• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于 RNN 的心电图预测抑郁风险。

Predicting the Risk of Depression Based on ECG Using RNN.

机构信息

Department of Electrical and Computer Engineering, North South University, Bashundhara, Dhaka 1229, Bangladesh.

School of Electronics and Electrical Engineering, Lovely Professional University, Phagwara, India.

出版信息

Comput Intell Neurosci. 2021 Jul 28;2021:1299870. doi: 10.1155/2021/1299870. eCollection 2021.

DOI:10.1155/2021/1299870
PMID:34367269
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8342171/
Abstract

This paper presents a model to predict the risk of depression based on electrocardiogram (ECG). This proposed model uses a Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) autoencoder to predict normal, abnormal, and PVC heartbeats. The RNN model is a deep learning-based model to classify normal, abnormal, and PVC heartbeats. We used the model as a classifier. The model uses a heart rates dataset to predict abnormal and PVC heartbeats. As for the dataset, we have used 5000 ECG samples. The model was trained on a training dataset and validation dataset. After that, it was tested on a test dataset. The model is trained on normal heartbeat rates, so the model can predict any heartbeat rates other than normal. Our contribution here is to build a model that can differentiate between "normal," "abnormal," and "risky" heartbeats. Our model predicts "normal" heartbeats with 97.24% accuracy and can predict "PVC" heartbeats with 100% accuracy. Other than the accuracy, we evaluated our model on the training loss graphs. These two types of training loss graphs were evaluated as "normal" versus "risky" and "abnormal" versus "risky." We have seen great results there as well. The best losses for "normal," "abnormal," and "risky" are 5.71, 33.36, and 34.78. However, these results may improve if a larger dataset is used. In studies, it was found that patients suffering from depression may have a different kind of heartbeat than the normal ones. In most cases, it is PVC (Premature Ventricular Contraction) heartbeats. Therefore, the target is to predict abnormal heartbeats and PVC heartbeats.

摘要

本文提出了一种基于心电图 (ECG) 预测抑郁风险的模型。该模型使用递归神经网络 (RNN) 和长短时记忆 (LSTM) 自动编码器来预测正常、异常和 PVC 心跳。RNN 模型是一种基于深度学习的模型，用于分类正常、异常和 PVC 心跳。我们使用该模型作为分类器。该模型使用心率数据集来预测异常和 PVC 心跳。对于数据集，我们使用了 5000 个 ECG 样本。该模型在训练数据集和验证数据集上进行训练。之后，在测试数据集上进行测试。该模型是基于正常心跳率进行训练的，因此可以预测除正常以外的任何心跳率。我们的贡献在于构建了一个可以区分“正常”、“异常”和“风险”心跳的模型。我们的模型预测“正常”心跳的准确率为 97.24%，可以预测“PVC”心跳的准确率为 100%。除了准确率，我们还根据训练损失图对模型进行了评估。这些两种类型的训练损失图是在“正常”与“风险”和“异常”与“风险”之间进行评估的。我们在这些方面也取得了很好的结果。“正常”、“异常”和“风险”的最佳损失分别为 5.71、33.36 和 34.78。然而，如果使用更大的数据集，这些结果可能会有所改善。在研究中发现，患有抑郁症的患者的心跳可能与正常人的心跳不同。在大多数情况下，是 PVC（室性早搏）心跳。因此，目标是预测异常心跳和 PVC 心跳。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/96416d6ed7a3/CIN2021-1299870.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/028622a1db07/CIN2021-1299870.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/ab4f36eeeda3/CIN2021-1299870.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/aba077ed5a3b/CIN2021-1299870.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/f00fcf381926/CIN2021-1299870.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/5644070271bf/CIN2021-1299870.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/7e31fcd380e0/CIN2021-1299870.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/9b4a11eb48a1/CIN2021-1299870.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/f1dea72c66cf/CIN2021-1299870.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/c80c7335e13f/CIN2021-1299870.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/3a4810cdaa00/CIN2021-1299870.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/96416d6ed7a3/CIN2021-1299870.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/028622a1db07/CIN2021-1299870.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/ab4f36eeeda3/CIN2021-1299870.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/aba077ed5a3b/CIN2021-1299870.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/f00fcf381926/CIN2021-1299870.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/5644070271bf/CIN2021-1299870.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/7e31fcd380e0/CIN2021-1299870.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/9b4a11eb48a1/CIN2021-1299870.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/f1dea72c66cf/CIN2021-1299870.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/c80c7335e13f/CIN2021-1299870.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/3a4810cdaa00/CIN2021-1299870.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9c40/8342171/96416d6ed7a3/CIN2021-1299870.011.jpg

