Deep-spindle: An automated sleep spindle detection system for analysis of infant sleep spindles

Artificial Intelligence Can Drive Sleep Medicine

This article explores the transformative role of artificial intelligence (AI) in sleep medicine, highlighting its applications in detecting sleep microstructure patterns and integrating novel metrics. AI enhances diagnostic accuracy and objectivity, addressing inter-rater variability. AI also facilitates the classification of sleep disorders and the prediction of health outcomes. AI can drive sleep medicine to achieve deeper insights into sleep's impact on health, leading to personalized treatment strategies and improved patient care.

Sleep-wake stages classification based on single channel ECG signals by using a dynamic connection convolutional neural network

In the field of sleep medicine, identifying sleep-wake stages is crucial for evaluate of sleep quality. Until now, numerous methods have been proposed for sleep-wake classification. These methods predominantly utilize electroencephalogram (EEG) signals, achieving competitive performance in sleep-wake stage classification. However, acquiring EEG signals is both cumbersome and inconvenient. At the same time, EEG signals are very weak and are easily disturbed. In contrast EEG signal, collecting electrocardiogram (ECG) signals is relatively simple and convenient. Therefore, based on the ECG signals, we propose a simple and effective sleep-wake stages model that can be used for wearable devices. In order to extract multi-scale features of ECG signals, convolutional kernels of different sizes are designed. Then, a novel dynamic connection convolutional neural network (DCCNN) is proposed to classify sleep-wake stages. First, the DCCNN calculates the goodness of feature maps from each layer. Second, according to the goodness of different layers, select the optimal layer to form a residual module with the current layer. The proposed method was tested on sleep data from a publicly accessible databases, namely the MIT-BIH Polysomnographic Database, resulting in an best accuracy of 92.21%. The findings are similar and higher performance to those models trained with EEG signals. Moreover, when compared to state-of-the-art methods, the proposed approach's effectiveness is further demonstrated. In conclusion, this research offers a novel approach for sleep monitoring.

Detection and location of EEG events using deep learning visual inspection

The electroencephalogram (EEG) is a major diagnostic tool that provides detailed insight into the electrical activity of the brain. This signal contains a number of distinctive waveform patterns that reflect the subject's health state in relation to sleep, neurological disorders, memory functions, and more. In this regard, sleep spindles and K-complexes are two major waveform patterns of interest to specialists, who visually inspect the recordings to identify these events. The literature typically follows a traditional approach that examines the time-varying signal to identify features representing the events of interest. Even though most of these methods target individual event types, their reported performance results leave significant room for improvement. The research presented here adopts a novel approach to visually inspect the waveform, similar to how specialists work, to develop a single model that can detect and determine the location of both sleep spindles and K-complexes. The model then produces bounding boxes that accurately delineate the location of these events within the image. Several object detection algorithms (i.e., Faster R-CNN, YOLOv4, and YOLOX) and multiple backbone CNN architectures were evaluated under a wide range of conditions, revealing their true representative performance. The results show exceptional precision (>95% mAP@50) in detecting sleep spindles and K-complexes, albeit with less consistency across backbones and thresholds for the latter.

Semi automatic quantification of REM sleep without atonia in natural sleep environment

Polysomnography, the gold standard diagnostic tool in sleep medicine, is performed in an artificial environment. This might alter sleep and may not accurately reflect typical sleep patterns. While macro-structures are sensitive to environmental effects, micro-structures remain more stable. In this study we applied semi-automated algorithms to capture REM sleep without atonia (RSWA) and sleep spindles, comparing lab and home measurements. We analyzed 107 full-night recordings from 55 subjects: 24 healthy adults, 28 Parkinson's disease patients (15 RBD), and three with isolated Rem sleep behavior disorder (RBD). Sessions were manually scored. An automatic algorithm for quantifying RSWA was developed and tested against manual scoring. RSWAi showed a 60% correlation between home and lab. RBD detection achieved 83% sensitivity, 79% specificity, and 81% balanced accuracy. The algorithm accurately quantified RSWA, enabling the detection of RBD patients. These findings could facilitate more accessible sleep testing, and provide a possible alternative for screening RBD.

Non-Invasive Biosensing for Healthcare Using Artificial Intelligence: A Semi-Systematic Review

The rapid development of biosensing technologies together with the advent of deep learning has marked an era in healthcare and biomedical research where widespread devices like smartphones, smartwatches, and health-specific technologies have the potential to facilitate remote and accessible diagnosis, monitoring, and adaptive therapy in a naturalistic environment. This systematic review focuses on the impact of combining multiple biosensing techniques with deep learning algorithms and the application of these models to healthcare. We explore the key areas that researchers and engineers must consider when developing a deep learning model for biosensing: the data modality, the model architecture, and the real-world use case for the model. We also discuss key ongoing challenges and potential future directions for research in this field. We aim to provide useful insights for researchers who seek to use intelligent biosensing to advance precision healthcare.

A robust deep learning detector for sleep spindles and K-complexes: towards population norms

Sleep spindles (SSs) and K-complexes (KCs) are brain patterns involved in cognitive functions that appear during sleep. Large-scale sleep studies would benefit from precise and robust automatic sleep event detectors, capable of adapting the variability in both electroencephalography (EEG) signals and expert annotation rules. We introduce the Sleep EEG Event Detector (SEED), a deep learning system that outperforms existing approaches in SS and KC detection, reaching an F1-score of 80.5% and 83.7%, respectively, on the MASS2 dataset. SEED transfers well and requires minimal fine-tuning for new datasets and annotation styles. Remarkably, SEED substantially reduces the required amount of annotated data by using a novel pretraining approach that leverages the rule-based detector A7. An analysis of 11,224 subjects revealed that SEED's detections provide better estimates of SS population statistics than existing approaches. SEED is a powerful resource for obtaining sleep-event statistics that could be useful for establishing population norms.

Transfer Learning-based Seizure Detection on Multiple Channels of Paediatric EEGs

Epilepsy is a common neurological disease characterised by recurring seizures that affect up to 70 million people worldwide. During the first ten years of life, approximately one in every 150 children is diagnosed with epilepsy. EEG is an important tool for diagnosing seizures and other brain disorders. However, expert visual analysis of EEGs is time-consuming. In addition to reducing expert annotation time, the automatic seizure detection method is a powerful tool for assisting experts with the analysis of EEGs. Research on the automated detection of seizures in pediatric EEG has been limited. Deep learning algorithms are typically used in paediatric seizure detection methods; however, they are computationally expensive and take a long time to develop. This problem can be solved using transfer learning. In this study, we developed a transfer learning-based seizure detection method on multiple channels of paediatric EEGs. The publicly available CHB-MIT EEG dataset was used to build our method. The dataset was split into training (n=14), validation (n=4), and testing (n=6). Spectrograms generated from 10 s EEG signals with 5 s overlap were used as the input into three pre-trained transfer learning models (ResNet50, VGG16 and InceptionV3). We took care to separate the children into either the training or test set to ensure that the test set was independent. Based on the EEG test set, the method has 85.41% accuracy, 85.94% recall, and 85.49% precision. This method has the potential to assist researchers and clinicians in the automated analysis of seizures in paediatric EEGs.