Noninvasive Classification of Blood Pressure Based on Photoplethysmography Signals Using Bidirectional Long Short-Term Memory and Time-Frequency Analysis

Неинвазивная классификация артериального давления на основе сигналов фотоплетизмографии с использованием двунаправленной долгой краткосрочной памяти и анализа «время–частота»
Hendrana Tjahjadi, Kalamullah Ramli, Hendri Murfi
2020-01-01

Bidirectional LSTMBlood pressure classificationPhotoplethysmography signalsSpectral entropyTime-frequency analysis
The photoplethysmography (PPG) method for continuous noninvasive measurements of blood pressure (BP) offers a more comfortable solution than conventional methods. The main challenge in using the PPG method is that its accuracy is greatly influenced by motion artifacts. In addition, the characteristics of PPG vary depending on physiological conditions; hence, the system must be calibrated to adjust for such changes. We attempt to address these limitations and propose a novel method for the classification of BP using a bidirectional long short-term memory (BLSTM) network with time-frequency (TF) analysis based on PPG signals. The TF analysis extracts information from PPG signals using a short-time Fourier transform (STFT) in the time domain to produce two features, namely, the instantaneous frequency and spectral entropy. Training the BLSTM network using TF features significantly improves the classification performance and decreases the training time. We classify 900 PPG waveform segment samples from 219 adult subjects into three classification levels: normotension (NT), prehypertension (PHT) and hypertension (HT). The results show that the proposed method is successful in the classification of BP with accuracy, sensitivity, and speciticity values of 97.33%, 100%, and 94.87%, respectively. The F1 scores of three BP classifications were 97.29%, 97.39%, and 93.93%, respectively. A comparison of current and previous approaches to the classification of BP is accomplished. Our proposed method achieves a higher accuracy than convolutional neural networks (CNNs), k-nearest neighbors (KNN), bagged tree, logistic regression, and AdaBoost tree methods.
1
A BLSTM network combined with short-time Fourier transform features enables noninvasive three-level blood-pressure classification from PPG signals.
2
F1 scores were 97.29% for normotension, 97.39% for prehypertension, and 93.93% for hypertension; accuracy exceeded several conventional machine-learning and CNN methods.
3
The method classified 900 PPG segments from 219 adults into normotension, prehypertension, and hypertension categories.
4
The proposed approach achieved 97.33% accuracy, 100% sensitivity, and 94.87% specificity for blood-pressure classification.
5
Time-frequency analysis extracts instantaneous frequency and spectral entropy features, improving classification performance and reducing BLSTM training time.

Photoplethysmography (PPG) signals from adult subjects

Blood pressure classification into normotension, prehypertension, and hypertension, including robustness to motion artifacts and physiological variation

Publication Details
Publication Date
2020-01-01
Journal
Publisher
ISSN
Cited by
67
Access Type
Author Information
Authors
Hendrana Tjahjadi
Kalamullah Ramli
Hendri Murfi
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%