2023 Fiscal Year Final Research Report

Machine Learning Model for Prediction of Ischemic Heart Disease Focusing on Epicardial Adipose Tissue and Fatty Liver

Research Project

PDF

Project/Area Number	21K12657
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Review Section	Basic Section 90110:Biomedical engineering-related
Research Institution	Waseda University
Principal Investigator	Yuba Mitsuru 早稲田大学, 総合研究機構, その他(招聘研究員) (50875367)
Co-Investigator(Kenkyū-buntansha)	岩崎清隆早稲田大学, 理工学術院, 教授 (20339691) 坪子侑佑国立医薬品食品衛生研究所, 医療機器部, 主任研究官 (40809399)
Project Period (FY)	2021-04-01 – 2024-03-31
Keywords	機械学習 / 虚血性心疾患 / 脂肪肝 / 心外膜下脂肪組織
Outline of Final Research Achievements	We have worked on the construction of a machine learning model that can diagnose ischemic heart disease using the presence or absence of fatty liver and the amount of epicardial adipose tissue obtained from coronary artery X-ray CT images in addition to basic patient information as training data. In this study, a significant improvement in diagnostic accuracy was observed when the presence or absence of fatty liver was learned in addition to the basic patient information, and the accuracy decreased when information on epicardial adipose tissue was added, indicating that information on the presence or absence of fatty liver may be more important as a risk factor for ischemic heart disease compared to information on epicardial adipose tissue. This indicates that information on the presence of fatty liver may be more important as a risk factor for ischemic heart disease than information on epicardial adipose tissue.
Free Research Field	医工学
Academic Significance and Societal Importance of the Research Achievements	本研究は、虚血性心疾患の新たなリスク因子として着目されている心外膜下脂肪量及び脂肪肝の有無を学習させた機械学習モデルの有用性を検証した研究である。これまで、虚血性心疾患のリスク因子を定量化する手法や重要度に関する研究が行われてきたなかで、両因子を機械学習させて比較した研究は存在しなかった。本研究の結果は冠動脈X線CT検査から得られる情報の中でも脂肪肝の情報が虚血性心疾患のリスク因子としてより有益であることを示すものであり、虚血性心疾患の早期発見・早期治療介入実現に向けた一助となりうると考えられた。