Oximetry Signals Research Articles

Automatic scoring of non-apnoea arousals using hand-crafted features from the polysomnogram

Objective: We present a system for automated annotation of non-apnoea arousals using twelve signals from the polysomnogram (PSG) including airflow, six signals of electroencephalogram, the electrooculogram, chin electromyogram, oximetry signal, and chest and abdominal respiratory effort signals. Approach: Fifty-nine time- and frequency-domain features were extracted from the twelve signals using 15 s epochs. Features from an epoch were combined with features from adjacent epochs and then processed with a bank of feed-forward networks that provided a probability estimate of the occurrence of a non-apnoea arousal event in every epoch. Data from the 2018 PhysioNet/Computing in Cardiology Challenge was used to develop and test the system. Ten-fold cross validation on the 994 PSGs of training data was used to compare the performance of different network configurations. Main results: Our highest performing configuration utilised a bank of 30 feed-forward neural networks. Each network processed ±4 epochs of features and each used a single hidden layer of 20 units. The performance of this configuration was evaluated on the independent test set of 989 PSGs and achieved an area under the receiver operator curve of 0.848 and an area under the precision-recall curve of 0.325 for correctly discriminating non-apnoea arousals from non-arousals samples. Significance: The classification performance results of our system demonstrate that automated annotation of non-apnoea arousals can be achieved with a high degree of reliability.

Protocol for a multicentre retrospective observational cohort study in Denmark: association between the intraoperative peripheral perfusion index and postoperative morbidity and mortality in acute non-cardiac surgical patients

IntroductionPerioperative haemodynamic instability is associated with postoperative morbidity and mortality. Macrocirculatory parameters, such as arterial blood pressure and cardiac output are associated with poor outcome but may be uncoupled from...

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.

Ready for Primetime? Home Sleep Apnea Tests for Children.

Ready for Primetime? Home Sleep Apnea Tests for Children.

Vision-Based Heart and Respiratory Rate Monitoring During Sleep - A Validation Study for the Population at Risk of Sleep Apnea.

A reliable, accessible, and non-intrusive method for tracking respiratory and heart rate is important for improving monitoring and detection of sleep apnea. In this study, an algorithm based on motion analysis of infrared video recordings was validated in 50 adults referred for clinical overnight polysomnography (PSG). The algorithm tracks the displacements of selected feature points on each sleeping participant and extracts respiratory rate using principal component analysis and heart rate using independent component analysis. For respiratory rate estimation (mean ± standard deviation), 89.89 % ± 10.95 % of the overnight estimation was accurate within 1 breath per minute compared to the PSG-derived respiratory rate from the respiratory inductive plethysmography signal, with an average root mean square error (RMSE) of 2.10 ± 1.64 breaths per minute. For heart rate estimation, 77.97 % ± 18.91 % of the overnight estimation was within 5 beats per minute of the heart rate derived from the pulse oximetry signal from PSG, with mean RMSE of 7.47 ± 4.79 beats per minute. No significant difference in estimation of RMSE of either signal was found according to differences in body position, sleep stage, or amount of the body covered by blankets. This vision-based method may prove suitable for overnight, non-contact monitoring of respiratory rate. However, at present, heart rate monitoring is less reliable and will require further work to improve accuracy.

Data Integrity-Based Methodology and Checklist for Identifying Implementation Risks of Physiological Sensing in Mobile Health Projects: Quantitative and Qualitative Analysis.

