Hypertension is one of the most important health-related problems worldwide, and its monitoring is necessary constantly.
Objective
The regular methods of blood pressure monitoring have disadvantages; hence, the interest in finding better solutions is stirred.
Methods
In this study, PPG signals from 218 subjects in Guilin People's Hospital were analyzed, where 657 PPG recordings were employed together with demographic and clinical data. CNN-Attention, CNN-GRU, and LSTM, have been conducted with z-score normalization and augmentation in an 80:20 train-test split.
Results
The highest performance of the CNN-GRU model achieved 75% accuracy, an AUC-ROC of 0.658, and perfect recall for hypertensive cases at 1.00. While the CNN-Attention model reached an accuracy of 61%, the overall poorest performance was given by LSTM.
Conclusion
These results prove that accessible cardiovascular monitoring is feasible and valuable in a resource-limited settings.
MillsKTStefanescuAHeJ. The global epidemiology of hypertension. Nat Rev Nephrol2020; 16: 223–237.
2.
KjeldsenSE. Hypertension and cardiovascular risk: general aspects. Pharmacol Res.2018; 129: 95–99.
3.
BarriYM. Hypertension and kidney disease: a deadly connection. Curr Hypertens Rep.2008; 10: 39–45.
4.
NitzanMSlotkiIShavitL. More accurate systolic blood pressure measurement is required for improved hypertension management: a perspective. Med Dev: Evid Res2017; 10: 157–163.
5.
LiSParkYLuanH, et al.Measurement of blood pressure via a skin-mounted, non-invasive pressure sensor. J Appl Mech.2021; 88: 101008.
6.
RiazFAzadMAArshadJ, et al.Pervasive blood pressure monitoring using Photoplethysmogram (PPG) sensor. Future Gener Comput Syst.2019; 98: 120–130.
7.
KarioK. Management of hypertension in the digital era. Hypertension2020; 76: 640–650.
8.
HanDBasharSKLazaroJ, et al. editors. Smartwatch PPG peak detection method for sinus rhythm and cardiac arrhythmia. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2019, IEEE.
9.
MouradianVPoghosyanAHovhannisyanL, editors. Noninvasive continuous mobile blood pressure monitoring using novel PPG optical sensor. 2015 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems (BioWireleSS). 2015, IEEE.
10.
ZhangGMeiZZhangY, et al.A noninvasive blood glucose monitoring system based on smartphone PPG signal processing and machine learning. IEEE Trans Ind Inf.2020; 16: 7209–7218.
11.
NourMPolatK. Automatic classification of hypertension types based on personal features by machine learning algorithms. Math Probl Eng.2020; 2020: 2742781.
12.
AmaratungaDCabreraJSargsyanD, et al.Uses and opportunities for machine learning in hypertension research. Int J Cardiol Hyperten2020; 5: 100027.
13.
HauggFElgendiMMenonC. Assessment of blood pressure using only a smartphone and machine learning techniques: a systematic review. Front Cardiovasc Med2022; 9: 894224.
14.
NieGZhuJTangG, et al.A review of deep learning methods for photoplethysmography data. arXiv preprintarXiv:2401127832024.
15.
TurkiAF. Assessing the efficacy of various machine learning algorithms in predicting blood pressure using pulse transit time. Diagnostics (Basel)2025; 15: 261.
16.
SassoAMDattaSJeitlerM, et al.HYPE: Predicting blood pressure from Photoplethysmograms in a hypertensive populationLecture Notes in Computer Science (LNCS) – Artificial Intelligence in Medicine (AIME 2020) Proceedings2020; 12299: 325–335.
17.
SchrumpfFFrenzelPAustC, et al.Assessment of non-invasive blood pressure prediction from PPG and rPPG signals using deep learningSensors (Basel)2021; 21: 6022. DOI: 10.3390/s21186022
18.
QinCLiYLiuC, et al.Cuff-less blood pressure prediction based on Photoplethysmography and modified ResNetBioengineering (Basel)2023; 10: 400.
19.
YanLWeiMHuS, et al.Photoplethysmography driven hypertension identification: A pilot studySensors (Basel)2023; 23: 3359.
20.
ElgendiMHauggFFletcherRR, et al.Recommendations for evaluating photoplethysmography-based algorithms for blood pressure assessment. Commun Med (Lond)2024; 4: 140.
21.
LiangYChenZLiuG, et al.A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China. Sci Data.2018; 5: –7.
22.
PhanHKochPKatzbergF, et al.Audio scene classification with deep recurrent neural networksProceedings of INTERSPEECH2017: 3043–3047.
23.
ZhangTZhangKWuJ. Multi-modal Attention Mechanisms in LSTM and Its Application to Acoustic Scene Classification. Hyderabad: INTERSPEECH, 2018.
24.
AbdillahMFKusnawiK. Comparative analysis of long short-term memory architecture for text classification. ILKOM Jurnal Ilmiah2023; 15: 455–464.
25.
ShenS-SLeeH-Y.Neural attention models for sequence classification: Analysis and application to key term extraction and dialogue act detectionProceedings of INTERSPEECH2016: 2716–2720.
26.
ZhangSZhangXHuangY, et al.A classification scheme for ECG signals based on bidirectional LSTM model. Adv Comp, Sign Syst2022; 6: 36–44.
27.
HuXYinSZhangX, et al.Blood pressure stratification using photoplethysmography and light gradient boosting machine. Front Physiol2023; 14: 1072273.
28.
MahardikaTNFuadahYNJeongDU, et al.PPG signals-based blood-pressure estimation using grid search in hyperparameter optimization of CNN-LSTMDiagnostics (Basel)2023; 13: 2566.
29.
NourMPolatKŞentürkÜ, et al.A novel Cuffless blood pressure prediction: Uncovering new features and new hybrid ML modelsDiagnostics (Basel)2023; 13: 1278.
30.
MejhoudiSJenkalRLWSaddikA, et al.Hardware architecture for adaptive dual threshold filter and discrete wavelet transform based ECG signal denoisingInt J Adv Comp Sci Appl (IJACSA)2021; 12: 45–54.
31.
ChoiJ-HLeeJ-S. Embracenet: a robust deep learning architecture for multimodal classification. Inf Fusion.2019; 51: 259–270.
32.
YanHRameshSGallagherT, et al.Performance, power, and area design trade-offs in millimeter-wave transmitter beamforming architectures. IEEE Circuits Syst Mag.2019; 19: 33–58.
