Multiscale Entropy Analysis of Unattended Oximetric Recordings to Assist in the Screening of Paediatric Sleep Apnoea at Home

Novel method combining multiscale attention entropy of overnight blood oxygen level and machine learning for easy sleep apnea screening

Objective

Sleep apnea is a common sleep disorder affecting a significant portion of the population, but many apnea patients remain undiagnosed because existing clinical tests are invasive and expensive. This study aimed to develop a method for easy sleep apnea screening.

Methods

Three supervised machine learning algorithms, including logistic regression, support vector machine, and light gradient boosting machine, were applied to develop apnea screening models at two apnea-hypopnea index cutoff thresholds: ≥ 5 and ≥ 30 events/hours. The SpO2 recordings of the Sleep Heart Health Study database (N = 5786) were used for model training, validation, and test. Multiscale entropy analysis was performed to derive a set of multiscale attention entropy features from the SpO2 recordings. Demographic features including age, sex, body mass index, and blood pressure were also used. The dependency among the multiscale attention entropy features were handled with the independent component analysis.

Results

For cutoff ≥ 5/hours, logistic regression model achieved the highest Matthew's correlation coefficient (0.402) and area under the curve (0.747), and reasonably good sensitivity (75.38%), specificity (74.02%), and positive predictive value (92.94%). For cutoff ≥ 30/hours, support vector machine model achieved the highest Matthew's correlation coefficient (0.545) and area under the curve (0.823), and good sensitivity (82.00%), specificity (82.69%), and negative predictive value (95.53%).

Conclusions

Our models achieved better performance than existing methods and have the potential to be integrated with home-use pulse oximeters.

Comparison of oxygen supplementation in very preterm infants: Variations of oxygen saturation features and their application to hypoxemic episode based risk stratification

Background

Oxygen supplementation is commonly used to maintain oxygen saturation (SpO₂) levels in preterm infants within target ranges to reduce intermittent hypoxemic (IH) events, which are associated with short- and long-term morbidities. There is not much information available about differences in oxygenation patterns in infants undergoing such supplementations nor their relation to observed IH events. This study aimed to describe oxygenation characteristics during two types of supplementation by studying SpO₂ signal features and assess their performance in hypoxemia risk screening during NICU monitoring.

Subjects and methods

SpO₂ data from 25 infants with gestational age <32 weeks and birthweight <2,000 g who underwent a cross over trial of low-flow nasal cannula (NC) and digitally-set servo-controlled oxygen environment (OE) supplementations was considered in this secondary analysis. Features pertaining to signal distribution, variability and complexity were estimated and analyzed for differences between the supplementations. Univariate and regularized multivariate logistic regression was applied to identify relevant features and develop screening models for infants likely to experience a critically high number of IH per day of observation. Their performance was assessed using area under receiver operating curves (AUROC), accuracy, sensitivity, specificity and F1 scores.

Results

While most SpO₂ measures remained comparable during both supplementations, signal irregularity and complexity were elevated while on OE, pointing to more volatility in oxygen saturation during this supplementation mode. In addition, SpO₂ variability measures exhibited early prognostic value in discriminating infants at higher risk of critically many IH events. Poincare plot variability at lag 1 had AUROC of 0.82, 0.86, 0.89 compared to 0.63, 0.75, 0.81 for the IH number, a clinical parameter at observation times of 30 min, 1 and 2 h, respectively. Multivariate models with two features exhibited validation AUROC > 0.80, F1 score > 0.60 and specificity >0.85 at observation times ≥ 1 h. Finally, we proposed a framework for risk stratification of infants using a cumulative risk score for continuous monitoring.

Conclusion

Analysis of oxygen saturation signal routinely collected in the NICU, may have extensive applications in inferring subtle changes to cardiorespiratory dynamics under various conditions as well as in informing clinical decisions about infant care.

