Evaluating gradient-based explanation methods for neural network ECG analysis using heatmaps.

IF 4.7 2区 医学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Journal of the American Medical Informatics Association Pub Date : 2024-11-06 DOI:10.1093/jamia/ocae280
Andrea Marheim Storås, Steffen Mæland, Jonas L Isaksen, Steven Alexander Hicks, Vajira Thambawita, Claus Graff, Hugo Lewi Hammer, Pål Halvorsen, Michael Alexander Riegler, Jørgen K Kanters
{"title":"Evaluating gradient-based explanation methods for neural network ECG analysis using heatmaps.","authors":"Andrea Marheim Storås, Steffen Mæland, Jonas L Isaksen, Steven Alexander Hicks, Vajira Thambawita, Claus Graff, Hugo Lewi Hammer, Pål Halvorsen, Michael Alexander Riegler, Jørgen K Kanters","doi":"10.1093/jamia/ocae280","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Evaluate popular explanation methods using heatmap visualizations to explain the predictions of deep neural networks for electrocardiogram (ECG) analysis and provide recommendations for selection of explanations methods.</p><p><strong>Materials and methods: </strong>A residual deep neural network was trained on ECGs to predict intervals and amplitudes. Nine commonly used explanation methods (Saliency, Deconvolution, Guided backpropagation, Gradient SHAP, SmoothGrad, Input × gradient, DeepLIFT, Integrated gradients, GradCAM) were qualitatively evaluated by medical experts and objectively evaluated using a perturbation-based method.</p><p><strong>Results: </strong>No single explanation method consistently outperformed the other methods, but some methods were clearly inferior. We found considerable disagreement between the human expert evaluation and the objective evaluation by perturbation.</p><p><strong>Discussion: </strong>The best explanation method depended on the ECG measure. To ensure that future explanations of deep neural networks for medical data analyses are useful to medical experts, data scientists developing new explanation methods should collaborate tightly with domain experts. Because there is no explanation method that performs best in all use cases, several methods should be applied.</p><p><strong>Conclusion: </strong>Several explanation methods should be used to determine the most suitable approach.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":null,"pages":null},"PeriodicalIF":4.7000,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the American Medical Informatics Association","FirstCategoryId":"91","ListUrlMain":"https://doi.org/10.1093/jamia/ocae280","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Objective: Evaluate popular explanation methods using heatmap visualizations to explain the predictions of deep neural networks for electrocardiogram (ECG) analysis and provide recommendations for selection of explanations methods.

Materials and methods: A residual deep neural network was trained on ECGs to predict intervals and amplitudes. Nine commonly used explanation methods (Saliency, Deconvolution, Guided backpropagation, Gradient SHAP, SmoothGrad, Input × gradient, DeepLIFT, Integrated gradients, GradCAM) were qualitatively evaluated by medical experts and objectively evaluated using a perturbation-based method.

Results: No single explanation method consistently outperformed the other methods, but some methods were clearly inferior. We found considerable disagreement between the human expert evaluation and the objective evaluation by perturbation.

Discussion: The best explanation method depended on the ECG measure. To ensure that future explanations of deep neural networks for medical data analyses are useful to medical experts, data scientists developing new explanation methods should collaborate tightly with domain experts. Because there is no explanation method that performs best in all use cases, several methods should be applied.

Conclusion: Several explanation methods should be used to determine the most suitable approach.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用热图评估基于梯度的神经网络心电图分析解释方法。
目的:使用热图可视化评估流行的解释方法,以解释用于心电图(ECG)分析的深度神经网络的预测,并为解释方法的选择提供建议:在心电图上训练残差深度神经网络,以预测间隔和振幅。医学专家对九种常用解释方法(Saliency、Deconvolution、Guided backpropagation、Gradient SHAP、SmoothGrad、Input × gradient、DeepLIFT、Integrated gradients、GradCAM)进行了定性评估,并使用基于扰动的方法进行了客观评估:结果:没有一种解释方法的性能始终优于其他方法,但有些方法的性能明显不如其他方法。我们发现专家评价和扰动客观评价之间存在很大分歧:讨论:最佳解释方法取决于心电图测量。为确保未来用于医学数据分析的深度神经网络解释对医学专家有用,开发新解释方法的数据科学家应与领域专家密切合作。由于没有一种解释方法能在所有使用情况下都表现最佳,因此应采用多种方法:结论:应采用多种解释方法来确定最合适的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Journal of the American Medical Informatics Association
Journal of the American Medical Informatics Association 医学-计算机:跨学科应用
CiteScore
14.50
自引率
7.80%
发文量
230
审稿时长
3-8 weeks
期刊介绍: JAMIA is AMIA''s premier peer-reviewed journal for biomedical and health informatics. Covering the full spectrum of activities in the field, JAMIA includes informatics articles in the areas of clinical care, clinical research, translational science, implementation science, imaging, education, consumer health, public health, and policy. JAMIA''s articles describe innovative informatics research and systems that help to advance biomedical science and to promote health. Case reports, perspectives and reviews also help readers stay connected with the most important informatics developments in implementation, policy and education.
期刊最新文献
Trending in the right direction: critical access hospitals increased adoption of advanced electronic health record functions from 2018 to 2023. Evaluating gradient-based explanation methods for neural network ECG analysis using heatmaps. The role of routine and structured social needs data collection in improving care in US hospitals. Correction to: Artificial intelligence for optimizing recruitment and retention in clinical trials: a scoping review. Is ChatGPT worthy enough for provisioning clinical decision support?
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1