BackgroundMobile health (mHealth) technologies have the potential to bring health care closer to people with otherwise limited access to adequate health care. However, physiological monitoring using mobile medical sensors is not yet widely used as adding biomedical sensors to mHealth projects inherently introduces new challenges. Thus far, no methodology exists to systematically evaluate these implementation challenges and identify the related risks.ObjectiveThis study aimed to facilitate the implementation of mHealth initiatives with mobile physiological sensing in constrained health systems by developing a methodology to systematically evaluate potential challenges and implementation risks.MethodsWe performed a quantitative analysis of physiological data obtained from a randomized household intervention trial that implemented sensor-based mHealth tools (pulse oximetry combined with a respiratory rate assessment app) to monitor health outcomes of 317 children (aged 6-36 months) that were visited weekly by 1 of 9 field workers in a rural Peruvian setting. The analysis focused on data integrity such as data completeness and signal quality. In addition, we performed a qualitative analysis of pretrial usability and semistructured posttrial interviews with a subset of app users (7 field workers and 7 health care center staff members) focusing on data integrity and reasons for loss thereof. Common themes were identified using a content analysis approach. Risk factors of each theme were detailed and then generalized and expanded into a checklist by reviewing 8 mHealth projects from the literature. An expert panel evaluated the checklist during 2 iterations until agreement between the 5 experts was achieved.ResultsPulse oximetry signals were recorded in 78.36% (12,098/15,439) of subject visits where tablets were used. Signal quality decreased for 1 and increased for 7 field workers over time (1 excluded). Usability issues were addressed and the workflow was improved. Users considered the app easy and logical to use. In the qualitative analysis, we constructed a thematic map with the causes of low data integrity. We sorted them into 5 main challenge categories: environment, technology, user skills, user motivation, and subject engagement. The obtained categories were translated into detailed risk factors and presented in the form of an actionable checklist to evaluate possible implementation risks. By visually inspecting the checklist, open issues and sources for potential risks can be easily identified.ConclusionsWe developed a data integrity–based methodology to assess the potential challenges and risks of sensor-based mHealth projects. Aiming at improving data integrity, implementers can focus on the evaluation of environment, technology, user skills, user motivation, and subject engagement challenges. We provide a checklist to assist mHealth implementers with a structured evaluation protocol when planning and preparing projects.

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.

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−1 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−1 and moderate-to-severe patients (AHI ⩾ 5 events h−1). 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 <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.

Complexity-Based Discrepancy Measures Applied to Detection of Apnea-Hypopnea Events

In recent years, an increasing interest in the development of discriminative methods based on sparse representations with discrete dictionaries for signal classification has been observed. It is still unclear, however, what is the most appropriate way for introducing discriminative information into the sparse representation problem. It is also unknown which is the best discrepancy measure for classification purposes. In the context of feature selection problems, several complexity-based measures have been proposed. The main objective of this work is to explore a method that uses such measures for constructing discriminative subdictionaries for detecting apnea-hypopnea events using pulse oximetry signals. Besides traditional discrepancy measures, we study a simple one called Difference of Conditional Activation Frequency (DCAF). We additionally explore the combined effect of overcompleteness and redundancy of the dictionary as well as the sparsity level of the representation. Results show that complexity-based measures are capable of adequately pointing out discriminative atoms. Particularly, DCAF yields competitive averaged detection accuracy rates of 72.57% at low computational cost. Additionally, ROC curve analyses show averaged diagnostic sensitivity and specificity of 81.88% and 87.32%, respectively. This shows that discriminative subdictionary construction methods for sparse representations of pulse oximetry signals constitute a valuable tool for apnea-hypopnea screening.

Quality of an ambulatory monitoring technique for diagnosing obstructive sleep apnea under conditions of limited resources.

Objectives:To: 1) evaluate the quality of an ambulatory monitoring technique for diagnosing Obstructive Sleep Apnea Syndrome (OSAS) while patients move through the city; and 2) identify factors that lead to data loss.Methods:Clinical histories were reviewed and ambulatory portable monitorings of adults with high pretest probability for OSAS were included, the signals monitored were pulse oximetry, heart rate, nasal pressure, snoring, chest band and body position. The equipment was connected from 14:00-20:00 h and then patients moved through the city turning it off and on at home. Results were analyzed visually to record all the minutes lost. A good-quality study was defined as recording time 240 min and signal loss <20%. A cost/benefit analysis was performed using Golpe et al.'s methodology.Results:A total of 70 recordings were analyzed. Most subjects were obese men with severe OSAS. Signal quality was determined to be good with a median signal loss of 4.9 min (0-405) that represented 1% (0-99) of total recording time. The signal lost most often was pulse oximetry at 1.8 min (0-403, p=0.0001). Of the 70 studies performed, 57 (81%) met the definition of good quality, while 13 (19%) had to be repeated. Men lost the pulse oximetry signal more often than women. This technique could represent savings of 65-75%.Conclusions:Placing a portable OSAS monitor during the day while patients move around the city turning it on and off at home does not affect the quality of the study results obtained and is a cost-effective method.