Integration of multiscale entropy and BASED scale of electroencephalography after adrenocorticotropic hormone therapy predict relapse of infantile spasms

BACKGROUND

Even though adrenocorticotropic hormone (ACTH) demonstrated powerful efficacy in the initially successful treatment of infantile spasms (IS), nearly half of patients have experienced a relapse. We sought to investigate whether features of electroencephalogram (EEG) predict relapse in those IS patients without structural brain abnormalities.

METHODS

We retrospectively reviewed data from children with IS who achieved initial response after ACTH treatment, along with EEG recorded within the last two days of treatment. The recurrence of epileptic spasms following treatment was tracked for 12 months. Subjects were categorized as either non-relapse or relapse groups. General clinical and EEG recordings were collected, burden of amplitudes and epileptiform discharges (BASED) score and multiscale entropy (MSE) were carefully explored for cross-group comparisons.

RESULTS

Forty-one patients were enrolled in the study, of which 26 (63.4%) experienced a relapse. The BASED score was significantly higher in the relapse group. MSE in the non-relapse group was significantly lower than the relapse group in the γ band but higher in the lower frequency range (δ, θ, α). Sensitivity and specificity were 85.71% and 92.31%, respectively, when combining MSE in the δ/γ frequency of the occipital region, plus BASED score were used to distinguish relapse from non-relapse groups.

CONCLUSIONS

BASED score and MSE of EEG after ACTH treatment could be used to predict relapse for IS patients without brain structural abnormalities. Patients with BASED score ≥ 3, MSE increased in higher frequency, and decreased in lower frequency had a high risk of relapse.

Reliability of machine learning to diagnose pediatric obstructive sleep apnea: Systematic review and meta-analysis

BACKGROUND

Machine-learning approaches have enabled promising results in efforts to simplify the diagnosis of pediatric obstructive sleep apnea (OSA). A comprehensive review and analysis of such studies increase the confidence level of practitioners and healthcare providers in the implementation of these methodologies in clinical practice.

OBJECTIVE

To assess the reliability of machine-learning-based methods to detect pediatric OSA.

DATA SOURCES

Two researchers conducted an electronic search on the Web of Science and Scopus using term, and studies were reviewed along with their bibliographic references.

ELIGIBILITY CRITERIA

Articles or reviews (Year 2000 onwards) that applied machine learning to detect pediatric OSA; reported data included information enabling derivation of true positive, false negative, true negative, and false positive cases; polysomnography served as diagnostic standard.

APPRAISAL AND SYNTHESIS METHODS

Pooled sensitivities and specificities were computed for three apnea-hypopnea index (AHI) thresholds: 1 event/hour (e/h), 5 e/h, and 10 e/h. Random-effect models were assumed. Summary receiver-operating characteristics (SROC) analyses were also conducted. Heterogeneity (I ² ) was evaluated, and publication bias was corrected (trim and fill).

RESULTS

Nineteen studies were finally retained, involving 4767 different pediatric sleep studies. Machine learning improved diagnostic performance as OSA severity criteria increased reaching optimal values for AHI = 10 e/h (0.652 sensitivity; 0.931 specificity; and 0.940 area under the SROC curve). Publication bias correction had minor effect on summary statistics, but high heterogeneity was observed among the studies.

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.

Multi-scale Entropy Evaluates the Proarrhythmic Condition of Persistent Atrial Fibrillation Patients Predicting Early Failure of Electrical Cardioversion

