Fusion of Whole Night Features and Desaturation Segments Combined with Feature Extraction for Event-Level Screening of Sleep-Disordered Breathing

A Dual-Modal Wearable Pulse Detection System Integrated with Deep Learning for High-Accuracy and Low-Power Sleep Apnea Monitoring

Despite being a serious health condition that significantly increases cardiovascular and metabolic disease risks, sleep apnea syndrome (SAS) remains largely underdiagnosed. While polysomnography (PSG) remains the gold standard for diagnosis, its clinical application is limited by high costs, complex setup requirements, and sleep quality interference. Although wearable devices using photoplethysmography (PPG) have shown promise in SAS detection, their continuous operation demands substantial power consumption, hindering long-term monitoring capabilities. Here, a dual-modal wearable system is presented integrating a piezoelectric nanogenerator (PENG) and PPG sensor with a biomimetic fingertip structure for SAS detection. A two-stage detection strategy is adopted where the self-powered PENG performs continuous preliminary screening, activating the PPG sensor only when suspicious events are detected. Combined with a Vision Transformer-based deep learning model, the high-accuracy configuration achieves 99.59% accuracy, while the low-power two-stage approach maintained 94.95% accuracy. This dual-modal wearable pulse detection system provides a practical solution for long-term SAS monitoring, overcoming the limitations of traditional PSG while maintaining high detection accuracy. The system's versatility in both home and clinical settings offers the potential for improving early detection rates and treatment outcomes for SAS patients.

A comparative study in class imbalance mitigation when working with physiological signals

Class imbalance is a common challenge that is often faced when dealing with classification tasks aiming to detect medical events that are particularly infrequent. Apnoea is an example of such events. This challenge can however be mitigated using class rebalancing algorithms. This work investigated 10 widely used data-level class imbalance mitigation methods aiming towards building a random forest (RF) model that attempts to detect apnoea events from photoplethysmography (PPG) signals acquired from the neck. Those methods are random undersampling (RandUS), random oversampling (RandOS), condensed nearest-neighbors (CNNUS), edited nearest-neighbors (ENNUS), Tomek's links (TomekUS), synthetic minority oversampling technique (SMOTE), Borderline-SMOTE (BLSMOTE), adaptive synthetic oversampling (ADASYN), SMOTE with TomekUS (SMOTETomek) and SMOTE with ENNUS (SMOTEENN). Feature-space transformation using PCA and KernelPCA was also examined as a potential way of providing better representations of the data for the class rebalancing methods to operate. This work showed that RandUS is the best option for improving the sensitivity score (up to 11%). However, it could hinder the overall accuracy due to the reduced amount of training data. On the other hand, augmenting the data with new artificial data points was shown to be a non-trivial task that needs further development, especially in the presence of subject dependencies, as was the case in this work.

Artifacts classification and apnea events detection in neck photoplethysmography signals

The novel pulse oximetry measurement site of the neck is a promising location for multi-modal physiological monitoring. Specifically, in the context of respiratory monitoring, in which it is important to have direct information about airflow. The neck makes this possible, in contrast to common photoplethysmography (PPG) sensing sites. However, this PPG signal is susceptible to artifacts that critically impair the signal quality. To fully exploit neck PPG for reliable physiological parameters extraction and apneas monitoring, this paper aims to develop two classification algorithms for artifacts and apnea detection. Features from the time, correlogram, and frequency domains were extracted. Two SVM classifiers with RBF kernels were trained for different window (W) lengths and thresholds (Thd) of corruption. For artifacts classification, the maximum performance was attained for the parameters combination of [W = 6s-Thd= 20%], with an average accuracy= 85.84%(ACC), sensitivity= 85.43%(SE) and specificity= 86.26%(SP). For apnea detection, the model [W = 10s-Thd= 50%] maximized all the performance metrics significantly (ACC= 88.25%, SE= 89.03%, SP= 87.42%). The findings of this proof of concept are significant for denoising novel neck PPG signals, and demonstrate, for the first time, that it is possible to promptly detect apnea events from neck PPG signals in an instantaneous manner. This could make a big impact in crucial real-time applications, like devices to prevent sudden-unexpected-death-in-epilepsy (SUDEP).