自校正递归神经网络在重症监护急性肾损伤预测中的应用

Health data science Pub Date : 2021-12-23 eCollection Date: 2021-01-01 DOI:10.34133/2021/9808426
Hao Du, Ziyuan Pan, Kee Yuan Ngiam, Fei Wang, Ping Shum, Mengling Feng
{"title":"自校正递归神经网络在重症监护急性肾损伤预测中的应用","authors":"Hao Du, Ziyuan Pan, Kee Yuan Ngiam, Fei Wang, Ping Shum, Mengling Feng","doi":"10.34133/2021/9808426","DOIUrl":null,"url":null,"abstract":"<p><p><i>Background</i>. In critical care, intensivists are required to continuously monitor high-dimensional vital signs and lab measurements to detect and diagnose acute patient conditions, which has always been a challenging task. Recently, deep learning models such as recurrent neural networks (RNNs) have demonstrated their strong potential on predicting such events. However, in real deployment, the patient data are continuously coming and there is no effective adaptation mechanism for RNN to incorporate those new data and become more accurate.<i>Methods</i>. In this study, we propose a novel self-correcting mechanism for RNN to fill in this gap. Our mechanism feeds prediction errors from the predictions of previous timestamps into the prediction of the current timestamp, so that the model can \"learn\" from previous predictions. We also proposed a regularization method that takes into account not only the model's prediction errors on the labels but also its estimation errors on the input data.<i>Results</i>. We compared the performance of our proposed method with the conventional deep learning models on two real-world clinical datasets for the task of acute kidney injury (AKI) prediction and demonstrated that the proposed model achieved an area under ROC curve at 0.893 on the MIMIC-III dataset and 0.871 on the Philips eICU dataset.<i>Conclusions</i>. The proposed self-correcting RNNs demonstrated effectiveness in AKI prediction and have the potential to be applied to clinical applications.</p>","PeriodicalId":73207,"journal":{"name":"Health data science","volume":"1 1","pages":"9808426"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10904062/pdf/","citationCount":"0","resultStr":"{\"title\":\"Self-Correcting Recurrent Neural Network for Acute Kidney Injury Prediction in Critical Care.\",\"authors\":\"Hao Du, Ziyuan Pan, Kee Yuan Ngiam, Fei Wang, Ping Shum, Mengling Feng\",\"doi\":\"10.34133/2021/9808426\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><i>Background</i>. In critical care, intensivists are required to continuously monitor high-dimensional vital signs and lab measurements to detect and diagnose acute patient conditions, which has always been a challenging task. Recently, deep learning models such as recurrent neural networks (RNNs) have demonstrated their strong potential on predicting such events. However, in real deployment, the patient data are continuously coming and there is no effective adaptation mechanism for RNN to incorporate those new data and become more accurate.<i>Methods</i>. In this study, we propose a novel self-correcting mechanism for RNN to fill in this gap. Our mechanism feeds prediction errors from the predictions of previous timestamps into the prediction of the current timestamp, so that the model can \\\"learn\\\" from previous predictions. We also proposed a regularization method that takes into account not only the model's prediction errors on the labels but also its estimation errors on the input data.<i>Results</i>. We compared the performance of our proposed method with the conventional deep learning models on two real-world clinical datasets for the task of acute kidney injury (AKI) prediction and demonstrated that the proposed model achieved an area under ROC curve at 0.893 on the MIMIC-III dataset and 0.871 on the Philips eICU dataset.<i>Conclusions</i>. The proposed self-correcting RNNs demonstrated effectiveness in AKI prediction and have the potential to be applied to clinical applications.</p>\",\"PeriodicalId\":73207,\"journal\":{\"name\":\"Health data science\",\"volume\":\"1 1\",\"pages\":\"9808426\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10904062/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Health data science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.34133/2021/9808426\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2021/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Health data science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.34133/2021/9808426","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2021/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

背景在重症监护中,重症监护医生需要持续监测高维生命体征和实验室测量,以检测和诊断急性患者状况,这一直是一项具有挑战性的任务。最近,诸如递归神经网络(RNN)之类的深度学习模型已经证明了它们在预测此类事件方面的强大潜力。然而,在实际部署中,患者数据不断出现,RNN没有有效的适应机制来整合这些新数据并变得更加准确。方法。在这项研究中,我们提出了一种新的RNN自校正机制来填补这一空白。我们的机制将来自先前时间戳预测的预测误差馈送到当前时间戳的预测中,以便模型可以从先前的预测中“学习”。我们还提出了一种正则化方法,该方法不仅考虑了模型在标签上的预测误差,还考虑了模型对输入数据的估计误差。后果我们在两个真实世界的临床数据集上比较了我们提出的方法与传统深度学习模型在急性肾损伤(AKI)预测任务中的性能,并证明了所提出的模型在MIMIC-III数据集上实现了0.893的ROC曲线下面积,在Philips eICU数据集上达到了0.871的ROC。结论。所提出的自校正RNN在AKI预测中证明了有效性,并具有应用于临床应用的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Self-Correcting Recurrent Neural Network for Acute Kidney Injury Prediction in Critical Care.

Background. In critical care, intensivists are required to continuously monitor high-dimensional vital signs and lab measurements to detect and diagnose acute patient conditions, which has always been a challenging task. Recently, deep learning models such as recurrent neural networks (RNNs) have demonstrated their strong potential on predicting such events. However, in real deployment, the patient data are continuously coming and there is no effective adaptation mechanism for RNN to incorporate those new data and become more accurate.Methods. In this study, we propose a novel self-correcting mechanism for RNN to fill in this gap. Our mechanism feeds prediction errors from the predictions of previous timestamps into the prediction of the current timestamp, so that the model can "learn" from previous predictions. We also proposed a regularization method that takes into account not only the model's prediction errors on the labels but also its estimation errors on the input data.Results. We compared the performance of our proposed method with the conventional deep learning models on two real-world clinical datasets for the task of acute kidney injury (AKI) prediction and demonstrated that the proposed model achieved an area under ROC curve at 0.893 on the MIMIC-III dataset and 0.871 on the Philips eICU dataset.Conclusions. The proposed self-correcting RNNs demonstrated effectiveness in AKI prediction and have the potential to be applied to clinical applications.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
3.70
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信