Atrial fibrillation (AF) is nowadays the most common cardiac arrhythmia, being associated with an increase in cardiovascular mortality and morbidity. When AF lasts for more than seven days, it is classified as persistent AF and external interventions are required for its termination. A well-established alternative for that purpose is electrical cardioversion (ECV). While ECV is able to initially restore sinus rhythm (SR) in more than 90% of patients, rates of AF recurrence as high as 20-30% have been found after only a few weeks of follow-up. Hence, new methods for evaluating the proarrhythmic condition of a patient before the intervention can serve as efficient predictors about the high risk of early failure of ECV, thus facilitating optimal management of AF patients. Among the wide variety of predictors that have been proposed to date, those based on estimating organization of the fibrillatory (f-) waves from the surface electrocardiogram (ECG) have reported very promising results. However, the existing methods are based on traditional entropy measures, which only assess a single time scale and often are unable to fully characterize the dynamics generated by highly complex systems, such as the heart during AF. The present work then explores whether a multi-scale entropy (MSE) analysis of the f-waves may provide early prediction of AF recurrence after ECV. In addition to the common MSE, two improved versions have also been analyzed, composite MSE (CMSE) and refined MSE (RMSE). When analyzing 70 patients under ECV, of which 31 maintained SR and 39 relapsed to AF after a four week follow-up, the three methods provided similar performance. However, RMSE reported a slightly better discriminant ability of 86%, thus improving the other multi-scale-based outcomes by 3-9% and other previously proposed predictors of ECV by 15-30%. This outcome suggests that investigation of dynamics at large time scales yields novel insights about the underlying complex processes generating f-waves, which could provide individual proarrhythmic condition estimation, thus improving preoperative predictions of ECV early failure.

Assessment of Airflow and Oximetry Signals to Detect Pediatric Sleep Apnea-Hypopnea Syndrome Using AdaBoost

The reference standard to diagnose pediatric Obstructive Sleep Apnea (OSA) syndrome is an overnight polysomnographic evaluation. When polysomnography is either unavailable or has limited availability, OSA screening may comprise the automatic analysis of a minimum number of signals. The primary objective of this study was to evaluate the complementarity of airflow (AF) and oximetry (SpO₂) signals to automatically detect pediatric OSA. Additionally, a secondary goal was to assess the utility of a multiclass AdaBoost classifier to predict OSA severity in children. We extracted the same features from AF and SpO₂ signals from 974 pediatric subjects. We also obtained the 3% Oxygen Desaturation Index (ODI) as a common clinically used variable. Then, feature selection was conducted using the Fast Correlation-Based Filter method and AdaBoost classifiers were evaluated. Models combining ODI 3% and AF features outperformed the diagnostic performance of each signal alone, reaching 0.39 Cohens's kappa in the four-class classification task. OSA vs. No OSA accuracies reached 81.28%, 82.05% and 90.26% in the apnea-hypopnea index cutoffs 1, 5 and 10 events/h, respectively. The most relevant information from SpO₂ was redundant with ODI 3%, and AF was complementary to them. Thus, the joint analysis of AF and SpO₂ enhanced the diagnostic performance of each signal alone using AdaBoost, thereby enabling a potential screening alternative for OSA in children.

Relation Between the Defect Interactions and the Serration Dynamics in a Zr-Based Bulk Metallic Glass

For this study, the effects of thermal annealing and compressive strain rate on the complexity of the serration behavior in a Zr-based bulk metallic glass (BMG) was investigated. Here, as-cast and thermally-annealed (300 °C, 1 week) Zr52.5Cu17.9Ni14.6Al10Ti5 BMG underwent room-temperature compression tests in the unconstrained condition at strain rates of 2 × 10−5 s−1 and 2 × 10−4 s−1. The complexity of the serrated flow was determined, using the refined composite multiscale entropy technique. Nanoindentation testing and X-ray diffraction characterization were performed to assess the changes in the microstructure and mechanical properties of the BMG that occurred during annealing. The results indicated that the BMG did not crystallize during annealing in the prescribed heating condition. Nanoindentation tests revealed that annealing led to a significant increase in the depth-dependent nanoindentation hardness and Young’s modulus, which were attributed to the structural relaxation in the glass. Furthermore, both annealing and an increased strain rate resulted in a marked enhancement in the complexity of the serrated flow during compression. It was concluded that the increase in the sample entropy with increasing strain rate is related to an increase in the number of defect interactions during the serrated flow.

