Sleep disorders are a common health condition that can affect numerous aspects of life. Obstructive sleep apnea is one of the most common disorders and is characterized by a reduction or cessation of airflow during sleep. In many countries, this disorder is usually diagnosed in sleep laboratories, by polysomnography, which is an expensive procedure involving much effort for the patient. Multiple systems have been proposed to address this situation, including performing the examination and analysis in the patient's home, using sensors to detect physiological signals that are automatically analyzed by algorithms. However, the precision of these devices is usually not enough to provide clinical diagnosis. Therefore, the objective of this review is to analyze already existing algorithms that have not been implemented on hardware but have had their performance verified by at least one experiment that aims to detect obstructive sleep apnea to predict trends. The performance of different algorithms and methods for apnea detection through the use of different sensors (pulse oximetry, electrocardiogram, respiration, sound, and combined approaches) has been evaluated. 84 original research articles published from 2003 to 2017 with the potential to be promising diagnostic tools have been selected to cover multiple solutions. This paper could provide valuable information for those researchers who want to carry out a hardware implementation of potential signal processing algorithms.

Sleep apnea is a sleep related disorder that significantly affects the population. Polysomnography, the gold standard, is expensive, inaccessible, uncomfortable and an expert technician is needed to score. Numerous researchers have proposed and implemented automatic scoring processes to address these issues, based on fewer sensors and automatic classification algorithms. Deep learning is gaining higher interest due to database availability, newly developed techniques, the possibility of producing machine created features and higher computing power that allows the algorithms to achieve better performance than the shallow classifiers. Therefore, the sleep apnea research has currently gained significant interest in deep learning. The goal of this work is to analyze the published research in the last decade, providing an answer to the research questions such as how to implement the different deep networks, what kind of pre-processing or feature extraction is needed, and the advantages and disadvantages of different kinds of networks. The employed signals, sensors, databases and implementation challenges were also considered. A systematic search was conducted on five indexing services from 2008–2018. A total of 255 papers were found and 21 were selected by considering the inclusion and exclusion criteria, using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) approach.

Sleep quality is directly related to overall wellness and can reveal symptoms of several diseases. However, the term “sleep quality” still lacks a definitional consensus and is commonly assessed in sleep labs with polysomnography, comprising high costs, or through sleep questionnaires, a highly subjective technique. Multiple methods have been proposed to address the estimation of sleep quality, and devices were developed to conduct the examination in the subject's home. The objective of this paper is to analyze the methods and the devices presented in the literature, assessing the development of objective markers that could lead to an improvement of the subjective sleep experience understanding, leading to developments in the treatment of sleep quality deficits. A systematic review was conducted, selecting research articles published from 2000 to 2018, and two research questions were formulated, specifically, “what methods for sleep quality assessment have been developed” and “what kind of measures are employed by the devices that have been developed to estimate sleep quality.” The research trend for the assessment of sleep quality is based on the sleep macrostructure, and it was verified that despite the convenience and considerable popularity among the consumers of home health monitoring of devices, such as actigraphs, the validity of these tools regarding the estimation of sleep quality still needs to be systematically examined. A detailed resume of the key findings and the identified challenges are presented, ascertaining the main gaps in the current state of the art.

In a classical classification process, automatic sleep apnea detection involves creating and selecting the features, using prior knowledge, and apply them to a classifier. A different approach is applied in this paper, where a Deep Belief Network is used for feature extraction, without using domain-specific knowledge, and then the same network is used for classification of sleep apnea. The Deep Belief Network was created by stacking Restricted Boltzmann Machines. The first two layers are autoencoder type and the last layer is of soft-max type. The initial weights are calculated using unsupervised learning and, at the end, a supervised fine-tuning of the weights is performed. Two public databases, one with 8 subjects and other with 25 subjects, are tested using tenfold cross validation. The optimum number of hidden neurons of this problem is found using a search technique. The accuracy achieved from UCD database is 85.26% and Apnea-ECG database is 97.64%.

Obstructive sleep apnea (OSA) is a common sleep disorder characterized by interrupted breathing during sleep. Because of the cost, complexity, and accessibility issue related to polysomnography, the gold standard test for apnea detection, automation of the diagnostic test based on a simpler method is desired. Several signals can be used for apnea detection, such as airflow and electrocardiogram. However, the reduction of airflow normally leads to a decrease in the blood oxygen saturation level (SpO2). This signal is usually measured by a pulse oximeter, a sensor that is cheap, portable, and easy to assemble. Therefore, the SpO2 was chosen as the reference signal. Feature based classifiers with shallow neural networks have been developed to provide apnea detection using SpO2. However, two main issues arise, the need for feature creation and the selection of the more relevant features. Deep neural networks can solve these issues by employing featureless methods. Among multiple deep classifiers that have been developed, convolution neural networks (CNN) are gaining popularity. However, the selection of the CNN structure and hyperparameters are typically done by experts, where prior knowledge is essential. With these problems in mind, an algorithm for automatic structure selection and hyper parameterization of a one dimension CNN was developed to detect OSA events using only the SpO2 signal. Three different input sizes and databases were tested, and the best model achieved an average accuracy, sensitivity, and specificity of 94%, 92%, and 96%, respectively.