderly and develop remote dry eye diagnostic tools

• Project/Area Number: 17K09129
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Epidemiology and preventive medicine
• Research Institution: Keio University
• Principal Investigator: UCHINO MIKI 慶應義塾大学, 医学部(信濃町), 特任講師 (00365339)
• Project Period (FY): 2017-04-01 – 2021-03-31
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2017: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
• Keywords: 機械学習 / ドライアイ / 超高齢者 / 機械学習アルゴリズム / ドライアイ診断ツール / ドライアイ有病率 / 遠隔スクリーニングツール / 集団学習

Outline of Final Research Achievements

This is a cohort study in which Kawasaki City and Keio University School of Medicine Hyakuju Research Center jointly conducted a screening for people aged 85 and over. We have collected more than 1000 participants data.
As a result of demonstrating the method of creating a dry eye diagnostic tool using a random forest or Naive Bayes machine learning algorithm, it was proved that both methods are useful in creating a dry eye diagnostic tool.

Academic Significance and Societal Importance of the Research Achievements

ランダムフォレストもしくは、Naive Bayesという二つの機械学習アルゴリズムによるドライアイ診断ツールの作成方法を実証した結果、どちらの方法もドライアイの診断ツール作成において有用であることが証明された。
機械学習という手段を持って、診断ツール作成の可能性が見出されたのは非常に意義があるものと考えられる。

Research Products

• [Presentation] Development of Quick Screening Tool for Dry Eye Disease Using Artificial Intelligence (2018)
  • Author(s): Maho Sato, Uchino Miki, Motoko Kawashima, Kazuo Tsubota
  • Organizer: 36th World Ophthalmology Congress
  • Int'l Joint Research
• [Presentation] Development of Quick Screening Tool for Dry Eye Disease Using Artificial Intelligence (2018)
  • Author(s): 佐藤真帆、内野美樹
  • Organizer: 角膜カンファランス 2018