Tracheal sound-based apnea detection using hidden Markov model in sedated volunteers and post anesthesia care unit patients.

The current method of apnea detection based on tracheal sounds is limited in certain situations. In this work, the Hidden Markov Model (HMM) algorithm based on segmentation is used to classify the respiratory and non-respiratory states of tracheal sounds, to achieve the purpose of apnea detection. Three groups of tracheal sounds were used, including two groups of data collected in the laboratory and a group of patient data in the post anesthesia care unit (PACU). One was used for model training, and the others (laboratory test group and clinical test group) were used for testing and apnea detection. The trained HMMs were used to segment the tracheal sounds in laboratory test data and clinical test data. Apnea was detected according to the segmentation results and respiratory flow rate/pressure which was the reference signal in two test groups. The sensitivity, specificity, and accuracy were calculated. For the laboratory test data, apnea detection sensitivity, specificity, and accuracy were 96.9%, 95.5%, and 95.7%, respectively. For the clinical test data, apnea detection sensitivity, specificity, and accuracy were 83.1%, 99.0% and 98.6%. Apnea detection based on tracheal sound using HMM is accurate and reliable for sedated volunteers and patients in PACU.

New method to measure interbreath intervals in infants for the assessment of apnoea and respiration.

BACKGROUND: Respiratory disorders, including apnoea, are common in preterm infants due to their immature respiratory control compared with term-born infants. However, our inability to accurately measure respiratory rate in hospitalised infants results in unreported episodes of apnoea and an incomplete picture of respiratory activity. METHODS: We develop, validate and use a novel algorithm to identify interbreath intervals (IBIs) and apnoeas in preterm infants. In 42 preterm infants (1600 hours of recordings), we assess IBIs from the chest electrical impedance pneumograph using an adaptive amplitude threshold for the detection of breaths. The algorithm is refined by comparing its accuracy with clinically observed breaths and pauses in breathing. We develop an automated classifier to differentiate periods of true apnoea from artefactually low amplitude signal. We assess the performance of this algorithm in the detection of morphine-induced respiratory depression. Finally, we use the algorithm to investigate whether retinopathy of prematurity (ROP) screening alters the IBI distribution. RESULTS: Individual breaths were detected with a false-positive rate of 13% and a false-negative rate of 12%. The classifier identified true apnoeas with an accuracy of 93%. As expected, morphine caused a significant shift in the IBI distribution towards longer IBIs. Following ROP screening, there was a significant increase in pauses in breathing that lasted more than 10 s (t-statistic=1.82, p=0.023). This was not reflected by changes in the monitor-derived respiratory rate and no episodes of apnoea were recorded in the medical records. CONCLUSIONS: We show that our algorithm offers an improved method for the identification of IBIs and apnoeas in preterm infants. Following ROP screening, increased respiratory instability can occur even in the absence of clinically significant apnoeas. Accurate assessment of infant respiratory activity is essential to inform clinical practice.

Detection of Apnea Bradycardia from ECG Signals of Preterm Infants Using Layered Hidden Markov Model.

Apnea-bradycardia (AB) is a common complication in prematurely born infants, which is associated with reduced survival and neurodevelopmental outcomes. Thus, early detection or predication of AB episodes is critical for initiating preventive interventions. To develop automatic real-time operating systems for early detection of AB, recent advances in signal processing can be employed. Hidden Markov Models (HMM) are probabilistic models with the ability of learning different dynamics of the real time-series such as clinical recordings. In this study, a hierarchy of HMMs named as layered HMM was presented to detect AB episodes from pre-processed single-channel Electrocardiography (ECG). For training the hierarchical structure, RR interval, and width of QRS complex were extracted from ECG as observations. The recordings of 32 premature infants with median 31.2 (29.7, 31.9) weeks of gestation were used for this study. The performance of the proposed layered HMM was evaluated in detecting AB. The best average accuracy of 97.14 ± 0.31% with detection delay of - 5.05 ± 0.41 s was achieved. The results show that layered structure can improve the performance of the detection system in early detecting of AB episodes. Such system can be incorporated for more robust long-term monitoring of preterm infants.

