Staff member

In this study, we propose a model-based tool for the detection of obstructive apnea episodes by using ECG features from a single lead channel. Several sequences of recurrent apnea were provoked in separate 15-min periods in anesthetized rats during an experimental model of obstructive sleep apnea (OSA). Morphology-based ECG markers and the beat-to-beat interval (RR) were assessed in each sequence. These markers were used to train dynamic Bayesian networks (DBN) with different orders and feature combinations to find a good tradeoff between network complexity and apnea-detection performance. By using a filtering approach, the resulting DBNs were used to infer the apnea probability signal for subsequent episodes in the same rat. These signals were then processed using by 15-s epochs to determine whether epochs were classified as apneic or nonapneic. Our results showed that fifth-order models provided suitable RMSE values, since higher order models become significantly more complex and present worse generalization. A global threshold of 0.2 gave the best overall performance for all combinations tested, with Acc = 81.3%, Se = 69.8% and Sp = 81.5%, using only two parameters including the RR and Ds (R-wave downslope) markers. We concluded that multivariate models using DBNs represent a powerful tool for detecting obstructive apnea episodes in short segments, which may also serve to estimate the number of total events in a given time period.

JTD Keywords: chronic respiratory diseases, obstructive sleep apnea, probabilistic models, Obstructive sleep apnea,probabilistic models,respiratory events,chronic respiratory disease, Respiratory events, Sleep-apnea syndrome,automated detection,oxygen-saturation,classification,recordings,signal

Identification of asymptomatic patients at higher risk for suffering cardiac events remains controversial and challenging in Brugada syndrome (BS). In this work, we proposed an ECG-based classifier to predict BS-related symptoms, by merging the most predictive electrophysiological features derived from the ventricular depolarization and repolarization periods, along with autonomic-related markers. The initial feature space included local and dynamic ECG markers, assessed during a physical exercise test performed in 110 BS patients (25 symptomatic). Morphological, temporal and spatial properties quantifying the ECG dynamic response to exercise and recovery were considered. Our model was obtained by proposing a two-stage feature selection process that combined a resampled-based regularization approach with a wrapper model assessment for balancing, simplicity and performance. For the classification step, an ensemble was constructed by several logistic regression base classifiers, whose outputs were fused using a performance-based weighted average. The most relevant predictors corresponded to the repolarization interval, followed by two autonomic markers and two other makers of depolarization dynamics. Our classifier allowed for the identification of novel symptom-related markers from autonomic and dynamic ECG responses during exercise testing, suggesting the need for multifactorial risk stratification approaches in order to predict future cardiac events in asymptomatic BS patients.

JTD Keywords: brugada syndrome, depolarization disorders, ensemble classifier, heart-rate recovery, Acute myocardial-ischemia, Autonomics, Brugada syndrome, Brugadum syndrome, Cardiac death, Depolarization, Depolarization disorder, Depolarization disorders, Dynamic ecg, Electrocardiography, Electrophysiology, Ensemble classifier, Ensemble-classifier, Events, Exercise, Forecasting, Heart, Heart-rate, Heart-rate recovery, Prognosis, Qrs, Quantification, Recovery, Repolarization, Sudden cardiac death

Chronic obstructive pulmonary disease (COPD) requires a multifactorial assessment, evaluating the airflow limitation and symptoms of the patients. The 6-min walk test (6MWT) is commonly used to evaluate the functional exercise capacity in these patients. This study aims to propose a novel predictive model of the major 6MWT outcomes for COPD assessment, without physical performance measurements.Cardiopulmonary and clinical parameters were obtained from fifty COPD patients. These parameters were used as inputs of a Bayesian network (BN), which integrated three multivariate models including the 6-min walking distance (6MWD), the maximum HR (HRmax) after the walking, and the HR decay 3 min after (HRR3). The use of BN allows the assessment of the patients' status by predicting the 6MWT outcomes, but also inferring disease severity parameters based on actual patient's 6MWT outcomes.Firstly, the correlation obtained between the estimated and actual 6MWT measures was strong (R = 0.84, MAPE = 8.10% for HRmax) and moderate (R = 0.58, MAPE = 15.43% for 6MWD and R = 0.58, MAPE = 32.49% for HRR3), improving the classical methods to estimate 6MWD. Secondly, the classification of disease severity showed an accuracy of 78.3% using three severity groups, which increased up to 84.4% for two defined severity groups.We propose a powerful two-way assessment tool for COPD patients, capable of predicting 6MWT outcomes without the need for an actual walking exercise. This model-based tool opens the way to implement a continuous monitoring system for COPD patients at home and to provide more personalized care.Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.

