Search

The ideal moment to withdraw respiratory supply of patients under Mechanical Ventilation at Intensive Care Units (ICU), is not easy to be determined for clinicians. Although the Spontaneous Breathing Trial (SBT) provides a measure of the patients’ readiness, there is still around 15–20% of predictive failure rate. This work is a proof of concept focused on adding new value to the prediction of the weaning outcome. Heart Rate Variability (HRV) and Cardiopulmonary Coupling (CPC) methods are evaluated as new complementary estimates to assess weaning readiness. The CPC is related to how the mechanisms regulating respiration and cardiac pumping are working simultaneously, and it is defined from HRV in combination with respiratory information. Three different techniques are used to estimate the CPC, including Time-Frequency Coherence, Dynamic Mutual Information and Orthogonal Subspace Projections. The cohort study includes 22 patients in pressure support ventilation, ready to undergo the SBT, analysed in the 24 h previous to the SBT. Of these, 13 had a successful weaning and 9 failed the SBT or needed reintubation –being both considered as failed weaning. Results illustrate that traditional variables such as heart rate, respiratory frequency, and the parameters derived from HRV do not differ in patients with successful or failed weaning. Results revealed that HRV parameters can vary considerably depending on the time at which they are measured. This fact could be attributed to circadian rhythms, having a strong influence on HRV values. On the contrary, significant statistical differences are found in the proposed CPC parameters when comparing the values of the two groups, and throughout the whole recordings. In addition, differences are greater at night, probably because patients with failed weaning might be experiencing more respiratory episodes, e.g. apneas during the night, which is directly related to a reduced respiratory sinus arrhythmia. Therefore, results sugge, Circuits and Systems

Feature selection techniques are very useful approaches for dimensionality reduction in data analysis. They provide interpretable results by reducing the dimensions of the data to a subset of the original set of features. When the data lack annotations, unsupervised feature selectors are required for their analysis. Several algorithms for this aim exist in the literature, but despite their large applicability, they can be very inaccessible or cumbersome to use, mainly due to the need for tuning non-intuitive parameters and the high computational demands. In this work, a publicly available ready-to-use unsupervised feature selector is proposed, with comparable results to the state-of-the-art at a much lower computational cost. The suggested approach belongs to the methods known as spectral feature selectors. These methods generally consist of two stages: manifold learning and subset selection. In the first stage, the underlying structures in the high-dimensional data are extracted, while in the second stage a subset of the features is selected to replicate these structures. This paper suggests two contributions to this field, related to each of the stages involved. In the manifold learning stage, the effect of non-linearities in the data is explored, making use of a radial basis function (RBF) kernel, for which an alternative solution for the estimation of the kernel parameter is presented for cases with high-dimensional data. Additionally, the use of a backwards greedy approach based on the least-squares utility metric for the subset selection stage is proposed. The combination of these new ingredients results in the utility metric for unsupervised feature selection U2FS algorithm. The proposed U2FS algorithm succeeds in selecting the correct features in a simulation environment. In addition, the performance of the method on benchmark datasets is comparable to the state-of-the-art, while requiring less computational time. Moreover, unlike the state-of-the-art, U2, Circuits and Systems

Objective: Respiratory sinus arrhythmia (RSA) refers to heart rate oscillations synchronous with respiration, and it is one of the major representations of cardiorespiratory coupling. Its strength has been suggested as a biomarker to monitor different conditions, and diseases. Some approaches have been proposed to quantify the RSA, but it is unclear which one performs best in specific scenarios. The main objective of this study is to compare seven state-of-the-art methods for RSA quantification using data generated with a model proposed to simulate, and control the RSA. These methods are also compared, and evaluated on a real-life application, for their ability to capture changes in cardiorespiratory coupling during sleep. Methods: A simulation model is used to create a dataset of heart rate variability, and respiratory signals with controlled RSA, which is used to compare the RSA estimation approaches. To compare the methods objectively in real-life applications, regression models trained on the simulated data are used to map the estimates to the same measurement scale. Results, and conclusion: RSA estimates based on cross entropy, time-frequency coherence, and subspace projections showed the best performance on simulated data. In addition, these estimates captured the expected trends in the changes in cardiorespiratory coupling during sleep similarly. Significance: An objective comparison of methods for RSA quantification is presented to guide future analyses. Also, the proposed simulation model can be used to compare existing, and newly proposed RSA estimates. It is freely accessible online., Circuits and Systems

