Classification of Photoplethysmographic Signal Quality with Deep Convolution Neural Networks for Accurate Measurement of Cardiac Stroke Volume

A Lightweight Hybrid Model Using Multiscale Markov Transition Field for Real-Time Quality Assessment of Photoplethysmography Signals

OBJECTIVE

The proliferation of wearable devices has escalated the standards for photoplethysmography (PPG) signal quality. This study introduces a lightweight model to address the imperative need for precise, real-time evaluation of PPG signal quality, followed by its deployment and validation utilizing our integrated upper computer and hardware system.

METHODS

Multiscale Markov Transition Fields (MMTF) are employed to enrich the morphological information of the signals, serving as the input for our proposed hybrid model (HM). HM undergoes initial pre-training utilizing the MIMIC-III and UCI databases, followed by fine-tuning the Queensland dataset. Knowledge distillation (KD) then transfers the large-parameter model's knowledge to the lightweight hybrid model (LHM). LHM is subsequently deployed on the upper computer for real-time signal quality assessment.

RESULTS

HM achieves impressive accuracies of 99.1% and 96.0% for binary and ternary classification, surpassing current state-of-the-art methods. LHM, with only 0.2 M parameters (0.44% of HM), maintains high accuracy despite a 2.6% drop. It achieves an inference speed of 0.023 s per image, meeting real-time display requirements. Furthermore, LHM attains a 97.7% accuracy on a self-created database. HM outperforms current methods in PPG signal quality accuracy, demonstrating the effectiveness of our approach. Additionally, LHM substantially reduces parameter count while maintaining high accuracy, enhancing efficiency and practicality for real-time applications.

CONCLUSION

The proposed methodology demonstrates the capability to achieve high-precision and real-time assessment of PPG signal quality, and its practical validation has been successfully conducted during deployment.

SIGNIFICANCE

This study contributes a convenient and accurate solution for the real-time evaluation of PPG signals, offering extensive application potential.

A Robust Approach Assisted by Signal Quality Assessment for Fetal Heart Rate Estimation from Doppler Ultrasound Signal

Fetal heart rate (FHR) monitoring, typically using Doppler ultrasound (DUS) signals, is an important technique for assessing fetal health. In this work, we develop a robust DUS-based FHR estimation approach complemented by DUS signal quality assessment (SQA) based on unsupervised representation learning in response to the drawbacks of previous DUS-based FHR estimation and DUS SQA methods. We improve the existing FHR estimation algorithm based on the autocorrelation function (ACF), which is the most widely used method for estimating FHR from DUS signals. Short-time Fourier transform (STFT) serves as a signal pre-processing technique that allows the extraction of both temporal and spectral information. In addition, we utilize double ACF calculations, employing the first one to determine an appropriate window size and the second one to estimate the FHR within changing windows. This approach enhances the robustness and adaptability of the algorithm. Furthermore, we tackle the challenge of low-quality signals impacting FHR estimation by introducing a DUS SQA method based on unsupervised representation learning. We employ a variational autoencoder (VAE) to train representations of pre-processed fetal DUS data and aggregate them into a signal quality index (SQI) using a self-organizing map (SOM). By incorporating the SQI and Kalman filter (KF), we refine the estimated FHRs, minimizing errors in the estimation process. Experimental results demonstrate that our proposed approach outperforms conventional methods in terms of accuracy and robustness.

A Wearable Assistant Device for the Hearing Impaired to Recognize Emergency Vehicle Sirens with Edge Computing

Wearable assistant devices play an important role in daily life for people with disabilities. Those who have hearing impairments may face dangers while walking or driving on the road. The major danger is their inability to hear warning sounds from cars or ambulances. Thus, the aim of this study is to develop a wearable assistant device with edge computing, allowing the hearing impaired to recognize the warning sounds from vehicles on the road. An EfficientNet-based, fuzzy rank-based ensemble model was proposed to classify seven audio sounds, and it was embedded in an Arduino Nano 33 BLE Sense development board. The audio files were obtained from the CREMA-D dataset and the Large-Scale Audio dataset of emergency vehicle sirens on the road, with a total number of 8756 files. The seven audio sounds included four vocalizations and three sirens. The audio signal was converted into a spectrogram by using the short-time Fourier transform for feature extraction. When one of the three sirens was detected, the wearable assistant device presented alarms by vibrating and displaying messages on the OLED panel. The performances of the EfficientNet-based, fuzzy rank-based ensemble model in offline computing achieved an accuracy of 97.1%, precision of 97.79%, sensitivity of 96.8%, and specificity of 97.04%. In edge computing, the results comprised an accuracy of 95.2%, precision of 93.2%, sensitivity of 95.3%, and specificity of 95.1%. Thus, the proposed wearable assistant device has the potential benefit of helping the hearing impaired to avoid traffic accidents.