JTD Keywords: 6mwt, bayesian networks, copd, distance, exercise capacity, physical capacity, reference equations, severity, survival, wearables, 6mwt, Heart-rate recovery, Wearables

In this study, we proposed an automatic detector for obstructive apnea episodes using only ECG-based time-series from a single-ECG channel. Several obstructive apnea episodes were provoked for different separated sequences of 15 minutes in anesthetized Sprague-Dawley rats. In this recurrent obstructive sleep apnea (OSA) model, each episode lasted 15s, while the number of total events per sequence was randomly selected. The beat-to-beat interval ( RR) and the R-wave amplitude ( Ra) time-series were extracted and processed for each sequence, and used to train Dynamic Bayesian Networks with different lags. An optimal trade-off between the lag ( L) and RMSE values was considered to select the best model to be used when detecting apnea episodes. The selected models were then used to estimate the occurrence probability of apnea episodes, p(At), by using a filtering approach. Finally, the time-series of the estimated probabilities were post-processed using non-overlapped 15-s epochs, to determine whether they are classified as apneic or non-apneic segments. Results showed that those lagged models with orders greater than 5, presented suitable RMSE values and become more sensitive as the order increased. A detection threshold of 0.2 seems to provide the best apnea detection performance overall, with Acc=0.81, Se=0.83 and Sp=0.79, using two ECG parameters and L=10. Clinical relevance- Dynamic Bayesian Networks represent a powerful tool to develop personalized models for apnea detection and diagnosis in OSA patients.

JTD

Patients suffering from obstructive sleep apnea (OSA) usually present an increased sympathetic activity caused by the intermittent hypoxia effect on autonomic control. This study evaluated the relationship between sleep stages and the apnea duration, frequency, and type, as well as their impact on HRV markers in different groups of disease severity. The hypnogram and R-R interval signals were extracted in 81 OSA patients from night polysomnographic (PSG) recordings. The apnea-hypopnea index (AHI) defined patient classification as mild-moderate (AHI< 30, n 44) or severe (AHI>30, n 37). The normalized power in VLH, LF, and HF bands of RR series were estimated by a time-frequency approach and averaged in 1-min epochs of normal and apnea segments. The autonomic response and the impact of sleep stages were assessed in both segments to compare patient groups. Deeper sleep stages (particularly S2) concentrated the shorter and mild apnea episodes (from 10 to 40 s) compared to light (SWS) and REM sleep. Longer episodes (>50 s) although less frequent, were of similar incidence in all stages. This pattern was more pronounced for the group of severe patients. Moreover, during apnea segments, LF nu was higher (p 0.044) for the severe group, since V LF nu and HF nu presented the greatest changes when compared to normal segments. The non-REM sleep seems to better differentiate OSA patients groups, particularly through VLF nu and HF nu (p<0.001). A significant difference in both sympathetic and vagal modulation between REM and non-REM sleep was only found within the severe group. These results confirm the importance of considering sleep stages for HRV analysis to further assess OSA disease severity, beyond the traditional and clinically limited AHI values.Clinical relevance - Accounting for sleep stages during HRV analysis could better assess disease severity in OSA patients. © 2021 IEEE.

JTD Keywords: blood-pressure, genomic consequences, intermittent hypoxia, rapid-eye-movement, sympathetic activity, Heart rate, Heart-rate-variability, Human, Humans, Polysomnography, Rem sleep, Sleep apnea, obstructive, Sleep disordered breathing, Sleep stage, Sleep stages, Sleep, rem

