A deep learning model based on the combination of convolutional and recurrent neural networks to enhance pulse oximetry ability to classify sleep stages in children with sleep apnea.

Characterization of sleep stages is essential in the diagnosis of sleep-related disorders but relies on manual scoring of overnight polysomnography (PSG) recordings, which is onerous and labor-intensive. Accordingly, we aimed to develop an accurate deep-learning model for sleep staging in children suffering from pediatric obstructive sleep apnea (OSA) using pulse oximetry signals. For this purpose, pulse rate (PR) and blood oxygen saturation (SpO2) from 429 childhood OSA patients were analyzed. A CNN-RNN architecture fed with PR and SpO2 signals was developed to automatically classify wake (W), non-Rapid Eye Movement (NREM), and REM sleep stages. This architecture was composed of: (i) a convolutional neural network (CNN), which learns stage-related features from raw PR and SpO2 data; and (ii) a recurrent neural network (RNN), which models the temporal distribution of the sleep stages. The proposed CNN-RNN model showed a high performance for the automated detection of W/NREM/REM sleep stages (86.0% accuracy and 0.743 Cohen's kappa). Furthermore, the total sleep time estimated for each children using the CNN-RNN model showed high agreement with the manually derived from PSG (intra-class correlation coefficient = 0.747). These results were superior to previous works using CNN-based deep-learning models for automatic sleep staging in pediatric OSA patients from pulse oximetry signals. Therefore, the combination of CNN and RNN allows to obtain additional information from raw PR and SpO2 data related to sleep stages, thus being useful to automatically score sleep stages in pulse oximetry tests for children evaluated for suspected OSA.Clinical Relevance-This research establishes the usefulness of a CNN-RNN architecture to automatically score sleep stages in pulse oximetry tests for pediatric OSA diagnosis.

An explainable deep-learning model to stage sleep states in children and propose novel EEG-related patterns in sleep apnea.

Automatic deep-learning models used for sleep scoring in children with obstructive sleep apnea (OSA) are perceived as black boxes, limiting their implementation in clinical settings. Accordingly, we aimed to develop an accurate and interpretable deep-learning model for sleep staging in children using single-channel electroencephalogram (EEG) recordings. We used EEG signals from the Childhood Adenotonsillectomy Trial (CHAT) dataset (n = 1637) and a clinical sleep database (n = 980). Three distinct deep-learning architectures were explored to automatically classify sleep stages from a single-channel EEG data. Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable artificial intelligence (XAI) algorithm, was then applied to provide an interpretation of the singular EEG patterns contributing to each predicted sleep stage. Among the tested architectures, a standard convolutional neural network (CNN) demonstrated the highest performance for automated sleep stage detection in the CHAT test set (accuracy = 86.9% and five-class kappa = 0.827). Furthermore, the CNN-based estimation of total sleep time exhibited strong agreement in the clinical dataset (intra-class correlation coefficient = 0.772). Our XAI approach using Grad-CAM effectively highlighted the EEG features associated with each sleep stage, emphasizing their influence on the CNN's decision-making process in both datasets. Grad-CAM heatmaps also allowed to identify and analyze epochs within a recording with a highly likelihood to be misclassified, revealing mixed features from different sleep stages within these epochs. Finally, Grad-CAM heatmaps unveiled novel features contributing to sleep scoring using a single EEG channel. Consequently, integrating an explainable CNN-based deep-learning model in the clinical environment could enable automatic sleep staging in pediatric sleep apnea tests.

Derivation and validation of a blood biomarker score for 2-day mortality prediction from prehospital care: a multicenter, cohort, EMS-based study.

