SpO2 Signal Research Articles

Abstract 16850: Machine Learning Based Estimation of Systolic and Diastolic Arterial Blood Pressure From the Electrocardiogram and Oxygen Saturation Waveforms

Introduction: Accurate, continuous blood pressure (BP) monitoring requires invasive equipment. We investigate the utility of a machine learning algorithm (ML) to estimate the systolic (sys) and diastolic (dia) BP from the electrocardiogram (ECG) and oxygen saturation (SpO2) signals. Methods: We identified over 2,000 hours (~9.2 M heart-beats), of 4 lead ECG, arterial BP, and SpO2 waveforms, from 82 random ICU patients, with various diagnoses. The ECG, BP and SpO2 waveforms were delineated using a wavelet-transform-based algorithm. Features extracted from the ECG and SpO2 signals were used as input to the ML model, while the sys/dia BP values of the corresponding BP signal (range: 0-250 mmHg), served as the gold standard. Using these features, we trained two independent Random Forest (RF) models to estimate the sys/dia BP values, and measured their performance over five-fold cross-validation. To identify the optimal window-length (# heart beats) in estimating sys/dia BP values, the entire process of extracting features and training/testing of RF models was performed for window-lengths of {1,5,6,7,8,9,10,11,12,13,14,15,20,30,50} heart-beats. Results: The root-mean-square error (RMSE) at each window-length is shown in the Figure. The lowest RMSE for both estimated sys/dia BP, 5.81±4.61 mmHg and 3.73±3.26 mmHg, respectively, was achieved at 14 heart-beats. The corresponding RMSE values using a one-beat length-window were 7.73±5.93 mmHg and 5.28±4.42 mmHg, respectively. This result indicates the ability to estimate the instantaneous BP values even on a beat-to-beat basis, with low-error. Conclusions: In comparison to prior studies, our novel ML model, to the best of our knowledge, has been trained over the largest amount of data. Our ML model can accurately estimate the sys/dia values of the arterial BP. Figure: RMSE values obtained while estimating the mean sys/dia BP, across different window-lengths.

Sensitivity analysis of a computer model of neonatal oxygen transport

Abstract Computer models of neonatal oxygenation could serve as a tool for a comprehensive comparison of closed-loop automated oxygen control systems. The behaviour of such models depends, besides the input data of the inspired fraction of oxygen and the premature infant's breath pattern, on internal parameters of the model. The aim of this study was to perform a sensitivity analysis of a computer model of neonatal oxygen transport to clarify the influence of its internal physiological parameters on the output signal of peripheral oxygen saturation (SpO2). We performed a multi-parameter sensitivity analysis using Monte Carlo simulations for randomly generated values of eight internal parameters. The influence on the model output SpO2 signal was evaluated using five characteristics of the output signal. The relations between the parameters and the output characteristics were displayed using scatter plots and analysed by linear correlation, standardized regression, and partial correlation. The main result of the study is that in our model the oxygen consumption in the tissue and the cardiac output have the greatest influence on the SpO2 drop and minimal SpO2 value during simulated desaturation. The rate of development of desaturation and its duration are most affected by the diffusion resistance of the alveolar-capillary membrane. The results of the sensitivity analysis will help to optimize the performance of the computer model of neonatal oxygen transport.

Greedy based convolutional neural network optimization for detecting apnea

Background and objectiveSleep apnea is a common sleep disorder, usually diagnosed using an expensive, highly specialized, and inconvenient test called polysomnography. A single SpO2 sensor based on an automated classification system can be developed to simplify the apnea detection. The main objective of this work is to develop a classifier based on a convolution neural network with the capability of detecting apnea events from one dimensional SpO2 signal. However, to find an optimum convolution neural network structure is a daunting task is usually done by a trial-and-error method. To solve this problem, a method is proposed to save time and simplify the process of searching for an optimum convolution neural network structure. MethodsGreedy based optimization is proposed to search for an optimized convolution neural network structure. Three different variants of greedy based optimization are proposed: the topology transfer, the weighted-topology transfer with rough estimation, and the weighted-topology transfer with fine tuning. The subject independent and the cross-database test are performed for the analysis. ResultsConsidering the balance between the execution time and the performance, the weighted-topology transfer with rough estimation is the best. An accuracy of 88.49% for the HuGCDN2008 database and 95.14% for the Apnea-ECG database are obtained for apnea events detection per minute. Regarding the apnea patient detection, also referred to as global classification, an accuracy of 95.71% is achieved for the HuGCDN2008 database, and 100% is achieved for the AED database without removing any subjects from both databases. ConclusionsThe proposed one-dimensional convolution neural network performs better in a similar situation than those presented in the literature. The greedy based methods, mainly the weighted-topology transfer with rough estimation, is an alternative method to extensive trial and error method.