Improving the Diagnostic Ability of Oximetry Recordings in Pediatric Sleep Apnea-Hypopnea Syndrome by Means of Multi-Class AdaBoost

Pediatric sleep apnea-hypopnea syndrome (SAHS) is a highly prevalent respiratory disorder that may impose many negative effects on the health and development of children. Due to the drawbacks of overnight polysomnography (PSG), the gold standard diagnosis technique, automated analysis of nocturnal oximetry has emerged as a simplified alternative. In order to improve diagnosis ability of oximetry, we propose to evaluate the usefulness of AdaBoost, a classification boosting algorithm, in the context of pediatric SAHS. A database composed of 981 SpO₂ recordings from pediatric subjects was used. For this purpose, a signal processing approach divided into two main stages was conducted: (i) feature extraction, where 3% oxygen desaturation index (ODI3), spectral, and nonlinear features were computed from the oximetry signal, and (ii) AdaBoost classification, where an AdaBoost.M2 model was trained with these features in order to determine the severity of pediatric SAHS according to the apnea-hypopnea index (AHI): AHI<1 events per hour (e/h), 1≤AHI<5 e/h, and AHI≥5 e/h. Our AdaBoost.M2 model achieved a Cohen's kappa of 0.474 in an independent test set in the 3-class classification task. In addition, high accuracies were obtained when using the AHI cutoffs for diagnosis of mild (AHI=1 e/h) and moderate-to-severe (AHI=5 e/h) SAHS: 80.9% and 82.9%, respectively. These results achieved slightly higher diagnostic accuracies than ODI3 as well as state-of-the-art studies. Therefore, AdaBoost could help to enhance the diagnostic ability of the oximetry signal to assess pediatric SAHS severity.

Detrended fluctuation analysis of the oximetry signal to assist in paediatric sleep apnoea-hypopnoea syndrome diagnosis

OBJECTIVE

To evaluate whether detrended fluctuation analysis (DFA) provides information that improves the diagnostic ability of the oximetry signal in the diagnosis of paediatric sleep apnoea-hypopnoea syndrome (SAHS).

APPROACH

A database composed of 981 blood oxygen saturation (SpO₂) recordings in children was used to extract DFA-derived features in order to quantify the scaling behaviour and the fluctuations of the SpO₂ signal. The 3% oxygen desaturation index (ODI3) was also computed for each subject. Fast correlation-based filter (FCBF) was then applied to select an optimum subset of relevant and non-redundant features. This subset fed a multi-layer perceptron (MLP) neural network to estimate the apnoea-hypopnoea index (AHI).

MAIN RESULTS

ODI3 and four features from the DFA reached significant differences associated with the severity of SAHS. An optimum subset composed of the slope in the first scaling region of the DFA profile and the ODI3 was selected using FCBF applied to the training set (60% of samples). The MLP model trained with this feature subset showed good agreement with the actual AHI, reaching an intra-class correlation coefficient of 0.891 in the test set (40% of samples). Furthermore, the estimated AHI showed high diagnostic ability, reaching an accuracy of 82.7%, 81.9%, and 91.1% using three common AHI cut-offs of 1, 5, and 10 events per hour (e h^-1), respectively. These results outperformed the overall performance of ODI3.

SIGNIFICANCE

DFA may serve as a reliable tool to improve the diagnostic performance of oximetry recordings in the evaluation of paediatric patients with symptoms suggestive of SAHS.

Symbolic dynamics to enhance diagnostic ability of portable oximetry from the phone oximeter in the detection of paediatric sleep apnoea

OBJECTIVE

This study is aimed at assessing symbolic dynamics as a reliable technique to characterise complex fluctuations of portable oximetry in the context of automated detection of childhood obstructive sleep apnoea-hypopnoea syndrome (OSAHS).

APPROACH

Nocturnal oximetry signals from 142 children with suspected OSAHS were acquired using the Phone Oximeter: a portable device that integrates a pulse oximeter with a smartphone. An apnoea-hypopnoea index (AHI) ≥5 events/h from simultaneous in-lab polysomnography was used to confirm moderate-to-severe childhood OSAHS. Symbolic dynamics was used to parameterise non-linear changes in the overnight oximetry profile. Conventional indices, anthropometric measures, and time-domain linear statistics were also considered. Forward stepwise logistic regression was used to obtain an optimum feature subset. Logistic regression (LR) was used to identify children with moderate-to-severe OSAHS.