Identifying potentially life-threatening diseases is a key challenge for emergency medical services. This study aims at examining the role of different prehospital biomarkers from point-of-care testing to derive and validate a score to detect 2-day in-hospital mortality. We conducted a prospective, observational, prehospital, ongoing, and derivation-validation study in three Spanish provinces, in adults evacuated by ambulance and admitted to the emergency department. A total of 23 ambulance-based biomarkers were collected from each patient. A biomarker score based on logistic regression was fitted to predict 2-day mortality from an optimum subset of variables from prehospital blood analysis, obtained through an automated feature selection stage. 2806 cases were analyzed, with a median age of 68 (interquartile range 51-81), 42.3% of women, and a 2-day mortality rate of 5.5% (154 non-survivors). The blood biomarker score was constituted by the partial pressure of carbon dioxide, lactate, and creatinine. The score fitted with logistic regression using these biomarkers reached a high performance to predict 2-day mortality, with an AUC of 0.933 (95% CI 0.841-0.973). The following risk levels for 2-day mortality were identified from the score: low risk (score < 1), where only 8.2% of non-survivors were assigned to; medium risk (1 ≤ score < 4); and high risk (score ≥ 4), where the 2-day mortality rate was 57.6%. The novel blood biomarker score provides an excellent association with 2-day in-hospital mortality, as well as real-time feedback on the metabolic-respiratory patient status. Thus, this score can help in the decision-making process at critical moments in life-threatening situations.

Conventional Machine Learning Methods Applied to the Automatic Diagnosis of Sleep Apnea.

The overnight polysomnography shows a range of drawbacks to diagnose obstructive sleep apnea (OSA) that have led to the search for artificial intelligence-based alternatives. Many classic machine learning methods have been already evaluated for this purpose. In this chapter, we show the main approaches found in the scientific literature along with the most used data to develop the models, useful and large easily available databases, and suitable methods to assess performances. In addition, a range of results from selected studies are presented as examples of these methods. Very high diagnostic performances are reported in these results regardless of the approaches taken. This leads us to conclude that conventional machine learning methods are useful techniques to develop new OSA diagnosis simplification proposals and to act as benchmark for other more recent methods such as deep learning.

ECG and Heart Rate Variability in Sleep-Related Breathing Disorders.

Here we discuss the current perspectives of comprehensive heart rate variability (HRV) analysis in electrocardiogram (ECG) signals as a non-invasive and reliable measure to assess autonomic function in sleep-related breathing disorders (SDB). It is a tool of increasing interest as different facets of HRV can be implemented to screen and diagnose SDB, monitor treatment efficacy, and prognose adverse cardiovascular outcomes in patients with sleep apnea. In this context, the technical aspects, pathophysiological features, and clinical applications of HRV are discussed to explore its usefulness in better understanding SDB.

Oximetry Indices in the Management of Sleep Apnea: From Overnight Minimum Saturation to the Novel Hypoxemia Measures.

Obstructive sleep apnea (OSA) is a multidimensional disease often underdiagnosed due to the complexity and unavailability of its standard diagnostic method: the polysomnography. Among the alternative abbreviated tests searching for a compromise between simplicity and accurateness, oximetry is probably the most popular. The blood oxygen saturation (SpO2) signal is characterized by a near-constant profile in healthy subjects breathing normally, while marked drops (desaturations) are linked to respiratory events. Parameterization of the desaturations has led to a great number of indices of severity assessment commonly used to assist in OSA diagnosis. In this chapter, the main methodologies used to characterize the overnight oximetry profile are reviewed, from visual inspection and simple statistics to complex measures involving signal processing and pattern recognition techniques. We focus on the individual performance of each approach, but also on the complementarity among the great amount of indices existing in the state of the art, looking for the most relevant oximetric feature subset. Finally, a quick overview of SpO2-based deep learning applications for OSA management is carried out, where the raw oximetry signal is analyzed without previous parameterization. Our research allows us to conclude that all the methodologies (conventional, time, frequency, nonlinear, and hypoxemia-based) demonstrate high ability to provide relevant oximetric indices, but only a reduced set provide non-redundant complementary information leading to a significant performance increase. Finally, although oximetry is a robust tool, greater standardization and prospective validation of the measures derived from complex signal processing techniques are still needed to homogenize interpretation and increase generalizability.

