Automatic detection of respiratory events during sleep from Polysomnography data using Layered Hidden Markov Model

2021 ◽  
Author(s):  
Azadeh Sadoughi ◽  
Mohammad Bagher Shamsollahi ◽  
Emad Fatemizadeh
Keyword(s):  
Sleep Apnea ◽  
Probabilistic Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Automatic Detection ◽  
Detection Algorithm ◽  
Respiratory Disorder ◽  
Respiratory Events ◽  
Increased Risk ◽  
Respiratory Event

Abstract Objective. Sleep apnea is a serious respiratory disorder, which is associated with increased risk factors for cardiovascular disease. Many studies in recent years have been focused on automatic detection of sleep apnea from polysomnography (PSG) recordings, however, detection of subtle respiratory events named Respiratory Event Related Arousals (RERAs) that do not meet the criteria for apnea or hypopnea is still challenging. The objective of this study was to develop automatic detection of sleep apnea based on Hidden Markov Models (HMMs) which are probabilistic models with the ability to learn different dynamics of the real time-series such as clinical recordings. Approach. In this study, a hierarchy of HMMs named Layered HMM was presented to detect respiratory events from PSG recordings. The recordings of 210 PSGs from Massachusetts General Hospital’s database were used for this study. To develop detection algorithms, extracted feature signals from airflow, movements over the chest and abdomen, and oxygen saturation in blood (SaO2) were chosen as observations. The respiratory disturbance index (RDI) was estimated as the number of apneas, hypopneas, and RERAs per hour of sleep. Main results. The best F1 score of the event by event detection algorithm was between 0.22±0.16 and 0.70±0.08 for different groups of sleep apnea severity. There was a strong correlation between the estimated and the PSG-derived RDI (R2=0.91, p<0.0001). The best recall of RERA detection was achieved 0.45±0.27. Significance. The results showed that the layered structure can improve the performance of the detection of respiratory events during sleep.

scholarly journals Automatic detection of alpine rockslides in continuous seismic data using hidden Markov models

2016 ◽  
Vol 121 (2) ◽  
pp. 351-371 ◽  
Author(s):  
Franziska Dammeier ◽  
Jeffrey R. Moore ◽  
Conny Hammer ◽  
Florian Haslinger ◽  
Simon Loew
Keyword(s):  
Hidden Markov Models ◽  
Seismic Data ◽  
Markov Models ◽  
Hidden Markov ◽  
Automatic Detection

scholarly journals Respiratory events associated with concomitant opioid and sedative use among Medicare beneficiaries with chronic obstructive pulmonary disease

2020 ◽  
Vol 7 (1) ◽  
pp. e000483 ◽  
Author(s):  
Tham Thi Le ◽  
Siyeon Park ◽  
Michelle Choi ◽  
Marniker Wijesinha ◽  
Bilal Khokhar ◽  
...  
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Older Adults ◽  
Pulmonary Disease ◽  
Chronic Obstructive ◽  
Medicare Beneficiaries ◽  
Opioid Use ◽  
Obstructive Pulmonary Disease ◽  
Respiratory Events ◽  
Increased Risk ◽  
Respiratory Event

BackgroundOpioids and sedatives are commonly prescribed in chronic obstructive pulmonary disease (COPD) patients for symptoms of dyspnoea, pain, insomnia, depression and anxiety. Older adults are advised to avoid these medications due to increased adverse events, including respiratory events. This study examines respiratory event risks associated with concomitant opioid and sedative use compared with opioid use alone in older adults with COPD.MethodsA 5% nationally representative sample of Medicare beneficiaries with COPD and opioid use between 2009 and 2013 was used for this retrospective cohort study. Current and past concomitant use were identified using drug dispensed within 7 days from the censored date: at respiratory event, at death, or at 12 months post index. Concomitant opioid and sedative use were categorised into no overlap (opioid only), 1 to 10, 11 to 30, 31 to 60 and >60 days of total overlap. The primary outcome was hospitalisation or emergency department (ED) visits for respiratory events (COPD exacerbations or respiratory depression). Propensity score matching was implemented and semi-competing risk models were used to address competing risk by death.ResultsAmong 48 120 eligible beneficiaries, 1810 (16.7%) concomitant users were matched with 9050 (83.3%) opioid only users. Current concomitant use of 1 to 10, 11 to 30 and 31 to 60 days was associated with increased respiratory events (HRs (95% CI): 2.8 (1.2 to 7.3), 9.3 (4.9 to 18.2) and 5.7 (2.5 to 12.5), respectively), compared with opioid only use. Current concomitant use of >60 days or past concomitant use of ≤60 days was not significantly associated with respiratory events. Consistent findings were found in sensitivity analyses, including in subgroup analysis of non-benzodiazepine sedatives. Additionally, current concomitant use significantly increased risk of death.ConclusionShort-term and medium-term current concomitant opioid and sedative use significantly increased risk of respiratory events and death in older COPD Medicare beneficiaries. Long-term past concomitant users, however, demonstrated lower risks of these outcomes, possibly reflecting a healthy user effect or developed tolerance to the effects of these agents.