CCBY Intermittent hypoxia (IH) produces autonomic dysfunction that promotes the development of arrhythmia and hypertension in patients with obstructive sleep apnea (OSA). This paper investigated different heart rate variability (HRV) indices in the context of IH using a rat model for OSA. Linear and non-linear HRV parameters were assessed from ultra-short (15-s segments) and short-term (5 min) analyses of heartbeat time-series. Transient changes observed from pre-apnea segments to hypoxia episodes were evaluated, besides the relative and global impact of IH, as a function of its severity. Results showed an overall increase in ultra-short HRV markers as immediate response to hypoxia: standard deviation of normal RR intervals, SDNN=1.2 ms (IQR: 1.1-2.1) vs 1.4 ms (IQR: 1.2-2.2), p=0.015; root mean square of the successive differences, RMSSD=1.7 ms (IQR: 1.5-2.2) vs 1.9 ms (IQR: 1.6-2.4), p=0.031. The power in the very low frequency (VLF) band also showed a significant increase: 0.09 ms2 (IQR: 0.05-0.20) vs 0.16 ms2 (IQR: 0.12-0.23), p=0.016, probably associated with the potentiation of the carotid body chemo-sensory response to hypoxia. Moreover, a clear link between severity of IH and short-term HRV measures was found in VLF and LF power, besides their progressive increase seen throughout the experiment after each apnea sequence. However, only those markers quantifying fragmentation levels in RR series were significantly affected when the experiment ended, as compared to baseline measures: percentage of inflection points, PIP=49% (IQR: 45-51) vs 53% (IQR: 47-53), p=0.031; percentage of short (≥3 RR intervals) accelerated/decelerated segments, PSS=75% (IQR: 51-81) vs 87% (IQR: 51-90), p=0.046. These findings suggest a significant deterioration of cardiac rhythm with a more erratic behavior beyond the normal sinus arrhythmia, that may lead to a future cardiac condition.

JTD Keywords: artificial intelligence, atmospheric modeling, electrocardiography, heart rate variability, hypoxia rat model, intermittent hypoxia, obstructive apneas, protocols, radio access technologies, Artificial intelligence, Atmospheric modeling, Electrocardiography, Heart rate variability, Hypoxia rat model, Intermittent hypoxia, Obstructive apneas, Protocols, Radio access technologies, Rats

In this work, we evaluated a non-linear approach to estimate morphological variations in ECG depolarization, in the context of intermittent hypoxia (IH). Obstructive apnea sequences were provoked for 15 minutes in anesthetized Sprague-Dawley rats, alternating with equal periods of normal breathing, in a recurrent obstructive sleep apnea (OSA) model. Each apnea episode lasted 15 s, while the frequency used for each sequence was randomly selected. Average heartbeats obtained before the start and at the end of each episode, were delineated to extract only the QRS wave. Then, the segmented QRS waves were non-linearly aligned using the dynamic time warping (DWT) algorithm. Morphological QRS changes in both the amplitude and temporal domains were estimated from this alignment procedure. The hypoxic and basal segments were analyzed using ECG (lead I) recordings acquired during the experiment. To assess the effects of IH over time, the changes relative to the basal QRS wave were determined, in the intervals prior to each successive events until the end of the experiment. The results showed a progressive increase in the amplitude and time-domain morphological markers of the QRS wave along the experiment, which were strongly correlated with the changes in traditional QRS markers (r ≈ 0.9). Significant changes were found between pre-apnea and hypoxic measures only for the time-domain analysis (p<0.001), probably due to the short duration of the simulated apnea episodes.Clinical relevance Increased variability in ECG depolarization morphology during recurrent hypoxic episodes would be closely related to the expression of cardiovascular dysfunction in OSA patients.

JTD Keywords: Electrocardiography, Rats, Heart rate variability, Sleep apnea, Protocols, Heuristic algorithms

A novel ECG-derived respiration (EDR) approach is presented to efficiently estimate the respiratory rate. It combines spatial rotations and magnitude variations of the heart's electrical vector due to respiration. Orthogonal leads X, Y and Z from 10 volunteers were analyzed during a tilt table test. The largest vector magnitude (VM) within each QRS loop was assessed, and its 3D coordinates were converted into unit quaternion qb. Angular distances between these quaternions and the axes of the reference coordinate system, θ x , θ y and θ z , were then computed as EDR signals to track their relative variations caused by respiration. The respiratory rate was estimated on the spectrum of individual EDR signals obtained from the angular distances and VM time-series, but also on EDR signals obtained by principal component analysis (PCA). Relative errors (eR) to the reference respiratory signal exhibited relatively low values. The combination of EDR signals' spectrum {θ X ,θ Y, θ Z , VM} (eR=0.63±4.15%) and individual signals derived from θ X (e R =0.46±8.22%) and PCA (eR=0.36±6.58%) achieved the overall best results. The proposed method represents a computationally efficient alternative to other EDR approaches, but its robustness should be further investigated. The method could be enhanced if combined with other features tracking morphological changes induced by respiration.