Deep-Learning Model Based on Convolutional Neural Networks to Classify Apnea-Hypopnea Events from the Oximetry Signal.

Automated analysis of the blood oxygen saturation (SpO2) signal from nocturnal oximetry has shown usefulness to simplify the diagnosis of obstructive sleep apnea (OSA), including the detection of respiratory events. However, the few preceding studies using SpO2 recordings have focused on the automated detection of respiratory events versus normal respiration, without making any distinction between apneas and hypopneas. In this sense, the characteristics of oxygen desaturations differ between obstructive apnea and hypopnea episodes. In this chapter, we use the SpO2 signal along with a convolutional neural network (CNN)-based deep-learning architecture for the automatic identification of apnea and hypopnea events. A total of 398 SpO2 signals from adult OSA patients were used for this purpose. A CNN architecture was trained using 30-s epochs from the SpO2 signal for the automatic classification of three classes: normal respiration, apnea, and hypopnea. Then, the apnea index (AI), the hypopnea index (HI), and the apnea-hypopnea index (AHI) were obtained by aggregating the outputs of the CNN for each subject (AICNN, HICNN, and AHICNN). This model showed a promising diagnostic performance in an independent test set, with 80.3% 3-class accuracy and 0.539 3-class Cohen's kappa for the classification of respiratory events. Furthermore, AICNN, HICNN, and AHICNN showed a high agreement with the values obtained from the standard PSG: 0.8023, 0.6774, and 0.8466 intra-class correlation coefficients (ICCs), respectively. This suggests that CNN can be used to analyze SpO2 recordings for the automated diagnosis of OSA in at-home oximetry tests.

A 2D convolutional neural network to detect sleep apnea in children using airflow and oximetry.

The gold standard approach to diagnose obstructive sleep apnea (OSA) in children is overnight in-lab polysomnography (PSG), which is labor-intensive for clinicians and onerous to healthcare systems and families. Simplification of PSG should enhance availability and comfort, and reduce complexity and waitlists. Airflow (AF) and oximetry (SpO2) signals summarize most of the information needed to detect apneas and hypopneas, but automatic analysis of these signals using deep-learning algorithms has not been extensively investigated in the pediatric context. The aim of this study was to evaluate a convolutional neural network (CNN) architecture based on these two signals to estimate the severity of pediatric OSA. PSG-derived AF and SpO2 signals from the Childhood Adenotonsillectomy Trial (CHAT) database (1638 recordings), as well as from a clinical database (974 recordings), were analyzed. A 2D CNN fed with AF and SpO2 signals was implemented to estimate the number of apneic events, and the total apnea-hypopnea index (AHI) was estimated. A training-validation-test strategy was used to train the CNN, adjust the hyperparameters, and assess the diagnostic ability of the algorithm, respectively. Classification into four OSA severity levels (no OSA, mild, moderate, or severe) reached 4-class accuracy and Cohen's Kappa of 72.55% and 0.6011 in the CHAT test set, and 61.79% and 0.4469 in the clinical dataset, respectively. Binary classification accuracy using AHI cutoffs 1, 5 and 10 events/h ranged between 84.64% and 94.44% in CHAT, and 84.10%-90.26% in the clinical database. The proposed CNN-based architecture achieved high diagnostic ability in two independent databases, outperforming previous approaches that employed SpO2 signals alone, or other classical feature-engineering approaches. Therefore, analysis of AF and SpO2 signals using deep learning can be useful to deploy reliable computer-aided diagnostic tools for childhood OSA.

Heart rate variability as a potential biomarker of pediatric obstructive sleep apnea resolution.

