Development of advanced AI system for high accurate diagnosis of cerebral infarction and myocardial infarction

2022 Fiscal Year Final Research Report

• Project/Area Number: 20H02108
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 20020:Robotics and intelligent system-related
• Research Institution: The University of Tokyo
• Principal Investigator: Hirose Kayo 東京大学, 医学部附属病院, 病院診療医(出向) (40532221)
• Co-Investigator(Kenkyū-buntansha): 梅津 信二郎 早稲田大学, 理工学術院, 教授 (70373032)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Keywords: IoTデバイス / AI判定 / 低コンピュータ負荷 / 心房細動 / 心筋梗塞

Outline of Final Research Achievements

In this project, we established a technology and system for early detection and prevention of atrial fibrillation and angina pectoris, which are causative diseases and signs of cardiogenic cerebral infarction and myocardial infarction. Specifically, the team acquired vital data using sensors with medical device-level measurement accuracy, and constructed a hybrid AI judgment system for this data. Since atrial fibrillation and angina pectoris do not always occur on a regular basis, it is difficult to detect them completely during regular checkups. In particular, it is estimated that there are as many as 800,000 patients with hidden atrial fibrillation. To solve this problem, we demonstrated that medical device-level health monitoring is possible in daily life, and furthermore, that disease detection is possible through hybrid AI judgment.

Free Research Field

知能機械学

Academic Significance and Societal Importance of the Research Achievements

医療資源が十分とはいえない中で高齢化社会を迎え、医療に対する需要が伸びていく日本の現状に対して、医療コストと被測定者に負担をかけることなく、日常生活の中で、重篤な疾患に繋がる前段階の病気を検出する技術・システムを構築したことは極めて社会的意義が高いと考えられる。また、患者数が極めて多いことから、多数の患者の健康寿命の延伸に寄与することが期待され、経済的な意義も大きい
また、計算負荷の小さい方法でハイスペック解析に匹敵する疾患判定精度を成しえたことは非常に学術的意義が高いと考えられる。