Reduction of death from colorectal cancer with help of artificial intelligence

2022 Fiscal Year Final Research Report

• Project/Area Number: 19KK0421
• Research Category: Fund for the Promotion of Joint International Research (Fostering Joint International Research (A))
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 53010:Gastroenterology-related
• Research Institution: Showa University
• Principal Investigator: Mori Yuichi 昭和大学, 医学部, 兼任講師 (20459209)
• Project Period (FY): 2019 – 2022
• Keywords: 人工知能

Outline of Final Research Achievements

Artificial intelligence (AI) for colonoscopy is expected to automatically detect colorectal polyps during colonoscopy and prevent doctors from overlooking them. The aim of this study project is to verify/infer whether future cancer deaths can actually be reduced by the use of AI. In order to achieve this objective, microsimulation studies and meta-analyses were conducted on the effect of AI on cancer incidence and mortality. Results of these studies were used to develop a randomised controlled trial design sufficient to verify the effectiveness of AI. These have enabled the establishment of a research infrastructure that will form the basis for large-scale clinical trials.

Free Research Field

消化器内科

Academic Significance and Societal Importance of the Research Achievements

人工知能（AI)の臨床応用においては、その有用性について十分な証拠が欠如している。本研究は、AIを大腸内視鏡に併用することで、将来の大腸がん罹患率を約５パーセント減らすことができることを高精度のシミュレーション研究で示した点において、学術的意義がある。今後は、実際の患者様への導入をすることでリアルワールドの有効性を検証する必要があるため、その意味で、研究インフラを確立させた本研究の社会的意義は大きい。