STUDY OBJECTIVES: Pediatric obstructive sleep apnea (OSA) affects cardiac autonomic regulation, altering heart rate variability (HRV). Although changes in classical HRV parameters occur after OSA treatment, they have not been evaluated as reporters of OSA resolution. Specific frequency bands (named BW1, BW2, and BWRes) have been recently identified in OSA. We hypothesized that changes with treatment in these spectral bands can reliably identify changes in OSA severity and reflect OSA resolution. METHODS: Four hundred and four OSA children (5-9.9 years) from the prospective Childhood Adenotonsillectomy Trial were included; 206 underwent early adenotonsillectomy (eAT), while 198 underwent watchful waiting with supportive care (WWSC). HRV changes from baseline to follow-up were computed for classical and OSA-related frequency bands. Causal mediation analysis was conducted to evaluate how treatment influences HRV through mediators such as OSA resolution and changes in disease severity. Disease resolution was initially assessed by considering only obstructive events, and was followed by adding central apneas to the analyses. RESULTS: Treatment, regardless of eAT or WWSC, affects HRV activity, mainly in the specific frequency band BW2 (0.028-0.074 Hz). Furthermore, only changes in BW2 were specifically attributable to all OSA resolution mediators. HRV activity in BW2 also showed statistically significant differences between resolved and non-resolved OSA. CONCLUSIONS: OSA treatment affects HRV activity in terms of change in severity and disease resolution, especially in OSA-related BW2 frequency band. This band allowed to differentiate HRV activity between children with and without resolution, so we propose BW2 as potential biomarker of pediatric OSA resolution. CLINICAL TRIAL REGISTRATION: Childhood Adenotonsillectomy Trial, NCT00560859, https://sleepdata.org/datasets/chat.

Automatic Sleep Staging in Children with Sleep Apnea using Photoplethysmography and Convolutional Neural Networks.

Sleep staging is of paramount importance in children with suspicion of pediatric obstructive sleep apnea (OSA). Complexity, cost, and intrusiveness of overnight polysomnography (PSG), the gold standard, have led to the search for alternative tests. In this sense, the photoplethysmography signal (PPG) carries useful information about the autonomous nervous activity associated to sleep stages and can be easily acquired in pediatric sleep apnea home tests with a pulse oximeter. In this study, we use the PPG signal along with convolutional neural networks (CNN), a deep-learning technique, for the automatic identification of the three main levels of sleep: wake (W), rapid eye movement (REM), and non-REM sleep. A database of 366 PPG recordings from pediatric OSA patients is involved in the study. A CNN architecture was trained using 30-s epochs from the PPG signal for three-stage sleep classification. This model showed a promising diagnostic performance in an independent test set, with 78.2% accuracy and 0.57 Cohen's kappa for W/NREM/REM classification. Furthermore, the percentage of time in wake stage obtained for each subject showed no statistically significant differences with the manually scored from PSG. These results were superior to the only state-of-the-art study focused on the analysis of the PPG signal in the automated detection of sleep stages in children suffering from OSA. This suggests that CNN can be used along with PPG recordings for sleep stages scoring in pediatric home sleep apnea tests.

The Different Facets of Heart Rate Variability in Obstructive Sleep Apnea.

Obstructive sleep apnea (OSA), a heterogeneous and multifactorial sleep related breathing disorder with high prevalence, is a recognized risk factor for cardiovascular morbidity and mortality. Autonomic dysfunction leads to adverse cardiovascular outcomes in diverse pathways. Heart rate is a complex physiological process involving neurovisceral networks and relative regulatory mechanisms such as thermoregulation, renin-angiotensin-aldosterone mechanisms, and metabolic mechanisms. Heart rate variability (HRV) is considered as a reliable and non-invasive measure of autonomic modulation response and adaptation to endogenous and exogenous stimuli. HRV measures may add a new dimension to help understand the interplay between cardiac and nervous system involvement in OSA. The aim of this review is to introduce the various applications of HRV in different aspects of OSA to examine the impaired neuro-cardiac modulation. More specifically, the topics covered include: HRV time windows, sleep staging, arousal, sleepiness, hypoxia, mental illness, and mortality and morbidity. All of these aspects show pathways in the clinical implementation of HRV to screen, diagnose, classify, and predict patients as a reasonable and more convenient alternative to current measures.