Prediction of Apnea Testing Duration to Ensure Safety During Brain Death Assessment.

BACKGROUND: Apnea testing is the last step of brain death assessment. This study aimed to determine whether apnea testing is safer when performed over a shorter duration. METHODS: The medical records of 200 brain-dead donors were retrospectively evaluated. All the records were anonymously registered in the Japanese Ministry of Health, Labor, and Welfare from 1999 to 2012. The rate of [Formula: see text] increase was analyzed to calculate the duration required for apnea testing. RESULTS: At baseline, body temperature and [Formula: see text] significantly affected the increase rate of [Formula: see text]. At baseline, the apnea testing durations were 4.7 min with normal body temperature and higher [Formula: see text] ([Formula: see text] 40-60 mm Hg, body temperature 36.5°C, [Formula: see text] 400 mm Hg); further, it was 3.0 min with higher body temperature and lower [Formula: see text] at baseline ([Formula: see text] 40-60 mm Hg, body temperature 38.0°C, [Formula: see text] 100 mm Hg). CONCLUSIONS: The specific duration of apnea testing during brain death assessment may be predicted by measuring the increase rate of [Formula: see text].

Apnea bradycardia detection based on new coupled hidden semi Markov model.

In this paper, a method for apnea bradycardia detection in preterm infants is presented based on coupled hidden semi Markov model (CHSMM). CHSMM is a generalization of hidden Markov models (HMM) used for modeling mutual interactions among different observations of a stochastic process through using finite number of hidden states with corresponding resting time. We introduce a new set of equations for CHSMM to be integrated in a detection algorithm. The detection algorithm was evaluated on a simulated data to detect a specific dynamic and on a clinical dataset of electrocardiogram signals collected from preterm infants for early detection of apnea bradycardia episodes. For simulated data, the proposed algorithm was able to detect the desired dynamic with sensitivity of 96.67% and specificity of 98.98%. Furthermore, the method detected the apnea bradycardia episodes with 94.87% sensitivity and 96.52% specificity with mean time delay of 0.73 s. The results show that the algorithm based on CHSMM is a robust tool for monitoring of preterm infants in detecting apnea bradycardia episodes. Graphical Abstract Apnea Bradycardia detection using Coupled hidden semi Markov Model from electrocardiography. In this model, a sequence of hidden states is assigned to each observation based on the effects of previous states of all observations.

Brain Death.

Death determined by neurologic criteria, commonly referred to as "brain death," occurs when function of the entire brain ceases, including the brain stem. Diagnostic criteria for brain death are explicit but controversy exists regarding nuances of the evaluation and potential confounders of the examination. Hospitals and ICU teams should carefully consider which clinicians will perform brain death testing and should use standard processes, including checklists to prevent diagnostic errors. Proper diagnosis is essential because misdiagnosis can be catastrophic. Timely, accurate brain death determination and aggressive physiologic support are cornerstones of both good end-of-life care and successful organ donation.

A low cost, simplified, and scaleable pneumotachograph and face mask for neonatal mouse respiratory measurements.

INTRODUCTION: Neonatal respiratory disorders are a leading cause of perinatal mortality due to complications resulting from premature births and prenatal exposure to drugs of abuse, but optimal treatments for these symptoms are still unclear due to a variety of confounds and risk factors. Mouse models present an opportunity to study the underlying mechanisms and efficacy of potential treatments of these conditions with controlled variables. However, measuring respiration in newborn mice is difficult and commercial components are expensive and often require modification, creating a barrier and limiting our understanding of the short and long-term effects of birth complications on respiratory function. METHODS: Here, we present an inexpensive and simple flow through pneumotachograph and face mask design that can be easily scaled for parallel, high-throughput assays measuring respiration in neonatal mouse pups. The final apparatus consists of three main parts: a water-jacketed chamber, an integrated support tray for the pup, and a pneumotachograph consisting of a two side-arm air channel that is attached to a pressure transducer. RESULTS: The pneumotach showed a linear response and clean, steady respiratory traces in which apneas and sighs were clearly visible. Administration of caffeine in P0.5 CD1 wildtype neonates resulted in an increase in tidal volume, minute ventilation, and minute ventilation normalized to oxygen consumption as well as a decrease in periodic instability. DISCUSSION: The described methods offer a relatively simple and inexpensive approach to constructing a pneumotachograph for non-invasive measurements of neonatal mouse respiration, enhancing accessibility and enabling the high-throughput and parallel characterizations of neonatal respiratory disorders and potential pharmacological therapies.