Early detection of exposure to a toxic chemical, e.g., in a military context, can be life-saving. We propose to use machine learning techniques and multiple continuously measured physiological signals to detect exposure, and to identify the chemical agent. Such detection and identification could be used to alert individuals to take appropriate medical counter measures in time. As a first step, we evaluated whether exposure to an opioid (fentanyl) or a nerve agent (VX) could be detected in freely moving guinea pigs using features from respiration, electrocardiography (ECG) and electroencephalography (EEG), where machine learning models were trained and tested on different sets (across subject classification). Results showed this to be possible with close to perfect accuracy, where respiratory features were most relevant. Exposure detection accuracy rose steeply to over 95% correct during the first five minutes after exposure. Additional models were trained to correctly classify an exposed state as being induced either by fentanyl or VX. This was possible with an accuracy of almost 95%, where EEG features proved to be most relevant. Exposure detection models that were trained on subsets of animals generalized to subsets of animals that were exposed to other dosages of different chemicals. While future work is required to validate the principle in other species and to assess the robustness of the approach under different, realistic circumstances, our results indicate that utilizing different continuously measured physiological signals for early detection and identification of toxic agents is promising., Signal Processing Systems

Cardiovascular diseases (CVD) are often characterized by their multifactorial complexity. This makes remote monitoring and ambulatory cardiac rehabilitation (CR) therapy challenging. Current wearable multimodal devices enable remote monitoring. Machine learning (ML) and artificial intelligence (AI) can help in tackling multifaceted datasets. However, for clinical acceptance, easy interpretability of the AI models is crucial. The goal of the present study was to investigate whether a multi-parameter sensor could be used during a standardized activity test to interpret functional capacity in the longitudinal follow-up of CR patients. A total of 129 patients were followed for 3 months during CR using 6-min walking tests (6MWT) equipped with a wearable ECG and accelerometer device. Functional capacity was assessed based on 6MWT distance (6MWD). Linear and nonlinear interpretable models were explored to predict 6MWD. The t-distributed stochastic neighboring embedding (t-SNE) technique was exploited to embed and visualize high dimensional data. The performance of support vector machine (SVM) models, combining different features and using different kernel types, to predict functional capacity was evaluated. The SVM model, using chronotropic response and effort as input features, showed a mean absolute error of 42.8 m (±36.8 m). The 3D-maps derived using the t-SNE technique visualized the relationship between sensor-derived biomarkers and functional capacity, which enables tracking of the evolution of patients throughout the CR program. The current study showed that wearable monitoring combined with interpretable ML can objectively track clinical progression in a CR population. These results pave the road towards ambulatory CR.

A real-life validation of a system for simultaneous acquisition of capacitively-coupled ECG (ccECG) and capacitively-coupled bioimpedance (ccBioz) is presented. The heart rate (HR) and respiration rate (RR) estimation performance was evaluated using polysomnography (PSG) signals as ground-truth, in recordings from 28 patients with suspected obstructive sleep apnea (OSA). A ccECG beat detection sensitivity of 98.4% and an R-R interval mean absolute error (MAE) of 17.1 ms were achieved when applying quality-based algorithms. RR MAE values of 3.48 and 6.37 breaths per minute were also achieved when using two different RR extraction methods. High similarity between unobtrusive signals and PSG ground-truth was observed, with a correlation between ccECG and psgECG of 91.5% and a correlation between ccBioz and PSG thoracic belt (TB) of 89.5%. Even in episodes containing OSA events, the characteristic respiration behavior of TB signals was also observed in the ccBioz signals. This shows the potential of ccECG and ccBioz for use in long-term monitoring without adding discomfort to the patient or user. Sleep-related applications as well as more generic cardiorespiratory monitoring in (patient) beds are obvious applications, but also other daily life monitoring can be done using a similar approach (e.g. in seats)., Circuits and Systems

Sleep apnea is a common sleep disorder, whose diagnosis can strongly benefit from home-based screening. As the total sleep time is essential to assess the sleep apnea severity, a sleep-wake classifier was developed based on heart rate and respiration. These two signals were selected as they can be measured using unobtrusive sensors. A 1D convolutional neural network (CNN) was designed to classify 30s epochs of tachograms and respiratory inductance plethysmography (RIP) signals. The input based on beat-to-beat variability allows the use of different sensor types. A dataset of 56 patients with an apnea-hypopnea index (AHI) below 10 was used to train and validate the network. This CNN was applied to an independent test set of ECG and RIP signals of 25 subjects. Of these, 8 subjects were simultaneously monitored using an unobtrusive capacitive-coupled ECG (ccECG) sensor integrated in a mattress. Artefact removal and data correction was performed on this acquired data. The performance on the independent dataset of ECG and RIP is comparable to state-of-the-art, with ? = 0.48. However, application on the ccECG data resulted in a drop in performance, with ? = 0.30. This was caused by a low amount of remaining wake epochs after data cleaning. Importantly, the network classified 30s segments of sleep apnea patients, without relying on past or future information for feature extraction., Circuits and Systems