Wavelet Analysis of Overnight Airflow to Detect Obstructive Sleep Apnea in Children.

This study focused on the automatic analysis of the airflow signal (AF) to aid in the diagnosis of pediatric obstructive sleep apnea (OSA). Thus, our aims were: (i) to characterize the overnight AF characteristics using discrete wavelet transform (DWT) approach, (ii) to evaluate its diagnostic utility, and (iii) to assess its complementarity with the 3% oxygen desaturation index (ODI3). In order to reach these goals, we analyzed 946 overnight pediatric AF recordings in three stages: (i) DWT-derived feature extraction, (ii) feature selection, and (iii) pattern recognition. AF recordings from OSA patients showed both lower detail coefficients and decreased activity associated with the normal breathing band. Wavelet analysis also revealed that OSA disturbed the frequency and energy distribution of the AF signal, increasing its irregularity. Moreover, the information obtained from the wavelet analysis was complementary to ODI3. In this regard, the combination of both wavelet information and ODI3 achieved high diagnostic accuracy using the common OSA-positive cutoffs: 77.97%, 81.91%, and 90.99% (AdaBoost.M2), and 81.96%, 82.14%, and 90.69% (Bayesian multi-layer perceptron) for 1, 5, and 10 apneic events/hour, respectively. Hence, these findings suggest that DWT properly characterizes OSA-related severity as embedded in nocturnal AF, and could simplify the diagnosis of pediatric OSA.

Heart rate variability during wakefulness as a marker of obstructive sleep apnea severity.

STUDY OBJECTIVES: Patients with obstructive sleep apnea (OSA) exhibit heterogeneous heart rate variability (HRV) during wakefulness and sleep. We investigated the influence of OSA severity on HRV parameters during wakefulness in a large international clinical sample. METHODS: 1247 subjects (426 without OSA and 821 patients with OSA) were enrolled from the Sleep Apnea Global Interdisciplinary Consortium. HRV parameters were calculated during a 5-minute wakefulness period with spontaneous breathing prior to the sleep study, using time-domain, frequency-domain and nonlinear methods. Differences in HRV were evaluated among groups using analysis of covariance, controlling for relevant covariates. RESULTS: Patients with OSA showed significantly lower time-domain variations and less complexity of heartbeats compared to individuals without OSA. Those with severe OSA had remarkably reduced HRV compared to all other groups. Compared to non-OSA patients, those with severe OSA had lower HRV based on SDNN (adjusted mean: 37.4 vs. 46.2 ms; p < 0.0001), RMSSD (21.5 vs. 27.9 ms; p < 0.0001), ShanEn (1.83 vs. 2.01; p < 0.0001), and Forbword (36.7 vs. 33.0; p = 0.0001). While no differences were found in frequency-domain measures overall, among obese patients there was a shift to sympathetic dominance in severe OSA, with a higher LF/HF ratio compared to obese non-OSA patients (4.2 vs. 2.7; p = 0.009). CONCLUSIONS: Time-domain and nonlinear HRV measures during wakefulness are associated with OSA severity, with severe patients having remarkably reduced and less complex HRV. Frequency-domain measures show a shift to sympathetic dominance only in obese OSA patients. Thus, HRV during wakefulness could provide additional information about cardiovascular physiology in OSA patients. CLINICAL TRIAL INFORMATION: A Prospective Observational Cohort to Study the Genetics of Obstructive Sleep Apnea and Associated Co-Morbidities (German Clinical Trials Register - DKRS, DRKS00003966) https://www.drks.de/drks_web/navigate.do?navigationId=trial.HTML&TRIAL_ID=DRKS00003966.

Bispectral analysis of overnight airflow to improve the pediatric sleep apnea diagnosis.

