Hypoglycemia Prediction in Type 1 Diabetes With Electrocardiography Beat Ensembles.

IF 4.1 Q2 ENDOCRINOLOGY & METABOLISM
Mu-Ruei Tseng, Kathan Vyas, Anurag Das, Waris Quamer, Darpit Dave, Madhav Erranguntla, Carolina Villegas, Daniel DeSalvo, Siripoom McKay, Gerard Cote, Ricardo Gutierrez-Osuna
{"title":"Hypoglycemia Prediction in Type 1 Diabetes With Electrocardiography Beat Ensembles.","authors":"Mu-Ruei Tseng, Kathan Vyas, Anurag Das, Waris Quamer, Darpit Dave, Madhav Erranguntla, Carolina Villegas, Daniel DeSalvo, Siripoom McKay, Gerard Cote, Ricardo Gutierrez-Osuna","doi":"10.1177/19322968251319347","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Current methods to detect hypoglycemia in type 1 diabetes (T1D) require invasive sensors (ie, continuous glucose monitors, CGMs) that generally have low accuracy in the hypoglycemic range. A forward-looking alternative is to monitor physiological changes induced by hypoglycemia that can be measured non-invasively using, eg, electrocardiography (ECG). However, current methods require extraction of fiduciary points in the ECG signal (eg, to estimate QT interval), which is challenging in ambulatory settings.</p><p><strong>Methods: </strong>To address this issue, we present a machine-learning model that uses (1) convolutional neural networks (CNNs) to extract morphological information from raw ECG signals without the need to identify fiduciary points and (2) ensemble learning to aggregate predictions from multiple ECG beats. We evaluate the model on an experimental data set that contains ECG and CGM recordings over a period of 14 days from ten participants with T1D. We consider two testing scenarios, one that divides ECG data according to CGM readings (CGM-split) and another that divides ECG data on a day-to-day basis (day-split).</p><p><strong>Results: </strong>We find that models trained using CGM-splits tend to produce overly optimistic estimates of hypoglycemia prediction, whereas day-splits provide more realistic estimates, which are consistent with the intrinsic accuracy of CGM devices. More importantly, we find that aggregating predictions from multiple ECG beats using ensemble learning significantly improves predictions at the beat level, though these improvements have large inter-individual differences.</p><p><strong>Conclusion: </strong>Deep learning models and ensemble learning can extract and aggregate morphological information in ECG signals that is predictive of hypoglycemia. Using two validation procedures, we estimate an upper bound on the accuracy of ECG hypoglycemia prediction of 81% equal error rate and a lower bound of 60%. Further improvements may be achieved using big-data approaches that require longitudinal data from a large cohort of participants.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251319347"},"PeriodicalIF":4.1000,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863193/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Diabetes Science and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/19322968251319347","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: Current methods to detect hypoglycemia in type 1 diabetes (T1D) require invasive sensors (ie, continuous glucose monitors, CGMs) that generally have low accuracy in the hypoglycemic range. A forward-looking alternative is to monitor physiological changes induced by hypoglycemia that can be measured non-invasively using, eg, electrocardiography (ECG). However, current methods require extraction of fiduciary points in the ECG signal (eg, to estimate QT interval), which is challenging in ambulatory settings.

Methods: To address this issue, we present a machine-learning model that uses (1) convolutional neural networks (CNNs) to extract morphological information from raw ECG signals without the need to identify fiduciary points and (2) ensemble learning to aggregate predictions from multiple ECG beats. We evaluate the model on an experimental data set that contains ECG and CGM recordings over a period of 14 days from ten participants with T1D. We consider two testing scenarios, one that divides ECG data according to CGM readings (CGM-split) and another that divides ECG data on a day-to-day basis (day-split).

Results: We find that models trained using CGM-splits tend to produce overly optimistic estimates of hypoglycemia prediction, whereas day-splits provide more realistic estimates, which are consistent with the intrinsic accuracy of CGM devices. More importantly, we find that aggregating predictions from multiple ECG beats using ensemble learning significantly improves predictions at the beat level, though these improvements have large inter-individual differences.

Conclusion: Deep learning models and ensemble learning can extract and aggregate morphological information in ECG signals that is predictive of hypoglycemia. Using two validation procedures, we estimate an upper bound on the accuracy of ECG hypoglycemia prediction of 81% equal error rate and a lower bound of 60%. Further improvements may be achieved using big-data approaches that require longitudinal data from a large cohort of participants.

1型糖尿病的低血糖预测与心电图心跳集合。
目前检测1型糖尿病(T1D)低血糖的方法需要侵入式传感器(即连续血糖监测仪,cgm),通常在低血糖范围内准确性较低。一种前瞻性的替代方案是监测由低血糖引起的生理变化,这种生理变化可以使用无创测量,例如心电图(ECG)。然而,目前的方法需要提取心电信号中的信义点(例如,估计QT间期),这在动态环境中是具有挑战性的。方法:为了解决这个问题,我们提出了一种机器学习模型,该模型使用(1)卷积神经网络(cnn)从原始心电信号中提取形态信息,而无需识别信标点;(2)集成学习从多个心电拍中汇总预测。我们在一个实验数据集上评估了该模型,该数据集包含10名T1D患者14天内的ECG和CGM记录。我们考虑了两种测试场景,一种是根据CGM读数划分ECG数据(CGM-split),另一种是根据日常划分ECG数据(day-split)。结果:我们发现使用CGM分割训练的模型倾向于对低血糖预测产生过于乐观的估计,而日分割提供了更现实的估计,这与CGM设备的内在准确性一致。更重要的是,我们发现使用集成学习对多个心电心跳的预测进行汇总可以显著提高心跳水平的预测,尽管这些改进存在很大的个体间差异。结论:深度学习模型和集成学习可以提取和汇总心电信号中的形态信息,预测低血糖。使用两种验证程序,我们估计心电图低血糖预测准确率的上限为81%等错误率,下限为60%。进一步的改进可以通过大数据方法来实现,这些方法需要来自大量参与者的纵向数据。
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 求助全文
来源期刊
Journal of Diabetes Science and Technology
Journal of Diabetes Science and Technology Medicine-Internal Medicine
CiteScore
7.50
自引率
12.00%
发文量
148
期刊介绍: The Journal of Diabetes Science and Technology (JDST) is a bi-monthly, peer-reviewed scientific journal published by the Diabetes Technology Society. JDST covers scientific and clinical aspects of diabetes technology including glucose monitoring, insulin and metabolic peptide delivery, the artificial pancreas, digital health, precision medicine, social media, cybersecurity, software for modeling, physiologic monitoring, technology for managing obesity, and diagnostic tests of glycation. The journal also covers the development and use of mobile applications and wireless communication, as well as bioengineered tools such as MEMS, new biomaterials, and nanotechnology to develop new sensors. Articles in JDST cover both basic research and clinical applications of technologies being developed to help people with diabetes.
×
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