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.

Optimising the Apnoea Classification Performance of a Neural Network Classifier Processing ECG-Oximetry Signals.

In this paper we investigate using principal components analysis to optimize the performance of a neural network system processing simultaneously acquired electrocardiogram (ECG) and oximetry signals. The algorithm identifies epochs of normal breathing, central apnoea (CA), and obstructive apnoea (OA) by processing a pooled feature set containing information capturing the desaturations from the oximeter sensor as well as time and spectral features from the ECG. Training and testing of the system was facilitated with a dataset of 125 scored polysomnogram recordings with accompanying respiratory event annotations. When classifying the three epoch types, our system achieved a specificity of 91%, a sensitivity to CA of 28% and sensitivity to OA of 63%. A sensitivity of 81% was achieved when the CA and OA epochs were combined into one class.

Replace “Have to” With “Want to”

Replace “Have to” With “Want to”

Breathing Rate Estimation From the Electrocardiogram and Photoplethysmogram: A Review.

Breathing rate (BR) is a key physiological parameter used in a range of clinical settings. Despite its diagnostic and prognostic value, it is still widely measured by counting breaths manually. A plethora of algorithms have been proposed to estimate BR from the electrocardiogram (ECG) and pulse oximetry (photoplethysmogram, PPG) signals. These BR algorithms provide opportunity for automated, electronic, and unobtrusive measurement of BR in both healthcare and fitness monitoring. This paper presents a review of the literature on BR estimation from the ECG and PPG. First, the structure of BR algorithms and the mathematical techniques used at each stage are described. Second, the experimental methodologies that have been used to assess the performance of BR algorithms are reviewed, and a methodological framework for the assessment of BR algorithms is presented. Third, we outline the most pressing directions for future research, including the steps required to use BR algorithms in wearable sensors, remote video monitoring, and clinical practice.

Post ROSC perfusion index and survival after out-of-hospital cardiac arrest

Purpose: Peripheral perfusion index (PI) derived from the pulse oximetry signal has been proposed for different clinical uses particularly for critically ill patients. Furthermore, prognostication after out of hospital cardiac arrest (OHCA) is still now an open issue. Our aim was to assess whether PI values measured after the return of spontaneous circulation (ROSC) could predict survival at 30 days.

Pattern Analysis of Oxygen Saturation Variability in Healthy Individuals: Entropy of Pulse Oximetry Signals Carries Information about Mean Oxygen Saturation.

Pulse oximetry is routinely used for monitoring patients' oxygen saturation levels with little regard to the variability of this physiological variable. There are few published studies on oxygen saturation variability (OSV), with none describing the variability and its pattern in a healthy adult population. The aim of this study was to characterize the pattern of OSV using several parameters; the regularity (sample entropy analysis), the self-similarity [detrended fluctuation analysis (DFA)] and the complexity [multiscale entropy (MSE) analysis]. Secondly, to determine if there were any changes that occur with age. The study population consisted of 36 individuals. The “young” population consisted of 20 individuals [Mean (±1 SD) age = 21.0 (±1.36 years)] and the “old” population consisted of 16 individuals [Mean (±1 SD) age = 50.0 (±10.4 years)]. Through DFA analysis, OSV was shown to exhibit fractal-like patterns. The sample entropy revealed the variability to be more regular than heart rate variability and respiratory rate variability. There was also a significant inverse correlation between mean oxygen saturation and sample entropy in healthy individuals. Additionally, the MSE analysis described a complex fluctuation pattern, which was reduced with age (p < 0.05). These findings suggest partial “uncoupling” of the cardio-respiratory control system that occurs with aging. Overall, this study has characterized OSV using pre-existing tools. We have showed that entropy analysis of pulse oximetry signals carries information about body oxygenation. This may have the potential to be used in clinical practice to detect differences in diseased patient subsets.

