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

2022 Fiscal Year Final Research Report

An system for detecting probable cardiac disease using ECG data

Research Project

  • PDF
Project/Area Number 20K04999
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 25020:Safety engineering-related
Research InstitutionMuroran Institute of Technology

Principal Investigator

Okada Yoshifumi  室蘭工業大学, 大学院工学研究科, 准教授 (00443177)

Project Period (FY) 2020-04-01 – 2023-03-31
Keywords心電図 / 心疾患 / 識別モデル / 畳み込みオートエンコーダー / 畳み込みニューラルネットワーク / サポートベクトルマシン
Outline of Final Research Achievements

The aim of this study was to develop a system that enabled the identification of suspicious cardiac diseases using ECG data. In this study, 14 different cardiac diseases were categorized into two cases, "cardiac diseases with observed beats" and "cardiac diseases with unclear beats," and for each case classification model was constructed. The experimental results to evaluate the model performances using test ECG data showed that the classification accuracies were much higher than that of existing studies for all cardiac diseases.

Free Research Field

データマイニング、機械学習

Academic Significance and Societal Importance of the Research Achievements

既存研究では、限定された心疾患の識別(例えば、心筋梗塞か否かの識別)に焦点が当てられていた。一方、本研究は多種類の心疾患を対象とした識別を可能にした点で既存研究と比較して優位性を有している。本研究で開発した技術は、医療現場のスタッフが心電図を用いて疑わしい心疾患を迅速に特定するための有効な支援ツールとなりえる。

URL: 

Published: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi