University of Amsterdam, Heart Center; Department of Clinical and Experimental Cardiology, Amsterdam Cardiovascular Sciences, Meibergdreef 9, Amsterdam, The Netherlands; University of Amsterdam, Department of Clinical Epidemiology, Biostatistics & Bioinformatics, Meibergdreef 9, Amsterdam, The Netherlands; Member of the European Reference Network for Rare and Low Prevalence Complex Diseases of the Heart (ERN GUARD-Heart).
University of Amsterdam, Heart Center; Department of Clinical and Experimental Cardiology, Amsterdam Cardiovascular Sciences, Meibergdreef 9, Amsterdam, The Netherlands.
Trends Cardiovasc Med. 2023 Jul;33(5):274-282. doi: 10.1016/j.tcm.2022.01.011. Epub 2022 Jan 31.
The number of inherited heart disease (IHD) studies using artificial intelligence (AI) has increased rapidly over the last years. In this scoping review, we aimed to present an overview of the current literature available on the applicability of AI within the field of IHD. The literature search resulted in eighteen articles in which an AI model was trained and tested, mostly for diagnostic and predictive purposes. The areas under the receiver operating characteristic curves ranged from 0.78-0.96, but varied between IHD types, used methods and outcome measures. Only three out of eighteen did perform validation on an external dataset and most studies did not use explainable deep learning models. To be able to integrate AI as a tool to aid physicians in their diagnoses and clinical decisions within the IHD field, generalizability has to be better evaluated and explainability of DL models has to be increased.
近年来，使用人工智能（AI）进行遗传性心脏病（IHD）研究的数量迅速增加。在本次范围综述中，我们旨在介绍当前关于 AI 在 IHD 领域应用的文献综述。文献检索共得到 18 篇文章，其中对 AI 模型进行了培训和测试，主要用于诊断和预测目的。受试者工作特征曲线下的面积范围从 0.78 到 0.96，但因 IHD 类型、使用的方法和结果测量而异。在 18 篇文章中，仅有 3 篇对外部数据集进行了验证，且大多数研究并未使用可解释的深度学习模型。为了能够将 AI 作为一种工具整合到 IHD 领域中，辅助医生进行诊断和临床决策，必须更好地评估其泛化能力，并提高深度学习模型的可解释性。