相似文献

1
Predicting the Risk of Depression Based on ECG Using RNN.基于 RNN 的心电图预测抑郁风险。
Comput Intell Neurosci. 2021 Jul 28;2021:1299870. doi: 10.1155/2021/1299870. eCollection 2021.
2
A deep convolutional neural network model to classify heartbeats.一种用于分类心跳的深度卷积神经网络模型。
Comput Biol Med. 2017 Oct 1;89:389-396. doi: 10.1016/j.compbiomed.2017.08.022. Epub 2017 Aug 24.
3
Robust PVC Identification by Fusing Expert System and Deep Learning.融合专家系统和深度学习的稳健 PVC 识别。
Biosensors (Basel). 2022 Mar 22;12(4):185. doi: 10.3390/bios12040185.
4
A robust multiple heartbeats classification with weight-based loss based on convolutional neural network and bidirectional long short-term memory.基于卷积神经网络和双向长短期记忆的带权重损失的稳健多心跳分类。
Front Physiol. 2022 Dec 5;13:982537. doi: 10.3389/fphys.2022.982537. eCollection 2022.
5
Detection of premature ventricular contractions on a ventricular electrocardiogram for patients with left ventricular assist devices.左心室辅助装置患者心室心电图上室性早搏的检测
Artif Organs. 2014 Dec;38(12):1040-6. doi: 10.1111/aor.12306. Epub 2014 Apr 21.
6
Robust deep learning pipeline for PVC beats localization.用于 PVC 搏动定位的稳健深度学习管道。
Technol Health Care. 2021;29(S1):475-486. doi: 10.3233/THC-218045.
7
Automatic diagnosis of arrhythmia with electrocardiogram using multiple instance learning: From rhythm annotation to heartbeat prediction.使用多实例学习通过心电图自动诊断心律失常：从节律注释到心跳预测。
Artif Intell Med. 2022 Oct;132:102379. doi: 10.1016/j.artmed.2022.102379. Epub 2022 Aug 22.
8
Automatic diagnosis of premature ventricular contraction based on Lyapunov exponents and LVQ neural network.基于李雅普诺夫指数和学习向量量化神经网络的室性早搏自动诊断
Comput Methods Programs Biomed. 2015 Oct;122(1):47-55. doi: 10.1016/j.cmpb.2015.06.010. Epub 2015 Jul 9.
9
Automatic classification of arrhythmias using multi-branch convolutional neural networks based on channel-based attention and bidirectional LSTM.基于通道注意力和双向 LSTM 的多分支卷积神经网络的心律失常自动分类。
ISA Trans. 2023 Jul;138:397-407. doi: 10.1016/j.isatra.2023.02.028. Epub 2023 Feb 27.
10
Premature beats detection based on a novel convolutional neural network.基于新型卷积神经网络的早搏检测
Physiol Meas. 2021 Jul 28;42(7). doi: 10.1088/1361-6579/ac0e82.

引用本文的文献

1
Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model.心脏注意力网络：利用高精度便携式深度学习模型推进心电图心搏特征分析
Front Cardiovasc Med. 2025 Jan 6;11:1473482. doi: 10.3389/fcvm.2024.1473482. eCollection 2024.
2
Retracted: Predicting the Risk of Depression Based on ECG Using RNN.撤回：基于心电图使用循环神经网络预测抑郁症风险。
Comput Intell Neurosci. 2023 Dec 13;2023:9819186. doi: 10.1155/2023/9819186. eCollection 2023.
3
QT interval is correlated with and can predict the comorbidity of depression and anxiety: A cross-sectional study on outpatients with first-episode depression.

本文引用的文献

1
A Comparative Analysis of Machine Learning Algorithms to Predict Alzheimer's Disease.机器学习算法预测阿尔茨海默病的比较分析。
J Healthc Eng. 2021 Jul 2;2021:9917919. doi: 10.1155/2021/9917919. eCollection 2021.
2
A Pneumonia Diagnosis Scheme Based on Hybrid Features Extracted from Chest Radiographs Using an Ensemble Learning Algorithm.基于集成学习算法从胸部 X 光片中提取的混合特征的肺炎诊断方案。
J Healthc Eng. 2021 Feb 25;2021:8862089. doi: 10.1155/2021/8862089. eCollection 2021.
3
Detection of major depressive disorder from linear and nonlinear heart rate variability features during mental task protocol.
QT间期与抑郁和焦虑的共病相关且可预测：一项针对首发抑郁症门诊患者的横断面研究。
Front Cardiovasc Med. 2022 Sep 29;9:915539. doi: 10.3389/fcvm.2022.915539. eCollection 2022.
4
State-of-the-Art Deep Learning Methods on Electrocardiogram Data: Systematic Review.心电图数据的最新深度学习方法：系统综述。
JMIR Med Inform. 2022 Aug 15;10(8):e38454. doi: 10.2196/38454.
基于精神任务协议中的线性和非线性心率变异性特征检测重度抑郁症。
Comput Biol Med. 2019 Sep;112:103381. doi: 10.1016/j.compbiomed.2019.103381. Epub 2019 Aug 4.
4
Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals.基于 EEG 信号的深度表示和序列学习的自动抑郁检测
J Med Syst. 2019 May 28;43(7):205. doi: 10.1007/s10916-019-1345-y.
5
Depression and mortality in a longitudinal study: 1952-2011.一项纵向研究中的抑郁与死亡率：1952 - 2011年
CMAJ. 2017 Oct 23;189(42):E1304-E1310. doi: 10.1503/cmaj.170125.
6
Excess mortality due to depression and anxiety in the United States: results from a nationally representative survey.美国抑郁症和焦虑症导致的超额死亡率：一项全国代表性调查的结果
Gen Hosp Psychiatry. 2016 Mar-Apr;39:39-45. doi: 10.1016/j.genhosppsych.2015.12.003. Epub 2015 Dec 18.
7
Relationship between premature ventricular complexes and depressive symptoms in non-ST-elevation acute coronary syndrome.非 ST 段抬高型急性冠状动脉综合征中心律不齐与抑郁症状的关系。
Eur Heart J Acute Cardiovasc Care. 2013 Mar;2(1):61-7. doi: 10.1177/2048872613476101.