Sleep apnea is a serious sleep-related breathing disorder that is common and can impact health if left untreated. Currently the traditional method for screening and diagnosis is overnight polysomnography. Polysomnography is expensive and takes a lot of time, and is not practical for screening large groups of people. In this paper, we explored a more accessible option, using respiratory audio recordings to spot signs of apnea.We utilized 18 audio files.The approach involved converting breathing sounds into spectrograms, balancing the dataset by oversampling apnea segments, and applying class weights to reduce bias toward the majority class. The model reached a recall of 90.55 for apnea detection. Intentionally, prioritizing catching apnea events over general accuracy. Despite low precision,the high recall suggests potential as a low-cost screening tool that could be used at home or in basic clinical setups, potentially helping identify at-risk individuals much earlier.

Sleep apnea, a prevalent sleep disorder, involves repeated episodes of breathing interruptions during sleep, leading to various health complications, including cognitive impairments, high blood pressure, heart disease, stroke, and even death. One of the main challenges in diagnosing and treating sleep apnea is identifying individuals at risk. The current gold standard for diagnosis, Polysomnography (PSG), is costly, labor intensive, and inconvenient, often resulting in poor quality sleep data. This paper presents a novel approach to the detection of sleep apnea using a Convolutional Neural Network (CNN) trained on single channel EEG data. The proposed CNN achieved an accuracy of 85.1% and a Matthews Correlation Coefficient (MCC) of 0.22, demonstrating a significant potential for home based applications by addressing the limitations of PSG in automated sleep apnea detection. Key contributions of this work also include the development of a comprehensive preprocessing pipeline with an Infinite Impulse Response (IIR) Butterworth filter, a dataset construction method providing broader temporal context, and the application of SMOTETomek to address class imbalance. This research underscores the feasibility of transitioning from traditional laboratory based diagnostics to more accessible, automated home based solutions, improving patient outcomes and broadening the accessibility of sleep disorder diagnostics.

This year marks the 10th anniversary of the Apple Watch, the top-selling rectangular wearable that can be seen on the wrists of millions of iPhone owners. As befits a landmark anniversary, this year's flagship Apple Watch 10 has gotten an updated design that is much thinner and lighter than the previous Watch Series 9, along with a new, jet black finish. Every year, Apple adds new health features to the watch. This year, that feature is sleep apnea detection. The most highly anticipated health feature was tracking for hypertension, or high blood pressure, and that has not shown up on the Apple Watch yet--probably because earlier this year, Apple was ordered to stop selling watches with blood oxygen sensing because of a patent dispute with Masimo Corp.

Apple is bringing sleep apnea detection to the most recent generations of its Watch, the company announced today. At the iPhones 16 launch event, Apple revealed the feature would come to the new Series 10, as well as the Series 9 and Ultra 2. If you wear your watch while you sleep, you'll get an alert in the morning if symptoms are detected through the night, urging you to visit your clinician. The data for this will be collated in the Health app on the iPhone. Rather than using oxygen saturation, which would be the logical approach, Apple says it's using motion tracking. This is likely related to the messy patent battle surrounding the blood oxygen sensor in the Watch that has stymied the company's work in this area.

Polysomnography (PSG) is a type of sleep study that records multimodal physiological signals and is widely used for purposes such as sleep staging and respiratory event detection. Conventional machine learning methods assume that each sleep study is associated with a fixed set of observed modalities and that all modalities are available for each sample. However, noisy and missing modalities are a common issue in real-world clinical settings. In this study, we propose a comprehensive pipeline aiming to compensate for the missing or noisy modalities when performing sleep apnea detection. Unlike other existing studies, our proposed model works with any combination of available modalities. Our experiments show that the proposed model outperforms other state-of-the-art approaches in sleep apnea detection using various subsets of available data and different levels of noise, and maintains its high performance (AUROC>0.9) even in the presence of high levels of noise or missingness. This is especially relevant in settings where the level of noise and missingness is high (such as pediatric or outside-of-clinic scenarios).

Sleep apnea (SA) is a significant respiratory condition that poses a major global health challenge. Previous studies have investigated several machine and deep learning models for electrocardiogram (ECG)-based SA diagnoses. Despite these advancements, conventional feature extractions derived from ECG signals, such as R-peaks and RR intervals, may fail to capture crucial information encompassed within the complete PQRST segments. In this study, we propose an innovative approach to address this diagnostic gap by delving deeper into the comprehensive segments of the ECG signal. The proposed methodology draws inspiration from Matrix Profile algorithms, which generate an Euclidean distance profile from fixed-length signal subsequences. From this, we derived the Min Distance Profile (MinDP), Max Distance Profile (MaxDP), and Mean Distance Profile (MeanDP) based on the minimum, maximum, and mean of the profile distances, respectively. To validate the effectiveness of our approach, we use the modified LeNet-5 architecture as the primary CNN model, along with two existing lightweight models, BAFNet and SE-MSCNN, for ECG classification tasks. Our extensive experimental results on the PhysioNet Apnea-ECG dataset revealed that with the new feature extraction method, we achieved a per-segment accuracy up to 92.11 \% and a per-recording accuracy of 100\%. Moreover, it yielded the highest correlation compared to state-of-the-art methods, with a correlation coefficient of 0.989. By introducing a new feature extraction method based on distance relationships, we enhanced the performance of certain lightweight models, showing potential for home sleep apnea test (HSAT) and SA detection in IoT devices. The source code for this work is made publicly available in GitHub: https://github.com/vinuni-vishc/MPCNN-Sleep-Apnea.

Sleep apnea is a common respiratory disorder characterized by breathing pauses during the night. Consequences of untreated sleep apnea can be severe. Still, many people remain undiagnosed due to shortages of hospital beds and trained sleep technicians. To assist in the diagnosis process, automated detection methods are being developed. Recent works have demonstrated that deep learning models can extract useful information from raw respiratory data and that such models can be used as a robust sleep apnea detector. However, trained sleep technicians take into account multiple sensor signals when annotating sleep recordings instead of relying on a single respiratory estimate. To improve the predictive performance and reliability of the models, early and late sensor fusion methods are explored in this work. In addition, a novel late sensor fusion method is proposed which uses backward shortcut connections to improve the learning of the first stages of the models. The performance of these fusion methods is analyzed using CNN as well as LSTM deep learning base-models. The results demonstrate a significant and consistent improvement in predictive performance over the single sensor methods and over the other explored sensor fusion methods, by using the proposed sensor fusion method with backward shortcut connections.