Pediatric Obstructive Sleep Apnea (OSA) is a respiratory disease whose diagnosis is performed through overnight polysomnography (PSG). Since it is a complex, time-consuming, expensive, and labor-intensive test, simpler alternatives are being intensively sought. In this study, bispectral analysis of overnight airflow (AF) signal is proposed as a potential approach to replace PSG when indicated. Thus, our objective was to characterize AF through bispectrum, and assess its performance to diagnose pediatric OSA. This characterization was conducted using 13 bispectral features from 946 AF signals. The oxygen desaturation index ≥3% (ODI3), a common clinical measure of OSA severity, was also obtained to evaluate its complementarity to the AF bispectral analysis. The fast correlation-based filter (FCBF) and a multi-layer perceptron (MLP) were used for subsequent automatic feature selection and pattern recognition stages. FCBF selected 3 bispectral features and ODI3, which were used to train a MLP model with ability to estimate apnea-hypopnea index (AHI). The model reached 82.16%, 82.49%, and 90.15% accuracies for the common AHI cut-offs 1, 5, and 10 events/h, respectively. The different bispectral approaches used to characterize AF in children provided complementary information. Accordingly, bispectral analysis showed that the occurrence of apneic events decreases the non-gaussianity and non-linear interaction of the AF harmonic components, as well as the regularity of the respiratory patterns. Moreover, the bispectral information from AF also showed complementarity with ODI3. Our findings suggest that AF bispectral analysis may serve as a useful tool to simplify the diagnosis of pediatric OSA, particularly for children with moderate-to-severe OSA.

A Convolutional Neural Network Architecture to Enhance Oximetry Ability to Diagnose Pediatric Obstructive Sleep Apnea.

This study aims at assessing the usefulness of deep learning to enhance the diagnostic ability of oximetry in the context of automated detection of pediatric obstructive sleep apnea (OSA). A total of 3196 blood oxygen saturation (SpO2) signals from children were used for this purpose. A convolutional neural network (CNN) architecture was trained using 20-min SpO2 segments from the training set (859 subjects) to estimate the number of apneic events. CNN hyperparameters were tuned using Bayesian optimization in the validation set (1402 subjects). This model was applied to three test sets composed of 312, 392, and 231 subjects from three independent databases, in which the apnea-hypopnea index (AHI) estimated for each subject (AHICNN) was obtained by aggregating the output of the CNN for each 20-min SpO2 segment. AHICNN outperformed the 3% oxygen desaturation index (ODI3), a clinical approach, as well as the AHI estimated by a conventional feature-engineering approach based on multi-layer perceptron (AHIMLP). Specifically, AHICNN reached higher four-class Cohen's kappa in the three test databases than ODI3 (0.515 vs 0.417, 0.422 vs 0.372, and 0.423 vs 0.369) and AHIMLP (0.515 vs 0.377, 0.422 vs 0.381, and 0.423 vs 0.306). In addition, our proposal outperformed state-of-the-art studies, particularly for the AHI severity cutoffs of 5 e/h and 10 e/h. This suggests that the information automatically learned from the SpO2 signal by deep-learning techniques helps to enhance the diagnostic ability of oximetry in the context of pediatric OSA.

EEG-Inception: A Novel Deep Convolutional Neural Network for Assistive ERP-Based Brain-Computer Interfaces.

In recent years, deep-learning models gained attention for electroencephalography (EEG) classification tasks due to their excellent performance and ability to extract complex features from raw data. In particular, convolutional neural networks (CNN) showed adequate results in brain-computer interfaces (BCI) based on different control signals, including event-related potentials (ERP). In this study, we propose a novel CNN, called EEG-Inception, that improves the accuracy and calibration time of assistive ERP-based BCIs. To the best of our knowledge, EEG-Inception is the first model to integrate Inception modules for ERP detection, which combined efficiently with other structures in a light architecture, improved the performance of our approach. The model was validated in a population of 73 subjects, of which 31 present motor disabilities. Results show that EEG-Inception outperforms 5 previous approaches, yielding significant improvements for command decoding accuracy up to 16.0%, 10.7%, 7.2%, 5.7% and 5.1% in comparison to rLDA, xDAWN + Riemannian geometry, CNN-BLSTM, DeepConvNet and EEGNet, respectively. Moreover, EEG-Inception requires very few calibration trials to achieve state-of-the-art performances taking advantage of a novel training strategy that combines cross-subject transfer learning and fine-tuning to increase the feasibility of this approach for practical use in assistive applications.

