期刊
NATURE MACHINE INTELLIGENCE
卷 3, 期 3, 页码 199-217出版社
NATURE PORTFOLIO
DOI: 10.1038/s42256-021-00307-0
关键词
-
资金
- Intel
- AstraZeneca
- European Research Council under the European Union [777826]
- Wellcome Trust
- Mark Foundation for Cancer Research
- Cancer Research UK Cambridge Centre [C9685/A25177]
- British Heart Foundation
- NIHR Cambridge Biomedical Research Centre
- HEFCE
- Lyzeum Ltd.
- Gates Cambridge Trust
- Cambridge International Trust
- EPSRC Cambridge Mathematics of Information in Healthcare Hub [EP/T017961/1]
- Cantab Capital Institute for the Mathematics of Information
- Leverhulme Trust
- EPSRC [EP/S026045/1, EP/T003553/1]
- Wellcome Innovator Award [RG98755]
- European Union [777826 NoMADS, 691070 CHiPS]
- Alan Turing Institute
Many machine learning-based approaches have been developed for the prognosis and diagnosis of COVID-19 from medical images. However, a systematic review found that current studies have methodological flaws, preventing their potential clinical utility. Recommendations are provided to address these issues for higher-quality model development.
Many machine learning-based approaches have been developed for the prognosis and diagnosis of COVID-19 from medical images and this Analysis identifies over 2,200 relevant published papers and preprints in this area. After initial screening, 62 studies are analysed and the authors find they all have methodological flaws standing in the way of clinical utility. The authors have several recommendations to address these issues. Machine learning methods offer great promise for fast and accurate detection and prognostication of coronavirus disease 2019 (COVID-19) from standard-of-care chest radiographs (CXR) and chest computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we consider all published papers and preprints, for the period from 1 January 2020 to 3 October 2020, which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. All manuscripts uploaded to bioRxiv, medRxiv and arXiv along with all entries in EMBASE and MEDLINE in this timeframe are considered. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 62 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher-quality model development and well-documented manuscripts.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据