LSTM-based real-time signal quality assessment for blood volume pulse analysis

Remote photoplethysmogram (rPPG) is a low-cost method to extract blood volume pulse (BVP). Some crucial vital signs, such as heart rate (HR) and respiratory rate (RR) etc. can be achieved from BVP for clinical medicine and healthcare application. As compared to the conventional PPG methods, rPPG is more promising because of its non-contacted measurement. However, both BVP detection methods, especially rPPG, are susceptible to motion and illumination artifacts, which lead to inaccurate estimation of vital signs. Signal quality assessment (SQA) is a method to measure the quality of BVP signals and ensure the credibility of estimated physiological parameters. But the existing SQA methods are not suitable for real-time processing. In this paper, we proposed an end-to-end BVP signal quality evaluation method based on a long short-term memory network (LSTM-SQA). Two LSTM-SQA models were trained using the BVP signals obtained with PPG and rPPG techniques so that the quality of BVP signals derived from these two methods can be evaluated, respectively. As there is no publicly available rPPG dataset with quality annotations, we designed a training sample generation method with blind source separation, by which two kinds of training datasets respective to PPG and rPPG were built. Each dataset consists of 38400 high and low-quality BVP segments. The achieved models were verified on three public datasets (IIP-HCI dataset, UBFC-Phys dataset, and LGI-PPGI dataset). The experimental results show that the proposed LSTM-SQA models can effectively predict the quality of the BVP signal in real-time.

Multimodal Finger Pulse Wave Sensing: Comparison of Forcecardiography and Photoplethysmography Sensors

Pulse waves (PWs) are mechanical waves that propagate from the ventricles through the whole vascular system as brisk enlargements of the blood vessels' lumens, caused by sudden increases in local blood pressure. Photoplethysmography (PPG) is one of the most widespread techniques employed for PW sensing due to its ability to measure blood oxygen saturation. Other sensors and techniques have been proposed to record PWs, and include applanation tonometers, piezoelectric sensors, force sensors of different kinds, and accelerometers. The performances of these sensors have been analyzed individually, and their results have been found not to be in good agreement (e.g., in terms of PW morphology and the physiological parameters extracted). Such a comparison has led to a deeper comprehension of their strengths and weaknesses, and ultimately, to the consideration that a multimodal approach accomplished via sensor fusion would lead to a more robust, reliable, and potentially more informative methodology for PW monitoring. However, apart from various multichannel and multi-site systems proposed in the literature, no true multimodal sensors for PW recording have been proposed yet that acquire PW signals simultaneously from the same measurement site. In this study, a true multimodal PW sensor is presented, which was obtained by integrating a piezoelectric forcecardiography (FCG) sensor and a PPG sensor, thus enabling simultaneous mechanical-optical measurements of PWs from the same site on the body. The novel sensor performance was assessed by measuring the finger PWs of five healthy subjects at rest. The preliminary results of this study showed, for the first time, that a delay exists between the PWs recorded simultaneously by the PPG and FCG sensors. Despite such a delay, the pulse waveforms acquired by the PPG and FCG sensors, along with their first and second derivatives, had very high normalized cross-correlation indices in excess of 0.98. Six well-established morphological parameters of the PWs were compared via linear regression, correlation, and Bland-Altman analyses, which showed that some of these parameters were not in good agreement for all subjects. The preliminary results of this proof-of-concept study must be confirmed in a much larger cohort of subjects. Further investigation is also necessary to shed light on the physical origin of the observed delay between optical and mechanical PW signals. This research paves the way for the development of true multimodal, wearable, integrated sensors and for potential sensor fusion approaches to improve the performance of PW monitoring at various body sites.

Estimation of Left Ventricular Ejection Fraction Using Cardiovascular Hemodynamic Parameters and Pulse Morphological Characteristics with Machine Learning Algorithms

It is estimated that 360,000 patients have suffered from heart failure (HF) in Taiwan, mostly those over the age of 65 years, who need long-term medication and daily healthcare to reduce the risk of mortality. The left ventricular ejection fraction (LVEF) is an important index to diagnose the HF. The goal of this study is to estimate the LVEF using the cardiovascular hemodynamic parameters, morphological characteristics of pulse, and bodily information with two machine learning algorithms. Twenty patients with HF who have been treated for at least six to nine months participated in this study. The self-constructing neural fuzzy inference network (SoNFIN) and XGBoost regression models were used to estimate their LVEF. A total of 193 training samples and 118 test samples were obtained. The recursive feature elimination algorithm is used to choose the optimal parameter set. The results show that the estimating root-mean-square errors (ERMS) of SoNFIN and XGBoost are 6.9 ± 2.3% and 6.4 ± 2.4%, by comparing with echocardiography as the ground truth, respectively. The benefit of this study is that the LVEF could be measured by the non-medical image method conveniently. Thus, the proposed method may arrive at an application level for clinical practice in the future.

Design of a Realtime Photoplethysmogram Signal Quality Checker for Wearables and Edge Computing

Photoplethysmogram (PPG) signal is extensively used for deducing health parameters of patients in order to infer about physiological conditions of heart, blood pressure, respiratory patterns, and so on. Such analysis and estimations can be done accurately only on high quality PPG signals with very minimal artifacts. PPG signals collected from fitness grade and smart phone scenarios are prone to muscle artifacts and hence there is a need to assess the signal quality before using the signal. Although there are approaches available in the realm of machine learning and deep learning, they are computationally expensive and may not be suitable for a wearable or edge computing scenario. In this paper, we propose the design of a quality checker to check the quality of the signal that can be directly implemented on edge devices like smartwatch. The algorithm is tested on PPG data collected from wearable, ICU and medical grade devices. In the wearable scenario where the noise levels are very high, our algorithm has performed significantly better with a F_score of over 0.92. Further we show that by applying the proposed quality checker, the accuracy of the computed heart rate from a smart phone PPG-application significantly improves.