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.

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.

1245 Cheyne-Stokes Respiration and Circulation Time—A Case to Add to the Mystery

Abstract Introduction Lung-to-finger circulation time (LFCT), the time taken for the circulation to reach the fingertips from the lungs, has been shown to correlate inversely with cardiac function (Hosokawa et al. 2015). LFCT can be measured on PSG as the time from the start of rebreathing after a central respiratory event to the nadir of the oxygen desaturation on the SpO2 signal. Patients with congestive heart failure (CHF) have been found to have increased LFCT, with even longer LFCT in patients with Cheyne-Stokes Respirations (CSR). We are reporting a case where LFCT increased throughout a single night by more than 40%. Report of Case A 66-year-old diabetic male with ischemic cardiomyopathy (LVEF 25%), CVA with residual L-sided paresthesias, CKD-IV and hypertension was diagnosed with severe CSA and OSA (AHI 31.5, CAI 13.9, OAI 0.0, MAI 0.2, hypopnea index of 17.4, minimum SpO2 of 80%; supine AHI 56.1). CSR was not mentioned on this diagnostic study. On his titration study, CPAP and BPAP failed to treat CSA, but ASV effectively treated his sleep-disordered breathing; however, he could not be started on ASV due to HFrEF. On a repeat titration after ICD implantation, CSR was prominent in the supine position, on both CPAP and BPAP S/T therapy. Cycle length progressively increased from 40 seconds at the beginning to 57 seconds at the end of the recording, an increase of 42% throughout the night. Circulation time also increased from 31 seconds to over 40 seconds. Scorable central respiratory events resolved but periodicity persisted. Conclusion To our knowledge, this is the first case of CSR with such progressive prolongation in cycle length during a single night. It again raises the question of the role of BPAP S/T in CSR with heart failure, and clarification of the potential use of supplemental oxygen in such situations.

Detection of Respiratory Events by Respiratory Effort and Oxygen Desaturation

PurposeSleep respiratory events are scored based on the reduction of airflow measured by a thermistor or nasal pressure cannula, together with oxygen desaturation and arousal criteria for hypopneas. We investigated whether automatic scoring can be performed without using the uncomfortable oronasal sensors and developed an automatic scoring system that is compatible with level III home sleep apnea testing devices.MethodsWe developed a respiratory event detection algorithm, based on SpO2 and respiratory effort signal measured from respiratory inductance plethysmograph (uncalibrated RIPsum), that outputs the time and duration of detected events and calculates an apnea–hypopnea-index (AHI) based on total recording time. The algorithm was tested on 98 polysomnography (PSG) recordings of patients, 77 with suspected sleep apnea and 21 without. The results were compared to annotations provided by the PSG systems where PSG AHI was computed using the total sleep time. The predicted AHI was evaluated for correlation and agreement with the PSG AHI using the intra-class correlation coefficient (ICC). Severity classification was performed and evaluated using the following categories: normal (< 5), mild (5–15), moderate (15–30), and severe (ge 30).ResultsThe ICC between predicted AHI and PSG AHI scored r = 0.96 (0.95–0.97, p < 0.001). The algorithm correctly predicted the severity for 74 recordings, overestimated 16, and underestimated 8. There was no misclassification by more than one severity level.ConclusionUsing respiratory effort and SpO2, our algorithm was able to detect respiratory events with high correlation and agreement compared to full PSG-based detection.