Apnea in the Otherwise Healthy, Term Newborn: National Prevalence and Utilization during the Birth Hospitalization.

OBJECTIVES: To describe the prevalence of apnea in otherwise healthy term newborns, identify attributable length of stay (LOS) and healthcare utilization (cost) of apnea, and measure hospital variation in attributable LOS and cost of apnea in this population. STUDY DESIGN: We conducted a secondary analysis of a national administrative dataset, the 2012 Kids' Inpatient Database, which included 3.4 million newborn discharges in the US. The birth hospitalizations of approximately 2.6 million otherwise healthy, full-term newborns were included for analysis. Attributable LOS and cost of apnea were calculated using multivariate analyses. RESULTS: Apnea was diagnosed in 1 in 1000 healthy full-term newborns. Multivariate analyses showed that newborns with apnea had 0.6 days longer LOS (P < .001) and $483 greater costs (P < .001) compared with healthy term newborns, per birth hospitalization. Newborns diagnosed with apnea plus hypoxia and/or bradycardia had 1.4 days longer LOS (P < .001) and $653 greater costs (P < .001). The attributable LOS and cost attributable to apnea varied between individual hospitals and differed by hospital region. CONCLUSIONS: Apnea is associated with higher LOS and cost in the newborn hospitalization, with variation in hospital practice. This suggests the need for better comprehension of the underlying physiology and standardization of practice in its management in the term newborn.

Apnea test during brain death assessment in mechanically ventilated and ECMO patients.

PURPOSE: To evaluate the feasibility and efficacy of an apnea test (AT) technique that combines the application of positive end expiratory pressure (PEEP) with subsequent pulmonary recruitment in a large cohort of brain-dead patients. METHODS: This study was a retrospective analysis of prospectively collected data on brain-dead patients admitted to our institution (Hospital San Gerardo, Monza, Italy) between January 2010 and December 2014. The rate of aborted apnea tests (ATs), occurrence of complications (i.e., pneumothorax, cardiac arrhythmias, cardiac arrest, and severe hypoxia, defined as PaO2 < 40 mmHg), ventilator settings, hemodynamics, and blood gas analyses were evaluated. Subgroup analysis was performed, with patients classified into veno-arterial extracorporeal membrane oxygenation (ECMO) or non-ECMO groups, and into hypoxic (i.e., baseline PaO2/FiO2 < 200 mmHg) and non-hypoxic (i.e., baseline PaO2/FiO2 > 200 mmHg) groups. RESULTS: In total, 169 consecutive patients including 25 on ECMO were included in the study. No AT abortion nor severe complications were detected. The AT was completed in all patients. Fluid boluses and increases or initiation of vasoactive drugs were required in less than 10 and 3% of the AT procedures, respectively. No clinically meaningful alteration in hemodynamics was recorded. Severe hypoxia occurred during 7 (2.4%) and 4 (8%) of the ATs performed in non-ECMO and ECMO patients, respectively (p = 0.063), and it occurred more frequently in hypoxic patients than in non-hypoxic patients (11.1 vs. 4.8%, respectively; p = 0.002). CONCLUSIONS: In a large cohort of consecutive patients, including the largest patient population on ECMO reported to date, our AT technique that combines the application of PEEP with subsequent pulmonary recruitment proved to be feasible and safe.

Coupled Hidden Markov Model-Based Method for Apnea Bradycardia Detection.