JTD Keywords: Heart, Three-dimensional displays, Quaternions, Robustness, Computational efficiency, Cardiology, Principal component analysis

Chronic obstructive pulmonary disease (COPD) patients exhibit impaired autonomic control which can be assessed by heart rate variability analysis. The study aims to evaluate the cardiac autonomic responses of COPD patients after completing a conventional six-minute walk test (6MWT). Fifty COPD patients were included in the study, for which an ECG signal (lead II) was acquired by a wearable device, before, during, and after the test. We used the heart rate (HR) time-series to assess the heart rate dynamic during recovery. The heart rate recovery (HRR) marker was evaluated every 5 s after the 6MWT and showed different dynamic trends among severity groups. We compared the HRR among patient groups classified according to the GOLD standard. Significantly larger normalized HRR values (nHRR) were found in mild COPD patients (n=23, GOLD={1,2}; nHRR 1 =14.B±7.5 %, nHRR 2 =18.6±8.1 %) compared to those with more disease severity (n=23, GOLD={3,4}; nHRR 1 =9.3±5.8 %, p=0.002; and nHRR 2 = 13.7±6.7%, p=0.041). The largest differences were observed around the first 30 s of the recovery phase (nHRR=10.8±6.6 % vs. nHRR=5.6±4 % p=0.001). Our results showed a slower recovery for the severest patients, suggesting that cardiac parameters like the ones we propose here, may provide valuable information for a better characterization of COPD severity.

JTD Keywords: Pulmonary diseases, Wearable computers, Electrocardiography, Market research, Cardiology, Heart rate variability

This paper proposes the integration and analysis of a closed-loop model of the baroreflex and cardiovascular systems, focused on a time-varying estimation of the autonomic modulation of heart rate in Brugada syndrome (BS), during exercise and subsequent recovery. Patient-specific models of 44 BS patients at different levels of risk (symptomatic and asymptomatic) were identified through a recursive evolutionary algorithm. After parameter identification, a close match between experimental and simulated signals (mean error = 0.81%) was observed. The model-based estimation of vagal and sympathetic contributions were consistent with physiological knowledge, enabling to observe the expected autonomic changes induced by exercise testing. In particular, symptomatic patients presented a significantly higher parasympathetic activity during exercise, and an autonomic imbalance was observed in these patients at peak effort and during post-exercise recovery. A higher vagal modulation during exercise, as well as an increasing parasympathetic activity at peak effort and a decreasing vagal contribution during post-exercise recovery could be related with symptoms and, thus, with a worse prognosis in BS. This work proposes the first evaluation of the sympathetic and parasympathetic responses to exercise testing in patients suffering from BS, through the recursive identification of computational models; highlighting important trends of clinical relevance that provide new insights into the underlying autonomic mechanisms regulating the cardiovascular system in BS. The joint analysis of the extracted autonomic parameters and classic electrophysiological markers could improve BS risk stratification.

JTD Keywords: Autonomic nervous system, Brugada syndrome, Computational model, Recursive identification

In this paper, a non-linear HRV analysis was performed to assess fragmentation signatures observed in heartbeat time series after intermittent hypoxia (IH). Three markers quantifying short-term fragmentation levels, PIP, IALS and PSS, were evaluated on R-R interval series obtained in a rat model of recurrent apnea. Through airway obstructions, apnea episodes were periodically simulated in six anesthetized Sprague-Dawley rats. The number of apnea events per hour (AHI index) was varied during the first half of the experiment while apnea episodes lasted 15 s. For the second part, apnea episodes lasted 5, 10 or 15 s, but the AHI index was fixed. Recurrent apnea was repeated for 15-min time intervals in all cases, alternating with basal periods of the same duration. The fragmentation markers were evaluated in segments of 5 minutes, selected at the beginning and end of the experiment. The impact of the heart and breathing rates (HR and BR, respectively) on the parameter estimates was also investigated. The results obtained show a significant increase (from 5 to 10%, p <; 0.05) in fragmentation measures of heartbeat time series after IH, indicating a clear deterioration of the initial conditions. Moreover, there was a strong linear relationship (r > 0.9) between these markers and BR, as well as with the ratio given by HR/BR. Although fragmentation may be impacted by IH, we found that it is highly dependent on HR and BR values and thus, they should be considered during its calculation or used to normalize the fragmentation estimates.

JTD Keywords: Rats, Time series analysis, Radio access technologies, Protocols, Heart beat