A Comparison of Deep Learning Techniques for Arterial Blood Pressure Prediction
Tóm tắt
Continuous vital signal monitoring is becoming more relevant in preventing diseases that afflict a large part of the world’s population; for this reason, healthcare equipment should be easy to wear and simple to use. Non-intrusive and non-invasive detection methods are a basic requirement for wearable medical devices, especially when these are used in sports applications or by the elderly for self-monitoring. Arterial blood pressure (ABP) is an essential physiological parameter for health monitoring. Most blood pressure measurement devices determine the systolic and diastolic arterial blood pressure through the inflation and the deflation of a cuff. This technique is uncomfortable for the user and may result in anxiety, and consequently affect the blood pressure and its measurement. The purpose of this paper is the continuous measurement of the ABP through a cuffless, non-intrusive approach. The approach of this paper is based on deep learning techniques where several neural networks are used to infer ABP, starting from photoplethysmogram (PPG) and electrocardiogram (ECG) signals. The ABP was predicted first by utilizing only PPG and then by using both PPG and ECG. Convolutional neural networks (ResNet and WaveNet) and recurrent neural networks (LSTM) were compared and analyzed for the regression task. Results show that the use of the ECG has resulted in improved performance for every proposed configuration. The best performing configuration was obtained with a ResNet followed by three LSTM layers: this led to a mean absolute error (MAE) of 4.118 mmHg on and 2.228 mmHg on systolic and diastolic blood pressures, respectively. The results comply with the American National Standards of the Association for the Advancement of Medical Instrumentation. ECG, PPG, and ABP measurements were extracted from the MIMIC database, which contains clinical signal data reflecting real measurements. The results were validated on a custom dataset created at Neuronica Lab, Politecnico di Torino.
Tài liệu tham khảo
Parati G, Valentini M. Prognostic relevance of blood pressure variability. Hypertension. 2006;47:137–8.
Ilies C, Bauer M, Berg P, Rosenberg J, Hedderich J, Bein B, Hinz J, Hanss R. Investigation of the agreement of a continuous non-invasive arterial pressure device in comparison with invasive radial artery measurement. Br J Anaesth. 2012;108:202–10.
Tegtmeyer K, Brady G, Lai S, Hodo R, Braner D (2006) Placement of an Arterial Line.
Verdecchia P, Schillaci G, Borgioni C, Ciucci A, Zampi I, Gattobigio R, Sacchi N, Porcellati C. White coat hypertension and white coat effect similarities and differences. Am J Hypertens. 1995;8:790–8.
Ar SČ, G, Mlakar N, Luštrek M. Blood pressure estimation from photoplethysmogram using a spectro-temporal deep neural network. Sensors (Switzerland). 2019. https://doi.org/10.3390/s19153420.
Billings SA. Nonlinear system identification: NARMAX methods in the time, frequency, and spatio-temporal domains. John Wiley & Sons, 2013
Jain P, Garibaldi JM, Hirst JD. Supervised machine learning algorithms for protein structure classification. Comput Biol Chem. 2009;33:216–23.
Bakhtiarizadeh MR, Moradi-Shahrbabak M, Ebrahimi M, Ebrahimie E. Neural network and SVM classifiers accurately predict lipid binding proteins, irrespective of sequence homology. J Theor Biol. 2014;356:213–22.
Pollastri G, Przybylski D, Rost B, Baldi P. Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles. Proteins Struct Funct Genet. 2002;47:228–35.
Amato F, López A, Peña-Méndez EM, Vaňhara P, Hampl A, Havel J. Artificial neural networks in medical diagnosis. J Appl Biomed. 2013;11:47–58.
Ieracitano C, Mammone N, Hussain A, Morabito FC. A novel explainable machine learning approach for EEG-based brain-computer interface systems. Neural Comput Appl. 2021. https://doi.org/10.1007/s00521-020-05624-w.
Ieracitano C, Mammone N, Hussain A, Morabito FC. A novel multi-modal machine learning based approach for automatic classification of EEG recordings in dementia. Neural Netw. 2020;123:176–90.
Reese MG. Application of a time-delay neural network to promoter annotation in the Drosophila melanogaster genome. Comput Chem. 2001;26:51–6.