Short-Term Impact of Sleep Apnea/Hypopnea on the Interaction Between Various Cortical Areas

2020 ◽  
pp. 155005942096544
Author(s):  
Guo-Lin Zhou ◽  
Yu Pan ◽  
Yuan-Yuan Liao ◽  
Jiu-Xing Liang ◽  
Xiang-Min Zhang ◽  
...  
Keyword(s):  
Sleep Apnea ◽  
Flow Direction ◽  
Brain Activity ◽  
Permutation Entropy ◽  
Cortical Arousal ◽  
Eeg Activity ◽  
Respiratory Events ◽  
Respiratory Event ◽  
Brain Structure And Function ◽  
Cortical Regions

Introduction Sleep apnea/hypopnea syndrome (SAHS) can change brain structure and function. These alterations are related to respiratory event-induced abnormal sleep, however, how brain activity changes during these events is less well understood. Methods To study information content and interaction among various cortical regions, we analyzed the variations of permutation entropy (PeEn) and symbolic transfer entropy (STE) of electroencephalography (EEG) activity during respiratory events. In this study, 57 patients with moderate SAHS were enrolled, including 2804 respiratory events. The events terminated with cortical arousal were independently researched. Results PeEn and STE were lower during apnea/hypopnea, and most of the brain interaction was higher after apnea/hypopnea termination than that before apnea in N2 stage. As indicated by STE, the respiratory events also affected the stability of information transmission mode. In N1, N2, and rapid eye movement (REM) stages, the information flow direction was posterior-to-anterior, but the anterior-to-posterior increased relatively during apnea/hypopnea. The above EEG activity trends maintained in events with cortical arousal. Conclusions These results may be related to the intermittent hypoxia during apnea and the cortical response. Furthermore, increased frontal information outflow, which was related to the compensatory activation of frontal neurons, may associate with cognitive function.

Extending hidden Markov models to allow conditioning on previous observations

2018 ◽  
Vol 16 (05) ◽  
pp. 1850019 ◽  
Author(s):  
Ioannis A. Tamposis ◽  
Margarita C. Theodoropoulou ◽  
Konstantinos D. Tsirigos ◽  
Pantelis G. Bagos
Keyword(s):  
Hidden Markov Models ◽  
Probabilistic Models ◽  
Markov Models ◽  
Transition Probabilities ◽  
Hidden Markov ◽  
Simple Extension ◽  
Computational Molecular Biology ◽  
Current State ◽  
Observation Sequence ◽  
Hidden States

Hidden Markov Models (HMMs) are probabilistic models widely used in computational molecular biology. However, the Markovian assumption regarding transition probabilities which dictates that the observed symbol depends only on the current state may not be sufficient for some biological problems. In order to overcome the limitations of the first order HMM, a number of extensions have been proposed in the literature to incorporate past information in HMMs conditioning either on the hidden states, or on the observations, or both. Here, we implement a simple extension of the standard HMM in which the current observed symbol (amino acid residue) depends both on the current state and on a series of observed previous symbols. The major advantage of the method is the simplicity in the implementation, which is achieved by properly transforming the observation sequence, using an extended alphabet. Thus, it can utilize all the available algorithms for the training and decoding of HMMs. We investigated the use of several encoding schemes and performed tests in a number of important biological problems previously studied by our team (prediction of transmembrane proteins and prediction of signal peptides). The evaluation shows that, when enough data are available, the performance increased by 1.8%–8.2% and the existing prediction methods may improve using this approach. The methods, for which the improvement was significant (PRED-TMBB2, PRED-TAT and HMM-TM), are available as web-servers freely accessible to academic users at www.compgen.org/tools/ .

scholarly journals Automatic detection of snow avalanches in continuous seismic data using hidden Markov models

2018 ◽  
Vol 18 (1) ◽  
pp. 383-396 ◽  
Author(s):  
Matthias Heck ◽  
Conny Hammer ◽  
Alec van Herwijnen ◽  
Jürg Schweizer ◽  
Donat Fäh
Keyword(s):  
Hidden Markov Models ◽  
Seismic Data ◽  
Markov Models ◽  
Hidden Markov ◽  
Winter Season ◽  
Automatic Detection ◽  
Seismic Signals ◽  
Snow Avalanches ◽  
Data Set ◽  
Processing Steps

