China
Africa
Explore chapters and articles related to this topic
A Review of Automated Sleep Apnea Detection Using Deep Neural Network
Published in Mohan Lal Kolhe, Kailash J. Karande, Sampat G. Deshmukh, Artificial Intelligence, Internet of Things (IoT) and Smart Materials for Energy Applications, 2023
Praveen Kumar Tyagi, Dheeraj Agarwal, Pushyamitra Mishra
The level of oxygen in the bloodstream is measured by the pulse oxygen saturation level (SpO2). It is defined as follows: SpO2 increases and decreases in proportion to how effectively a patient breathes and how efficiently blood is distributed throughout the body. Due to the extreme repeated episodes of apnea, that are often followed by oxygen desaturations, substantial changes could be seen in patients with OSA. The Physionet Apnea ECG Database (AED) [21] and the University College Dublin Sleep Apnea Database (UCD Dataset) [22] were both obtained from the Physionet web page that is free and accessible. Just eight of the 70 recordings in the AED have SpO2 signals [23]. These records, which ranged in length from 7 to 10 hours and include minute-by-minute annotation [23], were used. This dataset is sampled at a rate of 50 Hz. Pathinarupothi et al. [24], Almazaydeh et al. [25], and Mostafa et al. [26] have used it from Apnea ECG Dataset. Twenty-one men and four women were among the 25 referred (identified SLA) cases at UCD [22]. Hypopnea (HYP) or obstructive (OA), central (CA), and mixed (MA) apnea are all chronically annotated throughout this database. The SpO2 signal was sampled every 8 seconds and was used by Almazaydeh et al. [25], Mostafa et al. [26], and Cen et al. [27].
Smart Textile-Based Interactive, Stretchable and Wearable Sensors for Healthcare
Published in Suresh Kaushik, Vijay Soni, Efstathia Skotti, Nanosensors for Futuristic Smart and Intelligent Healthcare Systems, 2022
Abbas Ahmed, Bapan Adak, Samrat Mukhopadhyay
circuit, the corresponding signals generated from each sensing unit are recorded, ensuring the final analog output from the smart textile which could accurately express the sleeping posture and physiological signals of a subject during sleep, as depicted in Figure 4(c–e). In addition, the smart textile was employed to reduce sudden death by monitoring obstructive sleep apnea-hypopnea syndrome (OSAHS). The smart textile embedded OSAHS supervision and intervening system could automatically interfere if the duration of apnea episodes exceeds 10 s along with a supine position, and based on the actual needs the time duration can be regulated. Moreover, a bulb or audible alarm will be activated to quickly wake up the patient and to breathe normally, Figure 4(f,g). Additionally, an alert may automatically be transferred to doctors for timely treatment, if the patient couldn’t manage to wake up in time.
Evaluating the Impact of Sleep Disruptions in Women through Automated Analysis
Published in Erick C. Jones, Supply Chain Engineering and Logistics Handbook, 2020
Shalini Gupta, Felicia Jefferson, Erick C. Jones
OSA is a common sleep disorder that is caused by complete or partial functional impairment of the upper airway dilator muscle, which leads to apnea/hypopnea-induced oxygen desaturation, repetitive micro-arousals, and disturbed sleep [3]. Thus, OSA patients suffer from sleep fragmentation and chronic sleep deprivation, with common symptoms of daytime sleepiness, tiredness, snoring, etc. [6]. When adequate apnea and hypopnea episodes are present together with these symptoms, OSA is labeled as obstructive sleep apnea syndrome (OSAS) [16]. Various factors have been identified as predictors of OSA including oropharyngeal narrowing, neck circumference, and BMI. In general, factors that predispose individuals to increased collapsibility of the upper airway are major risk factors for OSA [20]. Among all of them, obesity is the greatest risk factor for OSA due to its high prevalence [21]. Clinical diagnosis of OSA requires baseline polysomnography (PSG) of patients and a Continuous Positive Airway Pressure (CPAP) titration study, while home studies are increasingly being used as screening tests [34].
A noise-robust Koopman spectral analysis of an intermittent dynamics method for complex systems: a case study in pathophysiological processes of obstructive sleep apnea
Published in IISE Transactions on Healthcare Systems Engineering, 2023
Phat K. Huynh, Arveity R. Setty, Trung B. Le, Trung Q. Le
We performed the intermittent forcing analysis on the pathophysiological processes of obstructive sleep apnea (OSA)—a common sleep breathing disorder with long-term consequences on the cardiorespiratory system. We selected the Apnea-ECG Database (Penzel et al., 2000) from Physionet.org to investigate the nonlinear intermittent behaviors. The data set has recordings of 70 OSA patients, and the recordings vary from 7 hours to nearly 10 hours each. Each recording comprises a continuous digitized ECG signal and apnea-hypopnea event expert-labeled annotations. The annotations consist of binary-coded events for each minute of the recording: “Normal breathing” (N) or “Disordered breathing” (A). The disordered breathing event may correspond to a single apnea episode, a hypopnea episode or a longer sequence of apneas and hypopneas. The severity of OSA is measured by an apnea-hypopnea index (AHI) that indicates the number of apneas or hypopneas per hour over the sleep study. Records of 22 OSA patients were shortlisted to be included in our HAVOK and intermittency analysis; we do not consider healthy (normal) subjects and patients with very mild OSA (AHI < 5) because healthy and very mild apnea cases do not exhibit significant intermittent switching between apnea-hypopnea events and normal episodes.
An Advanced Circular Adaptive Search Butterfly Optimization Algorithm for the CNN-based Sleep Apnea Detection Approach
Published in IETE Journal of Research, 2022
The dataset used in this approach is the database of signals collected from St. Vincent University Hospital/University College [37]. This database has recordings of 25 persons including 21 males and four females. The signals include PSG recordings recorded for a full night. The PSG recordings are taken for patients with a suspected sleep disorder. Every signal is recorded for around 5.9–7.7. The recordings are provided with annotation files, in which the details of sleep apnea/hypopnea events are specified. The PSG recordings were obtained using the JaegerToennies system. A modified V2 lead is employed to record ECG and a finger pulse oximeter is employed to record the SpO2 signal. A sleep technologist executed the staging of sleep by means of the full polysomnography record with different types of sleep apnea such as obstructive sleep apnea, mixed apnea, central apnea and hypopnea. In the considered database, among 25 persons, 2 persons have apnea disorder. SpO2 samples from the database are taken at the rate of 8 Hz. And the signals are segmented into 1-min epochs. The epoch is labeled as “apnea” if there exists an apnea event for a minimum of 5 s continuously; else, the epoch is labeled as “normal”. Thus, 222 apneic epochs and 9359 normal epochs were obtained. A total of 9581 epochs are present in the dataset.
Introduce structural equation modelling to machine learning problems for building an explainable and persuasive model
Published in SICE Journal of Control, Measurement, and System Integration, 2021
Jiarui Li, Tetsuo Sawaragi, Yukio Horiguchi
Before collecting data, we review the factors relating to OSA. According to the recently published literature [13–17], OSA relates closely with the following aspects: age, gender, body mass index (BMI), sleep quality including daytime tiredness, snore, health status, and underlying diseases. Thus, we collected questionnaire data considering these factors – the data used for analysis comes from the Sleep Heart Health Study (SHHS) database [18,19]. Apnea-Hypopnea Index (AHI) data can be made on the basis of PSG collection. Among all 5408 participants, 3931 subjects completed all data collection and had no history of OSA diagnosis. is an indicator of suffering from OSA. A total of 70% of subjects had an in our study (3931 in total, 1863 males, 2068 females, age ).