Hosanee M, Chan G, Welykholowa K, et al. Cuffless single-site photoplethysmography for blood pressure monitoring. J Clin Med. 2020;9:723.
Randazzo V, Ferretti J, Pasero E. ECG WATCH: A real time wireless wearable ECG. Med Meas Appl MeMeA 2019 - Symp Proc. https://doi.org/10.1109/MeMeA.2019.8802210
Randazzo V, Ferretti J, Pasero E. A wearable smart device to monitor multiple vital parameters—VITAL ECG. Electronics. 2020;9:300. https://doi.org/10.3390/electronics9020300
Randazzo V, Pasero E, Navaretti S. VITAL-ECG: a portable wearable hospital. In: 2018 IEEE Sensors Appl. Symp. SAS 2018 - Proc. Institute of Electrical and Electronics Engineers Inc., pp 1–6
Paviglianiti A, Randazzo V, Pasero E, Vallan A. Noninvasive arterial blood pressure estimation using ABPNet and VITAL-ECG. I2MTC 2020 - Int Instrum Meas Technol Conf Proc. https://doi.org/10.1109/I2MTC43012.2020.9129361
Paviglianiti A, Randazzo V, Cirrincione G, Pasero E. Neural recurrent approches to noninvasive blood pressure estimation. 2020 Int. Jt. Conf. Neural Networks
He X, Goubran RA, Liu XP. Evaluation of the correlation between blood pressure and pulse transit time. In: MeMeA 2013 - IEEE Int. Symp. Med. Meas. Appl. Proc. pp 17–20
Shriram R, Wakankar A, Daimiwal N, Ramdasi D. Continuous cuffless blood pressure monitoring based on PTT. In: ICBBT 2010 - 2010 Int. Conf. Bioinforma. Biomed. Technol. pp 51–55
Ma Y, Choi J, Hourlier-Fargette A, et al. Relation between blood pressure and pulse wave velocity for human arteries. Proc Natl Acad Sci U S A. 2018;115:11144–9.
Chua CP, Heneghan C. Continuous blood pressure monitoring using ECG and finger photoplethysmogram. In: Annu. Int. Conf. IEEE Eng. Med. Biol. - Proc. 2016.pp 5117–5120
Kurylyak Y, Lamonaca F, Grimaldi D. A neural network-based method for continuous blood pressure estimation from a PPG signal. In: Conf. Rec. - IEEE Instrum. Meas. Technol. Conf. 2013.pp 280–283
MIMIC Database v1.0.0. https://physionet.org/content/mimicdb/1.0.0/. Accessed 6 Apr 2021
Moody GB, Mark RG. A database to support development and evaluation of intelligent intensive care monitoring. Comput Cardiol 1996.0:657–660
Senturk U, Yucedag I, Polat K. Repetitive neural network (RNN) based blood pressure estimation using PPG and ECG signals. ISMSIT 2018 - 2nd Int Symp Multidiscip Stud Innov Technol Proc. https://doi.org/10.1109/ISMSIT.2018.8567071
MIMIC II Databases. https://archive.physionet.org/mimic2/. Accessed 31 Aug 2020
Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE. 2000 PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals Circulation 10.1161/01.cir.101.23.e215
GitHub - MIT-LCP/wfdb-python: Native Python WFDB package. https://github.com/MIT-LCP/wfdb-python. Accessed 6 Apr 2021
The WFDB Software Package. https://archive.physionet.org/physiotools/wfdb.shtml. Accessed 6 Apr 2021
Elgendi M, Norton I, Brearley M, Abbott D, Schuurmans D. Systolic peak detection in acceleration photoplethysmograms measured from emergency responders in tropical conditions. PLoS One 2013;8:e76585
Maronna, Ricardo A., et al. Robust statistics: theory and methods (with R). John Wiley & Sons, 2019.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition, 2016.
Géron A. Hands-on machine learning with Scikit-Learn, Keras, And TensorFlow: concepts, tools, and techniques To Build Intelligent Systems, 2019.
Oord A van den, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K. WaveNet: a generative model for raw audio, 2016.
Bergmeir C, Benítez JM. On the use of cross-validation for time series predictor evaluation. Inf Sci (Ny). 2012;191:192–213.