Abstract. Snow avalanches generate seismic signals as many other mass movements. Detection of avalanches by seismic monitoring is highly relevant to assess avalanche danger. In contrast to other seismic events, signals generated by avalanches do not have a characteristic first arrival nor is it possible to detect different wave phases. In addition, the moving source character of avalanches increases the intricacy of the signals. Although it is possible to visually detect seismic signals produced by avalanches, reliable automatic detection methods for all types of avalanches do not exist yet. We therefore evaluate whether hidden Markov models (HMMs) are suitable for the automatic detection of avalanches in continuous seismic data. We analyzed data recorded during the winter season 2010 by a seismic array deployed in an avalanche starting zone above Davos, Switzerland. We re-evaluated a reference catalogue containing 385 events by grouping the events in seven probability classes. Since most of the data consist of noise, we first applied a simple amplitude threshold to reduce the amount of data. As first classification results were unsatisfying, we analyzed the temporal behavior of the seismic signals for the whole data set and found that there is a high variability in the seismic signals. We therefore applied further post-processing steps to reduce the number of false alarms by defining a minimal duration for the detected event, implementing a voting-based approach and analyzing the coherence of the detected events. We obtained the best classification results for events detected by at least five sensors and with a minimal duration of 12 s. These processing steps allowed identifying two periods of high avalanche activity, suggesting that HMMs are suitable for the automatic detection of avalanches in seismic data. However, our results also showed that more sensitive sensors and more appropriate sensor locations are needed to improve the signal-to-noise ratio of the signals and therefore the classification.

scholarly journals Predictors of changes in cerebral perfusion and oxygenation during obstructive sleep apnea

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Zhongxing Zhang ◽  
Ming Qi ◽  
Gordana Hügli ◽  
Ramin Khatami
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Near Infrared ◽  
Sleep Apnea Syndrome ◽  
Apnea Hypopnea Index ◽  
Mixed Effect ◽  
Respiratory Events ◽  
Obstructive Sleep ◽  
Respiratory Event ◽  
Titration Protocol

AbstractObstructive sleep apnea syndrome (OSAS) is a common sleep disorder. Severe OSAS defined as apnea–hypopnea index (AHI) ≥ 30/h is a risk factor for developing cerebro-cardiovascular diseases. The mechanisms of how repetitive sleep apneas/hypopneas damage cerebral hemodynamics are still not well understood. In this study, changes in blood volume (BV) and oxygen saturation (StO2) in the left forehead of 29 newly diagnosed severe OSAS patients were measured by frequency-domain near-infrared spectroscopy during an incremental continuous positive airway pressure (CPAP) titration protocol together with polysomnography. The coefficients of variation of BV (CV-BV) and the decreases of StO2 (de-StO2) of more than 2000 respiratory events were predicted using linear mixed-effect models, respectively. We found that longer events and apneas rather than hypopneas induce larger changes in CV-BV and stronger cerebral desaturation. Respiratory events occurring during higher baseline StO2 before their onsets, during rapid-eye-movement sleep and those associated with higher heart rate induce smaller changes in CV-BV and de-StO2. The stepwise increased CPAP pressures can attenuate these changes. These results suggest that in severe OSAS the length and the type of respiratory event rather than widely used AHI may be better parameters to indicate the severity of cerebral hemodynamic changes.

scholarly journals Respiratory events in patients undergoing laparoscopic gastric bypass surgery

F1000Research ◽  
2012 ◽  
Vol 1 ◽  
pp. 44 ◽  
Author(s):  
Patrick Ziemann-Gimmel ◽  
Priscilla Hensel ◽  
Salam Abdo ◽  
John Koppman ◽  
Robert Marema
Keyword(s):  
Gastric Bypass ◽  
Laparoscopic Gastric Bypass ◽  
Bypass Surgery ◽  
Gastric Bypass Surgery ◽  
Postoperative Management ◽  
Cpap Therapy ◽  
Respiratory Events ◽  
Obstructive Sleep ◽  
Increased Risk ◽  
Respiratory Event