Multi-scale Entropy and Multiclass Fisher’s Linear Discriminant for Emotion Recognition Based on Multimodal Signal

Emotion recognition using physiological signals has been a special topic frequently discussed by researchers and practitioners in the past decade. However, the use of SpO2 and Pulse rate signals for emotion recognitionisvery limited and the results still showed low accuracy. It is due to the low complexity of SpO2 and Pulse rate signals characteristics. Therefore, this study proposes a Multiscale Entropy and Multiclass Fisher’s Linear Discriminant Analysis for feature extraction and dimensional reduction of these physiological signals for improving emotion recognition accuracy in elders. In this study, the dimensional reduction process was grouped into three experimental schemes, namely a dimensional reduction using only SpO2 signals, pulse rate signals, and multimodal signals (a combination feature vectors of SpO2 and Pulse rate signals). The three schemes were then classified into three emotion classes (happy, sad, and angry emotions) using Support Vector Machine and Linear Discriminant Analysis Methods. The results showed that Support Vector Machine with the third scheme achieved optimal performance with an accuracy score of 95.24%. This result showed a significant increase of more than 22%from the previous works.

Multi-Objective Hyperparameter Optimization of Convolutional Neural Network for Obstructive Sleep Apnea Detection

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.

Monitoring of limb perfusion after vascular surgery in critical limb ischemia using near-infrared spectroscopy: A prospective observational study

Background:Intra and postoperative perfusion monitoring should be used in critical limb ischemia patients undergoing vascular surgery to improve outcomes and reduce costs. While a pulse oximeter can be applied on the affected limb to monitor the arterial saturation of the limb, thus reflecting flow in that limb, we need to focus on other important parameters like muscle oxygen consumption and regional blood flow for a good outcome. Near-infrared spectroscopy (NIRS) can be used in such patients to monitor regional and tissue oxygenation.Methodology:In this prospective observational study, 30 adult patients undergoing infra-inguinal bypass were recruited. All these patients were given combined spinal-epidural anesthesia. In addition to routine monitoring, a pulse oximeter and NIRS electrodes were applied on the affected limb. rsO2, limb spO2, and Doppler signals were noted before the induction of anesthesia (baseline) and postoperatively at 0, 6, and 12 h. Improvement in rsO2 and limb spO2 values after surgery was noted and fall in these values was evaluated. Pearson correlation between rsO2 and limb spO2 was assessed. The data was analyzed using repeated-measures ANOVA.Results:Pearson correlation between rsO2 and limb spO2 was r > 0.8. Two patients had a fall in rsO2 in postoperative period, which co-related with a fall in limb spO2 and decreased/absent Doppler signals.Conclusion:NIRS represents a noninvasive and reliable means to monitor limb perfusion in patients undergoing vascular surgery for rest pain.

Neural network analysis of nocturnal SPO2 Signal enables easy screening of sleep apnea in acute stroke and transient ischemic attack patients

Neural network analysis of nocturnal SPO2 Signal enables easy screening of sleep apnea in acute stroke and transient ischemic attack patients

Estimation of cerebral blood flow velocity during breath-hold challenge using artificial neural networks

The effect of untreated Obstructive Sleep Apnoea (OSA) on cerebral haemodynamics and CA impairment is an active field of research interest. A breath-hold challenge is usually used in clinical and research settings to simulate cardiovascular and cerebrovascular changes that mimic OSA events. This work utilises temporal arterial oxygen saturation (SpO2) and photoplethysmography (PPG) signals to estimate the temporal cerebral blood flow velocity (CBFv) waveform. Measurements of CBFv, SpO2, and PPG, were acquired concurrently from volunteers performing two different protocols of breath-hold challenge in the supine position. Past values of the SpO2 and PPG signals were used to estimate the current values of CBFv using different permutations and topologies of supervised learning with shallow artificial neural networks (ANNs). The measurements from one protocol were used to train the ANNs and find the optimum topologies, which in turn were tested using the other protocol. Data collected from 10 normotensive, healthy subjects (four females, age 28.5 ± 6.1 years, Body Mass Index (BMI) 24.0 ± 4.7 kg/m2) were used in this study. The results show that different subjects have different optimum topologies for ANNs, thus indicating the effects of inter-subject variability on ANNs. Successfully reconstructed blind waveforms for the same subject group in the second protocol showed a reasonable accuracy of 60–80% estimation compared to the measured waveforms. HypothesisTemporal waveforms for SpO2 and PPG contain adequate information to estimate the temporal CBFv waveform using ANNs. MethodologyConcurrent measurements of SpO2 and PPG using pulse oximetry from the forehead and CBFv from the middle cerebral artery (MCA) using transcranial Doppler (TCD) were recorded from healthy, normotensive subjects performing a breath-hold challenge. The breath-hold challenge mimicked the cerebrovascular response to apnoea, and was recorded by measuring CBFv in MCA. Two protocols were used, each consisting of five breath-holding manoeuvres and differing in terms of the time between the five successive breath-holds. Using data from one protocol, several permutations of the temporal values of SpO2 and PPG signals were used as inputs to different ANN topologies, in order to train and find the optimum model. The optimum model was evaluated using the data from the other protocol as a blind dataset. ResultsUsing the first protocol for training, optimum ANN configurations were found to be different for each subject, and accuracy of 75–87% was achieved. When these optimum ANN models were tested using the second protocol as a blind dataset, the accuracy achieved was around 60–80%. ConclusionsA novel approach employing temporal records of SpO2 and PPG can be used to estimate the CBFv waveform using ANNs with acceptable accuracy. Increases in the size and diversity of the population dataset and the use of features extracted from SpO2 and PPG signals are needed for generalisation of the method and potential future clinical applications.