A novel method to precisely detect apnea and hypopnea events by airflow and oximetry signals

Sleep apnea hypopnea syndrome (SAHS) affects people's quality of life. The apnea hypopnea index (AHI) is the key indicator for diagnosing SAHS. The determination of the AHI is based on accurate detection of apnea and hypopnea events. This paper provides a novel method to detect apnea and hypopnea events based on the respiratory nasal airflow signal and the oximetry signal. The method uses sliding window and short time slice methods to eliminate systematic and sporadic noise of the airflow signal for improving the detection precision. Using this algorithm, the sleep data of 30 subjects from the Huaxi Sleep Center of Sichuan University (HSCSU) and the Teaching Hospital of Chengdu University of Traditional Chinese Medicine (THCUTCM) were auto-analyzed for detecting the apnea and hypopnea events. The total predicted apnea and hypopnea events were 8470. By manual investigation, the sensitivity and positive predictive value (PPV) of detecting apnea and hypopnea events were 97.6% and 95.7%, respectively. The sleep data of 28 subjects form HSCSU were auto-diagnosed SAHS according to the AHI. The sensitivity and PPV were 92.3% and 92.3%, respectively. This is an effective and precise method to diagnose SAHS. It can fit the home care SAHS screener.

Discriminative methods based on sparse representations of pulse oximetry signals for sleep apnea–hypopnea detection

Abstract The obstructive sleep apnea–hypopnea (OSAH) syndrome is a very common and generally undiagnosed sleep disorder. It is caused by repeated events of partial or total obstruction of the upper airway while sleeping. This work introduces two novel approaches called most dicriminative activation selection (MDAS) and most discriminative column selection (MDCS) for the detection of apnea–hypopnea events using only pulse oximetry signals. These approaches use discriminative information of sparse representations of the signals to detect apnea–hypopnea events. Complete (CD) and overcomplete (OD) dictionaries, and three different strategies (FULL sparse representation, MDAS, and MDCS), are considered. Thus, six methods (FULL-OD, MDAS-OD, MDCS-OD, FULL-CD, MDAS-CD, and MDCS-CD) emerge. It is shown that MDCS-OD outperforms all the others methods. A receiver operating characteristic (ROC) curve analysis of this method shows an area under the curve of 0.937 and diagnostic sensitivity and specificity percentages of 85.65 and 85.92, respectively. This shows that sparse representation of pulse oximetry signals is a very valuable tool for estimating apnea–hypopnea indices. The implementation of the MDCS-OD method could be embedded into the oximeter so as to be used by primary attention clinical physicians in the search and detection of patients suspected of suffering from OSAH.

Can We Assess Pulsus Paradoxus through Polysomnography in a Patient with Chronic Obstructive Pulmonary Disease and Sleep-Disordered Breathing?

Pulsus paradoxus (PP) is a decrease in systolic blood pressure greater than 10 mm Hg during inspiration that occurs in various medical conditions. Using polysomnography pulse oximetry signal, photoplethysmography variations of the amplitude of the pulse pressure within the respiratory cycle were observed. There is a proportional relationship between the changes of inspiratory waveform values and the generated PP. A 59-year-old male underwent polysomnography that showed sleep hypoxemia, obstructive sleep-disordered breathing (apnea hypopnea index [AHI] = 5.1and respiratory disturbance index [RDI] = 87.9), with variations of pulse pressure induced primarily by inspiration. The highest variations in the pulse wave were observed in NREM sleep during obstructive respiratory events and in biocalibration during nasal breathing. The lowest variations occurred after the correction of inspiratory obstructive events and during biocalibration when asked to hold his breath.