Open Access

Today many scientific works are using deep learning algorithms and time series, which can detect physiological events of interest. In sleep medicine, this is particularly relevant in detecting sleep apnea, specifically in detecting obstructive sleep apnea events. Deep learning algorithms with different architectures are used to achieve decent results in accuracy, sensitivity, etc. Although there are models that can reliably determine apnea and hypopnea events, another essential aspect to consider is the explainability of these models, i.e., why a model makes a particular decision. Another critical factor is how these deep learning models determine how severe obstructive sleep apnea is in patients based on the apnea-hypopnea index (AHI). Deep learning models trained by two approaches for AHI determination are exposed in this work. Approaches vary depending on the data format the models are fed: full-time series and window-based time series.

Normal breathing during sleep is essential for people’s health and well-being. Therefore, it is crucial to diagnose apnoea events at an early stage and apply appropriate therapy. Detection of sleep apnoea is a central goal of the system design described in this article. To develop a correctly functioning system, it is first necessary to define the requirements outlined in this manuscript clearly. Furthermore, the selection of appropriate technology for the measurement of respiration is of great importance. Therefore, after performing initial literature research, we have analysed in detail three different methods and made a selection of a proper one according to determined requirements. After considering all the advantages and disadvantages of the three approaches, we decided to use the impedance measurement-based one. As a next step, an initial conceptual design of the algorithm for detecting apnoea events was created. As a result, we developed an activity diagram on which the main system components and data flows are visually represented.

Home health applications have evolved over the last few decades. Assistive systems such as a data platform in connection with health devices can allow for health-related data to be automatically transmitted to a database. However, there remain significant challenges concerning intermodular communication. Central among them is the challenge of achieving interoperability, the ability of devices to communicate and share data with each other. A major goal of this project was to extend an existing data platform (COMES®) and establish working interoperability by connecting assistive devices with differing approaches. We describe this process for a sleep monitoring and a physical exercise device. Furthermore, we aimed to test this setup and the implementation with a data platform in both a laboratory and an in-home setting with 11 elderly participants. The platform modification was realized, and the relevant changes were made so that the incoming data could be processed by the data platform, as well as visually displayed in real-time. Data was recorded by the respective device and transmitted into the data server with minor disruptions. Our observations affirmed that difficulties and data loss are far more likely to occur with increasing technical complexity, in the event of instable internet connection, or when the device setup requires (elderly) subjects to take specific steps for proper functioning. We emphasize the importance for tests and evaluations of home health technologies in real-life circumstances.

Introduction Despite its high accuracy, polysomnography (PSG) has several drawbacks for diagnosing obstructive sleep apnea (OSA). Consequently, multiple portable monitors (PMs) have been proposed. Objective This systematic review aims to investigate the current literature to analyze the sets of physiological parameters captured by a PM to select the minimum number of such physiological signals while maintaining accurate results in OSA detection. Methods Inclusion and exclusion criteria for the selection of publications were established prior to the search. The evaluation of the publications was made based on one central question and several specific questions. Results The abilities to detect hypopneas, sleep time, or awakenings were some of the features studied to investigate the full functionality of the PMs to select the most relevant set of physiological signals. Based on the physiological parameters collected (one to six), the PMs were classified into sets according to the level of evidence. The advantages and the disadvantages of each possible set of signals were explained by answering the research questions proposed in the methods. Conclusions The minimum number of physiological signals detected by PMs for the detection of OSA depends mainly on the purpose and context of the sleep study. The set of three physiological signals showed the best results in the detection of OSA.

There are a large number of scientific publications that focus on the development and evaluation of artificial intelligence (AI) models for the detection of various pathologies in the field of sleep medicine. However, most of these publications do not show the process or methodology to be followed for the final deployment of these models in a complete diagnostic system (in terms of software and hardware). This is a major drawback when translating from the development or research environment to the real clinical setting. This work focuses on a methodology for deploying an AI model for sleep apnea detection with the end user in mind: the clinician. For the deployment, the transmission of data between the device, the cloud platform and the machine learning server, as well as the protocols used, were considered. In addition, the storage and visualization of the data has been taken into account so that it can be analyzed accurately by experts.