Artificial neural network analysis of the oxygen saturation signal enables accurate diagnostics of sleep apnea

The severity of obstructive sleep apnea (OSA) is classified using apnea-hypopnea index (AHI). Accurate determination of AHI currently requires manual analysis and complicated registration setup making it expensive and labor intensive. Partially for these reasons, OSA is a heavily underdiagnosed disease as only 7% of women and 18% of men suffering from OSA have diagnosis. To resolve these issues, we introduce an artificial neural network (ANN) that estimates AHI and oxygen desaturation index (ODI) using only the blood oxygen saturation signal (SpO2), recorded during ambulatory polygraphy, as an input. Therefore, hypopneas associated only with an arousal were not considered in this study. SpO2 signals from 1692 patients were used for training and 99 for validation. Two test sets were used consisting of 198 and 1959 patients. In the primary test set, the median absolute errors of ANN estimated AHI and ODI were 0.78 events/hour and 0.68 events/hour respectively. Based on the ANN estimated AHI and ODI, 90.9% and 94.4% of the test patients were classified into the correct OSA severity category. In conclusion, AHI and ODI can be reliably determined using neural network analysis of SpO2 signal. The developed method may enable a more affordable screening of OSA.

Model of SpO2 signal of the neonate

Abstract The advantages of automatic control of the fraction of inspired oxygen in neonates have been documented in recently published clinical trials. Many control algorithms are available, but their comparison is missing in the literature. A mathematical model of neonatal oxygen transport could be a useful tool to compare and enhance both automatic control algorithms and manual control of fraction of inspired oxygen. Besides other components, the model of neonatal oxygen transport must include a module linking arterial (SaO2) and peripheral (SpO2) oxygen saturation. The pulse oximeter module must reflect issues of SpO2 measurement typical for clinical practice, such as overestimation of SpO2 over SaO2 documented by several studies, or inaccurate pulse oximeter readings due to high noise. The aim of this study was to describe both the bias between SaO2 and SpO2 and the noise, characteristic for continuous SpO2 recording, for a computer model of oxygenation of a premature infant. The SpO2-SaO2 bias, derived from available clinical data, describes a typical deviation of the SpO2 measurement as a function of the true SaO2 value in three different SaO2 intervals. The SpO2 measurement noise was considered as a random process that affects biased SpO2values at each time point with statistical properties estimated from SpO2 continuous recordings of 5 stable newborns. The results of the study will help to adjust a computer model of neonatal oxygenation to the real situations observed in the clinical practice.

Pre-diabetic patients with severe obstructive sleep apnea: novel parameters of hypoxia during sleep correlate with insulin resistance.

