|
|
基于心音心电信号的心衰分析系统
|
Abstract:
心音信号和心电信号作为常见的生理信号，在临床上被广泛用于心脏疾病的预防、诊断和长期检测。针对心衰的监测和诊断，目前现有的传统诊断方式较为不便，因此本文设计了一种基于心音心电信号的心衰分析系统。本系统的生理信号采集装置以STM32L432KBU6为主控制器，以ADS1292R为模拟前端采集心电信号，以驻极体麦克风采集心音信号。然后通过蓝牙连接手机，由手机应用软件显示同步心音心电信号并且上传至云平台，实现远程实时监护。云平台上部署的多模态深度神经网对其进行心衰分析。本系统使用简单，且有较高的心衰分类准确率，极大方便了家庭个人使用，同时也能在一定程度上提高医护人员的工作效率。
As common physiological signals, heart sound signal and ECG signal are widely used in clinical prevention, diagnosis and long-term detection of heart disease. For the monitoring and diagnosis of heart failure, the existing traditional diagnosis methods are inconvenient, so this paper designs a heart failure analysis system based on heart sound ECG signal. The physiological signal acquisition device of the system uses STM32L432KBU6 as the main controller, ADS1292R as the analog front end to collect the ECG signal, and electret microphone to collect the heart sound signal; then connects the mobile phone through Bluetooth, the mobile phone application software displays the synchronous heart sound ECG signal and uploads it to the cloud platform, realizing remote real-time monitoring. The multimodal deep neural network deployed on the cloud platform was used for heart failure analysis. This system is simple to use, and has a high classification accuracy of heart failure, greatly convenient for family personal use, also can improve the work efficiency of medical staff to a certain extent.
| [1] | 中国心血管健康与疾病报告编写组. 中国心血管健康与疾病报告2019概要[J]. 中国循环杂志, 2020, 35(9): 833-854, 9. |
| [2] | 黄博强, 庞宇, 彭良广, 吴优. 一种生命体征信号采集装置设计[J]. 传感器与微系统, 2018, 37(3): 103-105.
http://doi.cnki.net/Resolution/Handler?doi=10.13873/j.1000-9787(2018)03-0103-03 |
| [3] | 宁国琛. 基于声源定位的头部姿态识别系统研究与实现[D]: [硕士学位论文]. 沈阳: 东北大学, 2017. |
| [4] | 郭亚涛. 低功耗宽供电范围CMOS生理信号检测前端研究与设计[D]: [硕士学位论文]. 广州: 华南理工大学, 2015. |
| [5] | 陈建锋, 孙朋, 林金朝, 庞宇, 王延向. 一种便携式心电和呼吸信号采集装置的设计[J]. 生命科学仪器, 2015, 13(6): 31-35. |
| [6] | 宋立新, 王祁, 王玉静. 基于Hilbert-Huang变换的ECG信号降噪方法[J]. 传感技术学报, 2006(6): 2578-2581+2590. |
| [7] | 唐琪, 梁劭华, 陈志平. 基于嵌入式的微型心电心音监测装置的设计[J]. 电子设计工程, 2014, 22(19): 156-159.
https://www.cnki.net/kcms/doi/10.14022/j.cnki.dzsjgc.2014.19.046.html |
| [8] | He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, 27-30 June 2016, 770-778.
https://doi.org/10.1109/CVPR.2016.90 |
| [9] | Cho, K., Van Merri？nboer, B., Bahdanau, D., et al. (2014) On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, 103-111. arXiv preprint arXiv:1409.1259
https://doi.org/10.3115/v1/W14-4012 |
| [10] | Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) Imagenet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 25, 1097-1105. |
| [11] | Wang, P., Lim, C.S., Chauhan, S., et al. (2007) Phonocardiographic Signal Analysis Method Using a Modified Hidden Markov Model. Annals of Biomedical Engineering, 35, 367-374. https://doi.org/10.1007/s10439-006-9232-3 |
| [12] | Maknickas, V. and Maknickas, A. (2017) Recognition of Normal-Abnormal Phonocardiographic Signals Using Deep Convolutional Neural Networks and Mel-Frequency Spectral Coefficients. Physiological Measurement, 38, 1671.
https://doi.org/10.1088/1361-6579/aa7841 |
| [13] | Kui, H.R., Pan, J.H., Zong, R., Yang, H.B. and Wang, W.L. (2021) Heart Sound Classification Based on Log Mel-Frequency Spectral Coefficients Features and Convolutional Neural Networks. Biomedical Signal Processing and Control, 69, 102893. https://doi.org/10.1016/j.bspc.2021.102893 |