Assessment of Nocturnal Autonomic Cardiac Imbalance in Positional Obstructive Sleep Apnea. A Multiscale Nonlinear Approach.

Positional obstructive sleep apnea (POSA) is a major phenotype of sleep apnea. Supine-predominant positional patients are frequently characterized by milder symptoms and less comorbidity due to a lower age, body mass index, and overall apnea-hypopnea index. However, the bradycardia-tachycardia pattern during apneic events is known to be more severe in the supine position, which could affect the cardiac regulation of positional patients. This study aims at characterizing nocturnal heart rate modulation in the presence of POSA in order to assess potential differences between positional and non-positional patients. Patients showing clinical symptoms of suffering from a sleep-related breathing disorder performed unsupervised portable polysomnography (PSG) and simultaneous nocturnal pulse oximetry (NPO) at home. Positional patients were identified according to the Amsterdam POSA classification (APOC) criteria. Pulse rate variability (PRV) recordings from the NPO readings were used to assess overnight cardiac modulation. Conventional cardiac indexes in the time and frequency domains were computed. Additionally, multiscale entropy (MSE) was used to investigate the nonlinear dynamics of the PRV recordings in POSA and non-POSA patients. A total of 129 patients (median age 56.0, interquartile range (IQR) 44.8-63.0 years, median body mass index (BMI) 27.7, IQR 26.0-31.3 kg/m2) were classified as POSA (37 APOC I, 77 APOC II, and 15 APOC III), while 104 subjects (median age 57.5, IQR 49.0-67.0 years, median BMI 29.8, IQR 26.6-34.7 kg/m2) comprised the non-POSA group. Overnight PRV recordings from positional patients showed significantly higher disorderliness than non-positional subjects in the smallest biological scales of the MSE profile (τ = 1: 0.25, IQR 0.20-0.31 vs. 0.22, IQR 0.18-0.27, p < 0.01) (τ = 2: 0.41, IQR 0.34-0.48 vs. 0.37, IQR 0.29-0.42, p < 0.01). According to our findings, nocturnal heart rate regulation is severely affected in POSA patients, suggesting increased cardiac imbalance due to predominant positional apneas.

Automatic Assessment of Pediatric Sleep Apnea Severity Using Overnight Oximetry and Convolutional Neural Networks.

In this study, we use the overnight blood oxygen saturation (SpO2) signal along with convolutional neural networks (CNN) for the automatic estimation of pediatric sleep apnea-hypopnea syndrome (SAHS) severity. The few preceding studies have focused on the application of conventional feature extraction methods to obtain information from the SpO2 signal, which may omit relevant data related to the illness. In contrast, deep learning techniques are able to automatically learn features from raw input signal. Thus, we propose to assess whether CNN, a deep learning algorithm, could automatically estimate the apnea-hypopnea index (AHÍ) from nocturnal oximetry to help establish pediatric SAHS presence and severity. A database of 746 SpO2 recordings is involved in the study. CNN was trained using 20-min segments from the SpO2 signal in the training set (400 subjects). Hyperparameters of the CNN architecture were tuned using a validation set (100 subjects). This model was applied to a test set (246 subjects), in which the final AHI of each patient was obtained as the average of the output of the CNN for all the segments of the corresponding SpO2 signal. The AHI estimated by the CNN showed a promising diagnostic performance, with 74.8%, 90.7%, and 95.1% accuracies for the common AHI severity thresholds of 1, 5, and 10 events per hour (e/h), respectively. Furthermore, this model reached 28.6, 32.9, and 120.0 positive likelihood ratios for the above-mentioned AHI thresholds. This suggests that the information extracted from the oximetry signal by deep learning techniques may be useful to both establish pediatric SAHS and its severity.