Obstructive sleep apnea (OSA) is an increasingly prevalent sleep disorder with estimated prevalence of moderate to severe sleep apnea ranging between 6-13% in the adult population. Nocturnal intermittent hypoxia has been associated with an increased risk of developing type 2 diabetes and insulin resistance (IR). The existing indices of hypoxia, used in polysomnography (PSG), cannot express accurately the influence of the mild desaturations precisely during sleep. In the present study, 73 subjects without other comorbidities were examined by PSG. Hypoxia parameters were analyzed, in the intervals with low values of SpO2 signal. The thresholds were set at 94% and 92% and the average value (M) of the SpO2 signal, in areas below thresholds, were calculated. The desaturations were analyzed together with their duration within the recording in terms of SpO2 signal parameters. Blood samples were taken for biochemical analysis. A total of 50 subjects were diagnosed with OSAS with mean AHI of 56.11±27.70/h and 23 subjects had no sleep apnea with mean AHI of 3.47±0.6/h. The amount of desaturations was significantly correlated with insulin levels (r=0.301, p=0.034) and the percentage of desaturation events (Dev) that were longer than 6 points (2 sec) (r=0.301, p=0.034). In addition, mean duration of desaturations was significantly correlated with IR as expressed by HOMA index (r=0.289, p=0.047), as well as with total duration of desaturation of SpO2 (r=0.322, p =0.025) and percentage of Dev that were long than 6 points (2 sec) (r=0.292, p=0.044). A strong correlation was also revealed between total duration of desaturations and fasting glucose (r=0.887, p=0.000). Results suggest that hypoxia parameters derived from SpO2 signal analysis, are strongly correlated with IR and fasting glucose levels, implying a role of hypoxia in the pathogenesis of diabetes.

Convolutional Neural Networks to Detect Pediatric Apnea-Hypopnea Events from Oximetry.

Pediatric sleep apnea-hypopnea syndrome (SAHS) is a highly prevalent breathing disorder that is related to many negative consequences for the children's health and quality of life when it remains untreated. The gold standard for pediatric SAHS diagnosis (overnight polysomnography) has several limitations, which has led to the search for alternative tests. In this sense, automated analysis of overnight oximetry has emerged as a simplified technique. Previous studies have focused on the extraction of ad-hoc features from the blood oxygen saturation (SpO2) signal, which may miss useful information related to apnea and hypopnea (AH) events. In order to overcome this limitation of traditional approaches, we propose the use of convolutional neural networks (CNN), a deep learning technique, to automatically detect AH events from the SpO2 raw data. CHAT-baseline dataset, composed of 453 SpO2 recordings, was used for this purpose. A CNN model was trained using 60-s segments from the SpO2 signal using a training set (50% of subjects). Optimum hyperparameters of the CNN architecture were obtained using a validation set (25% of subjects). This model was applied to a third test set (25% of subjects), reaching 93.6% accuracy to detect AH events. These results suggest that the application of CNN may be useful to detect changes produced in the oximetry signal by AH events in pediatric SAHS patients.

Airflow from nasal pulse oximetry in the screening of obstructive sleep apnea.

Obstructive Sleep Apnea (OSA) is recognized as an increasing health risk, leading to daytime sleepiness and various medical conditions, such as hypertension and heart failure. Polysomnography (PSG), the gold standard to diagnose OSA, is a resource-intensive and expensive investigation confined to the hospital.Portable home monitoring, i.e. pulse oximetry, may become an acceptable OSA screening method. The novel nasal pulse oximeter sensor (Xhale Alar) adds the possibility of combining pulse oximetry (SpO2) with airflow analysis by an integrated thermistor, which might increase the diagnostic accuracy.In the Alar pilot study, 39 adults were measured during an overnight PSG recording together with the Alar sensor. This study aims to investigate the additional value of an airflow signal compared to SpO2 analysis in OSA screening. Both time and spectral features were extracted from SpO2 and airflow signals recorded with the Alar sensor. Leave one out cross-validation was used to develop Random Forest models in screening for apnea-hypopnea index (AHI) thresholds 5 and 10. Using both AHI ≥ 5 and AHI ≥ 10 as the diagnostic cutoff, the airflow signal shows respectively an AUC of 89% and 80% compared to 78% and 77% with SpO2 analysis, showing a higher performance using an airflow signal in screening adults for OSA.

A review of approaches for analysing obstructive sleep apnoea-related patterns in pulse oximetry data.

Overnight pulse oximetry allows the relatively non-invasive estimation of peripheral blood haemoglobin oxygen saturations (SpO2 ), and forms part of the typical polysomnogram (PSG) for investigation of obstructive sleep apnoea (OSA). While the raw SpO2 signal can provide detailed information about OSA-related pathophysiology, this information is typically summarized with simple statistics such as the oxygen desaturation index (ODI, number of desaturations per hour). As such, this study reviews the technical methods for quantifying OSA-related patterns in oximetry data. The technical methods described in literature can be broadly grouped into four categories: (i) Describing the detailed characteristics of desaturations events; (ii) Time series statistics; (iii) Analysis of power spectral distribution (i.e. frequency domain analysis); and (d) Non-linear analysis. These are described and illustrated with examples of oximetry traces. The utilization of these techniques is then described in two applications. First, the application of detailed oximetry analysis allows the accurate automated classification of PSG-defined OSA. Second, quantifications which better characterize the severity of desaturation events are better predictors of OSA-related epidemiological outcomes than standard clinical metrics. Finally, methodological considerations and further applications and opportunities are considered.

