Efficient multi-view fusion and flexible adaptation to view missing in cardiovascular system signals.

The progression of deep learning and the widespread adoption of sensors have facilitated automatic multi-view fusion (MVF) about the cardiovascular system (CVS) signals. However, prevalent MVF model architecture often amalgamates CVS signals from the same temporal step but different views into a unified representation, disregarding the asynchronous nature of cardiovascular events and the inherent heterogeneity across views, leading to catastrophic view confusion. Efficient training strategies specifically tailored for MVF models to attain comprehensive representations need simultaneous consideration. Crucially, real-world data frequently arrives with incomplete views, an aspect rarely noticed by researchers. Thus, the View-Centric Transformer (VCT) and Multitask Masked Autoencoder (M2AE) are specifically designed to emphasize the centrality of each view and harness unlabeled data to achieve superior fused representations. Additionally, we systematically define the missing-view problem for the first time and introduce prompt techniques to aid pretrained MVF models in flexibly adapting to various missing-view scenarios. Rigorous experiments involving atrial fibrillation detection, blood pressure estimation, and sleep staging-typical health monitoring tasks-demonstrate the remarkable advantage of our method in MVF compared to prevailing methodologies. Notably, the prompt technique requires finetuning <3 % of the entire model's data, substantially fortifying the model's resilience to view missing while circumventing the need for complete retraining. The results demonstrate the effectiveness of our approaches, highlighting their potential for practical applications in cardiovascular health monitoring. Codes and models are released at URL.

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.

Biometric recognition based on scalable end-to-end convolutional neural network using photoplethysmography: A comparative study.

Photoplethysmography (PPG), as one of the most widely used physiological signals on wearable devices, with dominance for portability and accessibility, is an ideal carrier of biometric recognition for guaranteeing the security of sensitive information. However, the existing state-of-the-art methods are restricted to practical deployment since power-constrained and compute-insufficient for wearable devices. 1D convolutional neural networks (1D-CNNs) have succeeded in numerous applications on sequential signals. Still, they fall short in modeling long-range dependencies (LRD), which are extremely needed in high-security PPG-based biometric recognition. In view of these limitations, this paper conducts a comparative study of scalable end-to-end 1D-CNNs for capturing LRD and parameterizing authorized templates by enlarging the receptive fields via stacking convolution operations, non-local blocks, and attention mechanisms. Compared to a robust baseline model, seven scalable models have different impacts (-0.2%-9.9%) on the accuracy of recognition over three datasets. Experimental cases demonstrate clear-cut improvements. Scalable models achieve state-of-the-art performance with an accuracy of over 97% on VitalDB and with the best accuracy on BIDMC and PRRB datasets performing 99.5% and 99.3%, respectively. We also discuss the effects of capturing LRD in generated templates by visualizations with Gramian Angular Summation Field and Class Activation Map. This study conducts that the scalable 1D-CNNs offer a performance-excellent and complexity-feasible approach for biometric recognition using PPG.

A novel method for continuous blood pressure estimation based on a single-channel photoplethysmogram signal.

OBJECTIVE: Currently, continuous blood pressure (BP) measurements are mostly based on multi-sensor combinations and datasets with limited BP ranges. Besides, most BP-related features derive from the photoplethysmogram (PPG) signal. The mechanism of PPG signal formation is not considered. We aimed to design a noninvasive and continuous method for estimation of BP using a single PPG sensor, which takes the mechanism of PPG signal formation into account. APPROACH: We prepared a dataset containing PPG signals for 294 patients from three public databases for constructing the BP estimation model. The features used in the model consisted of two types: novel features based on a multi-Gaussian model and existing features. The multi-Gaussian model fitted the different components (i.e. the main wave, the dicrotic wave and the tidal wave) of the PPG signal. Ensemble machine learning algorithms were applied to estimate systolic blood pressure (SBP) and diastolic blood pressure (DBP). When partitioning the dataset, there was an overlap between the training set and the testing set. MAIN RESULTS: Datasets with a wide-range of SBP and DBP values (SBP ranging from 74 to 229 mmHg and DBP ranging from 26 to 141 mmHg) were used to evaluate our method. The mean and standard deviation of error for SBP and DBP estimations were -0.21 ± 5.21 mmHg and -0.19 ± 3.37 mmHg, respectively. The model performance fully met the Association for the Advancement of Medical Instrumentation standard and was grade 'A' on the British Hypertension Society standard. SIGNIFICANCE: The multi-Gaussian model could be used to estimate BP, and our method was able to track a wide range of BP accurately. In addition our method is based on a single PPG sensor, making it very convenient.

Arrhythmias Classification Using Short-Time Fourier Transform and GAN Based Data Augmentation.

Lacking sufficient training samples of different heart rhythms is a common bottleneck to obtain arrhythmias classification models with high accuracy using artificial neural networks. To solve this problem, we propose a novel data augmentation method based on short-time Fourier transform (STFT) and generative adversarial network (GAN) to obtain evenly distributed samples in the training dataset. Firstly, the one-dimensional electrocardiogram (ECG) signals with a fixed length of 6 s are subjected to STFT to obtain the coefficient matrices, and then the matrices of different heart rhythm samples are used to train GAN models respectively. The generated matrices are later employed to augment the training dataset of classification models based on four convolutional neural networks (CNNs). The result shows that the performances of the classification networks are all improved after we adopt the data enhancement strategy. The proposed method is helpful in augmentation and classification of biomedical signals, especially in detecting multiple arrhythmias, since adequate training samples are usually inaccessible in these studies.