In this paper, we present a novel framework for the coupled hidden Markov model (CHMM), based on the forward and backward recursions and conditional probabilities, given a multidimensional observation. In the proposed framework, the interdependencies of states networks are modeled with Markovian-like transition laws that influence the evolution of hidden states in all channels. Moreover, an offline inference approach by maximum likelihood estimation is proposed for the learning procedure of model parameters. To evaluate its performance, we first apply the CHMM model to classify and detect disturbances using synthetic data generated by the FitzHugh-Nagumo model. The average sensitivity and specificity of the classification are above 93.98% and 95.38% and those of the detection reach 94.49% and 99.34%, respectively. The method is also evaluated using a clinical database composed of annotated physiological signal recordings of neonates suffering from apnea-bradycardia. Different combinations of beat-to-beat features extracted from electrocardiographic signals constitute the multidimensional observations for which the proposed CHMM model is applied, to detect each apnea bradycardia episode. The proposed approach is finally compared to other previously proposed HMM-based detection methods. Our CHMM provides the best performance on this clinical database, presenting an average sensitivity of 95.74% and specificity of 91.88% while it reduces the detection delay by -0.59 s.

Assessment of heart rate variability in breath holding children by 24 hour Holter monitoring.

PURPOSE: Previous studies have shown that the underlying pathophysiologic mechanism in children with breath holding may be generalised autonomic dysregulation. Thus, we performed cardiac rhythm and heart rate variability analyses using 24-hour Holter monitoring to evaluate the cardiac effects of autonomic dysregulation in children with breath-holding spells. METHODS: We performed cardiac rhythm and heart rate analyses using 24-hour Holter monitors to evaluate the cardiac effects of autonomic dysregulation in children during a breath-holding spell. Our study group consisted of 68 children with breath-holding spells - 56 cyanotic type and 12 pallid type - and 39 healthy controls. RESULTS: Clinical and heart rate variability results were compared between each spell type - cyanotic or pallid - and the control group; significant differences (p<0.05) in standard deviation of all NN intervals, mean of the standard deviations of all NN intervals for all 5-minute segments, percentage of differences between adjacent RR intervals >50 ms, and square root of the mean of the sum of squares of the differences between adjacent NN intervals values were found between the pallid and cyanotic groups. CONCLUSIONS: Holter monitoring for 24 hours and heart rate variability parameters, particularly in children with pallid spells, are crucial for evaluation of cardiac rhythm changes.

Online apnea-bradycardia detection based on hidden semi-Markov models.

In this paper, we propose a new online apnea-bradycardia detection scheme that takes into account not only the instantaneous values of time series, but also their temporal evolution. The detector is based on a set of hidden semi-Markov models, representing the temporal evolution of beat-to-beat interval (RR interval) time series. A preprocessing step, including quantization and delayed version of the observation vector, is also proposed to maximize detection performance. This approach is quantitatively evaluated through simulated and real signals, the latter being acquired in neonatal intensive care units (NICU). Compared to two conventional detectors used in NICU, our best detector shows an improvement on average of around 15 % in sensitivity and 7 % in specificity. Furthermore, a reduced detection delay of approximately 2 s is also observed with respect to conventional detectors.

Caffeine for apnea of prematurity: a neonatal success story.

Caffeine, a methylxanthine and nonspecific inhibitor of adenosine receptors, is an example of a drug that has been in use for more than 40 years. It is one of the most commonly prescribed drugs in neonatal medicine. However, until 2006, it had only a few relatively small and short-term studies supporting its use. It is thanks to the efforts of Barbara Schmidt and the Caffeine for Apnea of Prematurity (CAP) Trial Group that we now have high-quality and reliable data not only on short-term but also long-term outcomes of caffeine use for apnea of prematurity. CAP was an international, multicenter, placebo-controlled randomized trial designed to determine whether survival without neurodevelopmental disability at a corrected age of 18 months is improved if apnea of prematurity is managed without methylxanthines in infants at a high risk of apneic attacks. CAP was kept simple and pragmatic in order to allow for maximum generalizability and applicability. Infants with birth weights of 500-1,250 g were enrolled during the first 10 days of life if their clinicians considered them to be candidates for methylxanthine therapy. The most frequent indication for therapy reported in CAP was treatment of documented apnea, followed by the facilitation of the removal of an endotracheal tube. Only about 20% of the neonatologists in the trial started caffeine for the prevention of apnea and the findings of CAP cannot automatically be extrapolated to an exclusive prophylactic indication. However, recent data suggest that the administration of prophylactic methylxanthine by neonatologists is now common practice.