MAIN RESULTS

The histogram of 3-symbol words from symbolic dynamics showed significant differences (p <0.01) between children with AHI <5 events/h and moderate-to-severe patients (AHI ≥5 events/h). Words representing increasing oximetry values after apnoeic events (re-saturations) showed relevant diagnostic information. Regarding the performance of individual characterization approaches, the LR model composed of features from symbolic dynamics alone reached a maximum performance of 78.4% accuracy (65.2% sensitivity; 86.8% specificity) and 0.83 area under the ROC curve (AUC). The classification performance improved combining all features. The optimum model from feature selection achieved 83.3% accuracy (73.5% sensitivity; 89.5% specificity) and 0.89 AUC, significantly (p-value <0.01) outperforming the other models.

SIGNIFICANCE

Symbolic dynamics provides complementary information to conventional oximetry analysis enabling reliable detection of moderate-to-severe paediatric OSAHS from portable oximetry.

Oximetry use in obstructive sleep apnea

INTRODUCTION

Overnight oximetry has been proposed as an accessible, simple, and reliable technique for obstructive sleep apnea syndrome (OSAS) diagnosis. From visual inspection to advanced signal processing, several studies have demonstrated the usefulness of oximetry as a screening tool. However, there is still controversy regarding the general application of oximetry as a single screening methodology for OSAS. Areas covered: Currently, high-resolution portable devices combined with pattern recognition-based applications are able to achieve high performance in the detection of this disease. In this review, recent studies involving automated analysis of oximetry by means of advanced signal processing and machine learning algorithms are analyzed. Advantages and limitations are highlighted and novel research lines aimed at improving the screening ability of oximetry are proposed. Expert commentary: Oximetry is a cost-effective tool for OSAS screening in patients showing high pretest probability for the disease. Nevertheless, exhaustive analyses are still needed to further assess unattended oximetry monitoring as a single diagnostic test for sleep apnea, particularly in the pediatric population and in populations with significant comorbidities. In the following years, communication technologies and big data analyses will overcome current limitations of simplified sleep testing approaches, changing the detection and management of OSAS.

Assessment of oximetry-based statistical classifiers as simplified screening tools in the management of childhood obstructive sleep apnea

PURPOSE

A variety of statistical models based on overnight oximetry has been proposed to simplify the detection of children with suspected obstructive sleep apnea syndrome (OSAS). Despite the usefulness reported, additional thorough comparative analyses are required. This study was aimed at assessing common binary classification models from oximetry for the detection of childhood OSAS.

METHODS

Overnight oximetry recordings from 176 children referred for clinical suspicion of OSAS were acquired during in-lab polysomnography. Several training and test datasets were randomly composed by means of bootstrapping for model optimization and independent validation. For every child, blood oxygen saturation (SpO₂) was parameterized by means of 17 features. Fast correlation-based filter (FCBF) was applied to search for the optimum features. The discriminatory power of three statistical pattern recognition algorithms was assessed: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and logistic regression (LR). The performance of each automated model was evaluated for the three common diagnostic polysomnographic cutoffs in pediatric OSAS: 1, 3, and 5 events/h.

RESULTS

Best screening performances emerged using the 1 event/h cutoff for mild-to-severe childhood OSAS. LR achieved 84.3% accuracy (95% CI 76.8-91.5%) and 0.89 AUC (95% CI 0.83-0.94), while QDA reached 96.5% PPV (95% CI 90.3-100%) and 0.91 AUC (95% CI 0.85-0.96%). Moreover, LR and QDA reached diagnostic accuracies of 82.7% (95% CI 75.0-89.6%) and 82.1% (95% CI 73.8-89.5%) for a cutoff of 5 events/h, respectively.

CONCLUSIONS

Automated analysis of overnight oximetry may be used to develop reliable as well as accurate screening tools for childhood OSAS.