Background: The incidence of morbid obesity is increasing and has led to an increase in bariatric procedures and previous studies have shown that 71% of these patients suffer from obstructive sleep apnea (OSA). Patients with OSA have a higher rate of postoperative complications. We investigated if patients with OSA undergoing laparoscopic gastric bypass surgery have an increased risk of postoperative respiratory events. In this observational study we examined the data of 89 consecutive patients undergoing gastric bypass surgery.Methods: All patients scheduled for gastric bypass surgery between 7/28/2010 and 02/15/2011 were enrolled and managed according to our routine clinical protocol (48 with OSA / 41 without OSA (NOSA)). Depending on the patient’s preoperative compliance with CPAP therapy, they were further assigned into a compliant (OSAc) and noncompliant (OSAn) group. A respiratory event was defined as a deviation from the regular postoperative management.Results: Both OSA and NOSA groups were similar based on clinical characteristics and narcotic consumption. Fourteen patients (29.2%) suffered from a respiratory event in the OSA group and 8 patients (19.5%) in the NOSA group (p=0.29). Patients compliant with continuous positive airway pressure CPAP had a similar complication rate to patients without OSA (p=0.96). 53.8% of patients with OSA that were noncompliant with CPAP therapy (OSAn) had a respiratory event in the direct postoperative period. This is statistically significant in comparison to patients diagnosed with OSA that are compliant with CPAP (OSAc) (p=0.03)Conclusion: It may be beneficial to encourage OSA patients to use CPAP preoperatively to reduce postoperative respiratory events. Furthermore, adequately treated OSA may not be an independent risk factor for postoperative respiratory events.

scholarly journals A Stochastic Framework for Evaluating Seizure Prediction Algorithms Using Hidden Markov Models

2007 ◽  
Vol 97 (3) ◽  
pp. 2525-2532 ◽  
Author(s):  
Stephen Wong ◽  
Andrew B. Gardner ◽  
Abba M. Krieger ◽  
Brian Litt
Keyword(s):  
Markov Models ◽  
Hidden Markov ◽  
Detection Algorithm ◽  
Type I ◽  
Seizure Prediction ◽  
Seizure Onset ◽  
Statistical Validation ◽  
Prediction Algorithms ◽  
Prediction Horizon ◽  
Stochastic Framework

Responsive, implantable stimulation devices to treat epilepsy are now in clinical trials. New evidence suggests that these devices may be more effective when they deliver therapy before seizure onset. Despite years of effort, prospective seizure prediction, which could improve device performance, remains elusive. In large part, this is explained by lack of agreement on a statistical framework for modeling seizure generation and a method for validating algorithm performance. We present a novel stochastic framework based on a three-state hidden Markov model (HMM) (representing interictal, preictal, and seizure states) with the feature that periods of increased seizure probability can transition back to the interictal state. This notion reflects clinical experience and may enhance interpretation of published seizure prediction studies. Our model accommodates clipped EEG segments and formalizes intuitive notions regarding statistical validation. We derive equations for type I and type II errors as a function of the number of seizures, duration of interictal data, and prediction horizon length and we demonstrate the model's utility with a novel seizure detection algorithm that appeared to predicted seizure onset. We propose this framework as a vital tool for designing and validating prediction algorithms and for facilitating collaborative research in this area.

scholarly journals Sleep quality, autonomic dysfunction and renal function in diabetic patients with pre-CKD phase

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Manabu Kadoya ◽  
Akiko Morimoto ◽  
Akio Miyoshi ◽  
Miki Kakutani-Hatayama ◽  
Kae Kosaka-Hamamoto ◽  
...  
Keyword(s):  
Risk Factors ◽  
Renal Function ◽  
Sleep Apnea ◽  
Sleep Quality ◽  
Cox Proportional Hazards ◽  
Renal Outcome ◽  
Diabetic Patients ◽  
Poor Sleep ◽  
Increased Risk ◽  
Respiratory Event

AbstractDiabetes has been established as a strong risk factor for chronic kidney disease (CKD). Sleep apnea, poor sleep quality (PSQ), and autonomic imbalance are also considered to be potential risk factors for decline in renal function, though no known study has examined their integrated predictive value in diabetic and non-diabetic patients without CKD. The present cohort consisted of 754 serial patients (diabetes; n = 231, non-diabetes; n = 523) without CKD registered in the Hyogo Sleep Cardio-Autonomic Atherosclerosis (HSCAA) study. Patients underwent examinations to determine respiratory event index and objective sleep quality using actigraphy, as well as heart rate variability (HRV). Renal outcome was defined as a decline in estimated glomerular filtration rate to less than 60 ml/min/1.73 m2 for more than 3 months. Kaplan–Meier analysis showed that diabetic patients with PSQ or low HRV, but not sleep apnea, had a significantly increased risk for renal outcome. Furthermore, Cox proportional hazards analysis revealed that PSQ was significantly associated with elevated risk of renal outcome (HR: 2.57; 95% CI: 1.01–6.53, p = 0.045) independent of sleep apnea and classical risk factors. Low HRV tended to be, but not significantly (p = 0.065), associated with the outcome. In non-diabetic patients, PSQ was also significantly and independently associated with renal outcome, whereas sleep apnea and low HRV were not. In conclusion, PSQ and low HRV appear to be important predictors of decline in renal function in diabetic patients without CKD.

Sign in / Sign up

Export Citation Format

Share Document