Triage in the Tower of Babel: interpreter services for children in the prehospital setting.

Minority pediatric populations have higher rates of emergency medical services use than the general pediatric population, and prior studies have documented that limited-English proficiency patients are more likely to undergo invasive procedures, require more resources, and be admitted once they arrive in the emergency department. Furthermore, limited-English proficiency patients may be particularly vulnerable because of immigration or political concerns. In this case report, we describe an infant with breath-holding spells for whom a language barrier in the prehospital setting resulted in an escalation of care to the highest level of trauma team activation. This infant underwent unnecessary, costly, and harmful interventions because of a lack of interpreter services. In a discussion of the legal, ethical, and medical implications of this case, we conclude that further investigation into prehospital strategies for overcoming language barriers is required to provide optimal prehospital care for pediatric patients.

Apnea testing during brain death assessment: a review of clinical practice and published literature.

The diagnosis of brain death is a complex process. Strong knowledge of neurophysiology and an understanding of brain death etiology must be used to confidently determine brain death. The key findings in brain death are unresponsiveness, and absence of brainstem reflexes in the setting of a devastating neurological injury. These findings are coupled with a series of confirmatory tests, and the diagnosis of brain death is established based on consensus recommendations. The drive to breathe in the setting of an intense ventilatory stimulus (ie, respiratory acidosis) is a critical marker of brainstem function. As a consequence, apnea testing is an important component of brain death assessment. This procedure requires close monitoring of a patient as all ventilator support is temporarily removed and Paco2 levels are allowed to rise. A "positive" test is defined by a total absence of respiratory efforts under these conditions. While apnea testing is not new, it still lacks consensus standardization regarding the actual procedure, monitored parameters, and evidence-based safety measures that may be used to prevent complications. The purpose of this report is to provide an overview of apnea testing and discuss issues related to the administration and safety of the procedure.

Medical retrieval and needs of infants with bronchiolitis: an analysis by gestational age.

AIM: Viral bronchiolitis is the most common lower respiratory tract infection in children less than 12 months of age. Prematurity is an independent risk factor for disease severity. Many infected infants require hospitalisation and those living in regional centres frequently require transfer to metropolitan hospitals capable of providing assisted ventilation. METHOD: We reviewed infants with bronchiolitis transported by the Victorian Newborn Emergency Transport Service between January 2003 and June 2007. We compared the clinical presentation and treatment required by infants born preterm with those of their term counterparts. RESULTS: Of the 192 infants transported, 92 were born preterm. Preterm infants were younger at time of transport (mean post-menstrual age 41 weeks vs. 45 weeks) and were more likely to require invasive ventilation (60% vs. 32%, P < 0.001) and to receive a fluid bolus (47% vs. 34%, P = 0.04) when compared with infants who had been born at term. Apnoea, either as a presenting symptom or in combination with respiratory distress, was more common in the preterm group (70% vs. 36%, P < 0.001). CONCLUSION: Higher illness severity should be anticipated in ex-preterm infants who present with bronchiolitis. Preterm infants with bronchiolitis are more likely to require invasive ventilation and fluid resuscitation than term infants, suggesting the need for a lower threshold for referral and medical retrieval.

On-line apnea-bradycardia detection using hidden semi-Markov models.

In this work, we propose a detection method that exploits not only the instantaneous values, but also the intrinsic dynamics of the RR series, for the detection of apnea-bradycardia episodes in preterm infants. A hidden semi-Markov model is proposed to represent and characterize the temporal evolution of observed RR series and different pre-processing methods of these series are investigated. This approach is quantitatively evaluated through synthetic and real signals, the latter being acquired in neonatal intensive care units (NICU). Compared to two conventional detectors used in NICU our best detector shows an improvement of around 13% in sensitivity and 7% in specificity. Furthermore, a reduced detection delay of approximately 3 seconds is obtained with respect to conventional detectors.

Mallampati class is not useful in the clinical assessment of sleep clinic patients.