Arterial oxygen saturation during Cheyne-Stokes respiration in heart failure patients: does measurement site matter?

ObjectiveDespite the fact that the ear is the site to monitor arterial oxygen saturation by pulse oximetry (SpO2) closest to carotid chemoreceptors, sleep studies almost invariably use finger probes. This study aimed to assess the timing and morphological differences between SpO2 signals at the ear and finger during Cheyne–Stokes respiration (CSR) in heart failure (HF) patients. MethodsWe studied 21 HF patients with CSR during a 40-min in-laboratory resting recording. SpO2 was recorded by: (1) two identical bedside pulse-oximeters with an ear (SpO2_Ear) and a finger probe (SpO2_Finger), and (2) a standard polysomnograph with a finger probe (SpO2_PSG). We estimated the delays between signals and, for each signal, computed the mean and minimum SpO2, the magnitude of cyclic desaturations and the overall time spent with SpO2<90% (T90%). ResultsThe SpO2_Finger signal was significantly delayed [bias: 12.7 s (95% limits of agreement: 2.2, 23.0 s)] and slightly but not significantly downward-shifted with respect to SpO2_Ear. SpO2_PSG was almost synchronous with SpO2_Finger; however, a further significant downward shift was observed relative to the latter. In particular, minimum SpO2_PSG was significantly lower [−2.1% (− 4.8, 0.6%)], and desaturations and T90% were significantly higher than SpO2_Finger [1.2% (−1.3, 3.7%), and 13.9% (−12.3, 40.0%), respectively]. ConclusionDuring CSR in HF patients, the marked delay between SpO2_Ear and SpO2_Finger makes the interpretation of the timing relationship between peripheral chemoreceptor stimulation and ventilatory events rather difficult. The observed discrepancies between SpO2_PSG and SpO2_Finger, which may be due to differences in the processing of raw SpO2 signals, call for a standardization of processing algorithms.

Wavelet analysis of oximetry recordings to assist in the automated detection of moderate-to-severe pediatric sleep apnea-hypopnea syndrome.

BackgroundThe gold standard for pediatric sleep apnea hypopnea syndrome (SAHS) is overnight polysomnography, which has several limitations. Thus, simplified diagnosis techniques become necessary.ObjectiveThe aim of this study is twofold: (i) to analyze the blood oxygen saturation (SpO2) signal from nocturnal oximetry by means of features from the wavelet transform in order to characterize pediatric SAHS; (ii) to evaluate the usefulness of the extracted features to assist in the detection of pediatric SAHS.Methods981 SpO2 signals from children ranging 2–13 years of age were used. Discrete wavelet transform (DWT) was employed due to its suitability to deal with non-stationary signals as well as the ability to analyze the SAHS-related low frequency components of the SpO2 signal with high resolution. In addition, 3% oxygen desaturation index (ODI3), statistical moments and power spectral density (PSD) features were computed. Fast correlation-based filter was applied to select a feature subset. This subset fed three classifiers (logistic regression, support vector machines (SVM), and multilayer perceptron) trained to determine the presence of moderate-to-severe pediatric SAHS (apnea-hypopnea index cutoff ≥ 5 events per hour).ResultsThe wavelet entropy and features computed in the D9 detail level of the DWT reached significant differences associated with the presence of SAHS. All the proposed classifiers fed with a selected feature subset composed of ODI3, statistical moments, PSD, and DWT features outperformed every single feature. SVM reached the highest performance. It achieved 84.0% accuracy (71.9% sensitivity, 91.1% specificity), outperforming state-of-the-art studies in the detection of moderate-to-severe SAHS using the SpO2 signal alone.ConclusionWavelet analysis could be a reliable tool to analyze the oximetry signal in order to assist in the automated detection of moderate-to-severe pediatric SAHS. Hence, pediatric subjects suffering from moderate-to-severe SAHS could benefit from an accurate simplified screening test only using the SpO2 signal.