A machine learning-based test for adult sleep apnoea screening at home using oximetry and airflow.

The most appropriate physiological signals to develop simplified as well as accurate screening tests for obstructive sleep apnoea (OSA) remain unknown. This study aimed at assessing whether joint analysis of at-home oximetry and airflow recordings by means of machine-learning algorithms leads to a significant diagnostic performance increase compared to single-channel approaches. Consecutive patients showing moderate-to-high clinical suspicion of OSA were involved. The apnoea-hypopnoea index (AHI) from unsupervised polysomnography was the gold standard. Oximetry and airflow from at-home polysomnography were parameterised by means of 38 time, frequency, and non-linear variables. Complementarity between both signals was exhaustively inspected via automated feature selection. Regression support vector machines were used to estimate the AHI from single-channel and dual-channel approaches. A total of 239 patients successfully completed at-home polysomnography. The optimum joint model reached 0.93 (95%CI 0.90-0.95) intra-class correlation coefficient between estimated and actual AHI. Overall performance of the dual-channel approach (kappa: 0.71; 4-class accuracy: 81.3%) significantly outperformed individual oximetry (kappa: 0.61; 4-class accuracy: 75.0%) and airflow (kappa: 0.42; 4-class accuracy: 61.5%). According to our findings, oximetry alone was able to reach notably high accuracy, particularly to confirm severe cases of the disease. Nevertheless, oximetry and airflow showed high complementarity leading to a remarkable performance increase compared to single-channel approaches. Consequently, their joint analysis via machine learning enables accurate abbreviated screening of OSA at home.

Usefulness of recurrence plots from airflow recordings to aid in paediatric sleep apnoea diagnosis.

BACKGROUND AND OBJECTIVE: In-laboratory overnight polysomnography (PSG) is the gold standard method to diagnose the Sleep Apnoea-Hypopnoea Syndrome (SAHS). PSG is a complex, expensive, labour-intensive and time-consuming test. Consequently, simplified diagnostic methods are desirable. We propose the analysis of the airflow (AF) signal by means of recurrence plots (RP) features. The main goal of our study was to evaluate the utility of the information from RPs of the AF signals to detect paediatric SAHS at different levels of severity. In addition, we also evaluated the complementarity with the 3% oxygen desaturation index (ODI3). METHODS: 946 AF and blood oxygen saturation (SpO2) recordings from children ages 0-13 years were used. The population under study was randomly split into training (60%) and test (40%) sets. RP was computed and 9 RP features were extracted from each AF recording. ODI3 was also calculated from each SpO2 recording. A feature selection stage was conducted in the training group by means of the fast correlation-based filter (FCBF) methodology to obtain a relevant and non-redundant optimum feature subset. A multi-layer perceptron neural network with Bayesian approach (BY-MLP), trained with these optimum features, was used to estimate the apnoea-hypopnoea index (AHI). RESULTS: 8 of the RP features showed statistically significant differences (p-value <0.01) among the SAHS severity groups. FCBF selected the maximum length of the diagonal lines from RP, as well as the ODI3. Using these optimum features, the BY-MLP model achieved 83.2%, 78.5%, and 91.0% accuracy in the test group for the AHI thresholds 1, 5, and 10 events/h, respectively. Moreover, this model reached a negative likelihood ratio of 0.1 for 1 event/h and a positive likelihood ratio of 13.7 for 10 events/h. CONCLUSIONS: RP analysis enables extraction of useful SAHS-related information from overnight AF paediatric recordings. Moreover, it provides complementary information to the widely-used clinical variable ODI3. Thus, RP applied to AF signals can be used along with ODI3 to help in paediatric SAHS diagnosis, particularly to either confirm the absence of SAHS or the presence of severe SAHS.