Automated localization and severity period prediction of myocardial infarction with clinical interpretability based on deep learning and knowledge graph

作者：

Highlights：

• Deep learning and knowledge graph are used for MI location and period prediction.

• DenseNet and diagnosis rules are employed to identify beat morphology of ECG.

• Knowledge graph of the patient is given to describe clinical interpretability.

• The proposed method was more competitive than most state-of-the-art methods.

摘要

•Deep learning and knowledge graph are used for MI location and period prediction.•DenseNet and diagnosis rules are employed to identify beat morphology of ECG.•Knowledge graph of the patient is given to describe clinical interpretability.•The proposed method was more competitive than most state-of-the-art methods.

论文关键词：Myocardial infarction,Knowledge graph,DenseNet,Production rules,Clinical interpretability

论文评审过程：Received 24 February 2022, Revised 5 July 2022, Accepted 3 August 2022, Available online 6 August 2022, Version of Record 9 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118398