STUDY OBJECTIVES: To assess the utility of Mallampati class, a simple grade of oropharyngeal appearance used to assess difficulty of intubation, to predict severe obstructive sleep apnea and absence of OSA (rule in severe OSA and rule out OSA). METHOD: Retrospective review of consecutive patients undergoing diagnostic polysomnography in a tertiary referral sleep disorders center. Modified Mallampati class and other simple patient characteristics (age, gender, body mass index) were compared to apnea-hypopnea index (AHI). The sensitivity, specificity, and the positive and negative likelihood ratios (LR+ and LR-) were calculated for Mallampati class IV to detect an AHI > 30 (rule in severe OSA) and Mallampati class I to detect an AHI < 5 (rule out OSA). RESULTS: A total of 953 consecutive patients (619 male) undergoing diagnostic polysomnography were included. The age of the cohort was 50.0 ± 6.4 years, with a BMI of 33.8 ± 8.6 kg/m² and AHI of 26.1 ± 25.1 /h (95% CI 1.4-78.8). Mallampati class was significantly associated with AHI (r = 0.13, p < 0.001), but there were no differences in AHI between Mallampati classes. A Mallampati class IV had a sensitivity of 40%, specificity of 67%, LR+ of 1.21, and LR- of 0.90 for an AHI > 30. A Mallampati class I was only 13% sensitive but 92% specific for an AHI < 5, with LR+ of 1.63 and LR- 0.90. CONCLUSIONS: Mallampati class is associated with AHI but does not significantly modify likelihood of severe OSA or absence of OSA. As such, it is of limited use to "rule in" severe OSA or "rule out OSA" in the sleep clinic population.

Avaliação da função ventricular esquerda pela sequência de ressonância magnética sem apneia e com múltiplas excitações / Left ventricular function assessment by free-breathing magnetic resonance sequence with multiple excitations

OBJETIVO: Avaliar a eficácia da sequência de ressonância magnética com três excitações, para obtenção de volumes e massas ventriculares, em indivíduos com respiração livre, sem apneia. MATERIAIS E MÉTODOS: Em 32 voluntários sadios, foram comparados os volumes e massas do ventrículo esquerdo, obtidos por meio de duas sequências de ressonância magnética em modo cine. A primeira, tradicionalmente utilizada e considerada padrão, em apneia e com excitação única, e a segunda, em respiração livre e com três excitações. Três leitores, com diferentes níveis de experiência, testaram a concordância e a reprodutibilidade. Para a análise estatística foram utilizados o coeficiente de correlação intraclasse, o teste t-pareado, os gráficos de Bland-Altman e o teste do sinal. RESULTADOS: Para os dois observadores mais experientes, os coeficientes de correlação intraclasse foram superiores a 0,913, assim como os níveis descritivos do teste t-pareado acima de 0,05, os gráficos de Bland-Altman com as diferenças distribuídas aleatoriamente em torno do zero e o teste do sinal com seu nível descritivo superior a 0,05. CONCLUSÃO: A sequência testada apresenta ótima concordância e reprodutibilidade em relação à sequência padrão, podendo ser aplicada em indivíduos com limitações respiratórias.

OBJECTIVE: To evaluate the efficacy of free-breathing magnetic resonance sequence with three excitations in the determination of ventricular volumes and masses in individuals without breathholding. MATERIALS AND METHODS: Left ventricular volumes and masses determined in 32 healthy volunteers through two cine magnetic resonance imaging sequences were compared: the first sequence, traditionally utilized and considered as a standard, performed under apnea, with a single excitation, and the second one, with free-breathing and three excitations. Three observers at different levels of experience evaluated the agreement and reproducibility. Intraclass correlation coefficient, paired t-test, Bland-Altman plots and sign test were utilized for statistical analysis. RESULTS: According to the two most experienced observers, intraclass correlation coefficients were > 0.913, the paired t-test demonstrated P values > 0.05, Bland-Altman plots had differences randomly distributed around zero and the sign test descriptive levels were > 0.05. CONCLUSION: The sequence evaluated presents an excellent agreement and reproducibility as compared with the standard sequence, and can be utilized in patients with respiratory limitations.