Signal Quality Assessment of Photoplethysmogram Signals using Quantum Pattern Recognition Technique and lightweight CNN Module

Photoplethysmography (PPG) signal comprises physiological information related to cardiorespiratory health. High-quality PPG signals are necessary to extract cardiores-piratory information accurately. Motion artifacts can easily corrupt PPG signals due to human locomotion, leading to noise enriched, poor quality signals. Several rule-based and Machine-Learning (ML) - based approaches for PPG signal quality estimation are available, but those algorithms' efficacy is questionable. So, the authors propose a lightweight CNN architecture for signal quality assessment by employing a novel Quantum Pattern Recognition (QPR) technique. The proposed algorithm is validated on manually annotated data obtained from the University of Queensland database. A total of 28366, 5s signal segments are preprocessed and transformed into image files of 20 x 500 pixels for input to the 2D CNN architecture. The developed model classifies the PPG signal as 'good' and 'bad' with an accuracy of 98.3% with 99.3% sensitivity, 94.5% specificity and 98.9% F1-score. The experimental analysis concludes that slim module based architecture and novel Spatio-temporal pattern recognition technique improve the system's performance. The proposed approach is suitable for a resource-constrained wearable implementation.

The Application of Deep Learning Algorithms for PPG Signal Processing and Classification

Photoplethysmography (PPG) is widely used in wearable devices due to its conveniency and cost-effective nature. From this signal, several biomarkers can be collected, such as heart and respiration rate. For the usual acquisition scenarios, PPG is an artefact-ridden signal, which mandates the need for the designated classification algorithms to be able to reduce the noise component effect on the classification. Within the selected classification algorithm, the hyperparameters’ adjustment is of utmost importance. This study aimed to develop a deep learning model for robust PPG wave detection, which includes finding each beat’s temporal limits, from which the peak can be determined. A study database consisting of 1100 records was created from experimental PPG measurements performed in 47 participants. Different deep learning models were implemented to classify the PPG: Long Short-Term Memory (LSTM), Bidirectional LSTM, and Convolutional Neural Network (CNN). The Bidirectional LSTM and the CNN-LSTM were investigated, using the PPG Synchrosqueezed Fourier Transform (SSFT) as the models’ input. Accuracy, precision, recall, and F1-score were evaluated for all models. The CNN-LSTM algorithm, with an SSFT input, was the best performing model with accuracy, precision, and recall of 0.894, 0.923, and 0.914, respectively. This model has shown to be competent in PPG detection and delineation tasks, under noise-corrupted signals, which justifies the use of this innovative approach.

Recurrence Plot and Machine Learning for Signal Quality Assessment of Photoplethysmogram in Mobile Environment

The purpose of this study was to develop a machine learning model that could accurately evaluate the quality of a photoplethysmogram based on the shape of the photoplethysmogram and the phase relevance in a pulsatile waveform without requiring complicated pre-processing. Photoplethysmograms were recorded for 76 participants (5 min for each participant). All recorded photoplethysmograms were segmented for each beat to obtain a total of 49,561 pulsatile segments. These pulsatile segments were manually labeled as ‘good’ and ‘poor’ classes and converted to a two-dimensional phase space trajectory image using a recurrence plot. The classification model was implemented using a convolutional neural network with a two-layer structure. As a result, the proposed model correctly classified 48,827 segments out of 49,561 segments and misclassified 734 segments, showing a balanced accuracy of 0.975. Sensitivity, specificity, and positive predictive values of the developed model for the test dataset with a ‘poor’ class classification were 0.964, 0.987, and 0.848, respectively. The area under the curve was 0.994. The convolutional neural network model with recurrence plot as input proposed in this study can be used for signal quality assessment as a generalized model with high accuracy through data expansion. It has an advantage in that it does not require complicated pre-processing or a feature detection process.

Detection of Atrial Fibrillation Using a Machine Learning Approach

The atrial fibrillation (AF) is one of the most well-known cardiac arrhythmias in clinical practice, with a prevalence of 1–2% in the community, which can increase the risk of stroke and myocardial infarction. The detection of AF electrocardiogram (ECG) can improve the early detection of diagnosis. In this paper, we have further developed a framework for processing the ECG signal in order to determine the AF episodes. We have implemented machine learning and deep learning algorithms to detect AF. Moreover, the experimental results show that better performance can be achieved with long short-term memory (LSTM) as compared to other algorithms. The initial experimental results illustrate that the deep learning algorithms, such as LSTM and convolutional neural network (CNN), achieved better performance (10%) as compared to machine learning classifiers, such as support vectors, logistic regression, etc. This preliminary work can help clinicians in AF detection with high accuracy and less probability of errors, which can ultimately result in reduction in fatality rate.