Electrical storm (ES) in ICD patients, defined as 3 or more appropriate ICD interventions within a time span of 24 hours, is a medical emergency associated with adverse outcome. However, it is debated if ES is only a marker of progressive near end-stage cardiac disease or an ar-rhythmogenic entity on its own. Better understanding and prediction are necessary to manage the burden of ES. The goal of this study is to explore the relation between the presence of fragmented QRS (fQRS) and the manifestation of electrical storm in patients with an ICD for ischemic heart disease. A balanced dataset of 100 patients was considered for this study, where 50 patients with ischemic heart disease and dilated cardiomyopathy present ES. 12-lead ECG signals were analyzed from 3 years before until the moment of ES, divided in 4 visits. The fQRS level in the 12-lead ECG data recorded in each visit was automatically quantified with a score between 0 and 1 for each lead. A Friedman test between the first and last visit for each of the groups showed a significant increase in the average level of fragmentation for the patients presenting ES, absent in the control group. This suggests that there is a trend towards deterioration in fQRS for patients manifesting ES with an ICD for ischemic heart disease., Circuits and Systems

The gold standard for the assessment of cardiac mass is cardiac magnetic resonance imaging (CMR). However, it is costly and requires specific expertise. Electrocardiographic (ECG) criteria could provide a low-cost solution, but have shown to be poorly correlated with LVM in athletes. We hypothesize that this poor correlation could be overcome by taking into account body measurements (length, weight) and composition (fat mass, lean mass and bone mass). The objective was to assess whether adding demographic (Demo) and/or Dual-energy X-ray absorptiometry (DXA) features could improve an ECG-based regression model for the estimation of LVM in athletes. 107 young competitive endurance athletes (19±2 years; 35 female) underwent a 12-lead ECG, a DXA scan and CMRI. We constructed four feature subsets: ECG, ECG+Demo, ECG+DXA and All. The best combination of features from each set, was used to build a Support Vector Machines regression model with 5 features. The ECG model performed significantly worse than all other models (R2 = 0.28 (0.17), RMSE = 34.33 (5.63) g). The best performing model was constructed with the entire feature set ((R2 = 0.67 (0.14), RMSE = 23.08 (4.42) g). These results suggest that an ECG based regression model for LVM prediction can be improved by adding demographic and/or body composition features., Circuits and Systems

Respiratory sinus arrhythmia (RSA) is one of the forms of cardiorespiratory coupling. It has been suggested as a potential biomarker for diverse illnesses and conditions. In general, methods for non-invasive quantification of the RSA combine information from heart rate variability (HRV) and respiratory signals. Abnormal beats, which commonly occur in different populations, alter the reliability of the HRV and thus hinder the quantification of the RSA. To overcome this problem, several methods for detection and correction of irregular beats have been reported in literature. However, the effect of each of these methods on the quantification of the RSA is not well understood yet. For this reason, an approach that avoids this step might be useful. This paper presents an alternative based on robust regression models. For comparison purposes, an algorithm to detect and correct for irregular beats, in combination with a state-of-the-art RSA estimate, are tested. A similar performance is achieved with both approaches. These results show that the proposed robust methodology is able to capture the strength of the RSA, even when irregular beats are present, avoiding the irregularities correction step., Circuits and Systems

Cardiac rehabilitation (CR) is a highly recommended secondary prevention measure for patients with diagnosed cardiovascular disease. Unfortunately, participation rates are low due to enrollment and adherence issues. As such, new CR delivery strategies are of interest, as to improve overall CR delivery. The goal of the study was to obtain a better understanding of the short-term progression of functional capacity throughout multidisciplinary CR, measured as the change in walking distance between baseline six-minute walking test (6MWT) and four consecutive follow-up tests. One-hundred-and-twenty-nine patients diagnosed with cardiovascular disease participated in the study, of which 89 patients who completed the whole study protocol were included in the statistical analysis. A one-way repeated measures ANOVA was conducted to determine whether there was a significant change in mean 6MWT distance (6MWD) throughout CR. A three-way-mixed ANOVA was performed to determine the influence of categorical variables on the progression in 6MWD between groups. Significant differences in mean 6MWD between consecutive measurements were observed. Two subgroups were identified based on the change in distance between baseline and end-of-study. Patients who increased most showed a linear progression. In the other group progression leveled off halfway through rehabilitation. Moreover, the improvement during the initial phase of CR seemed to be indicative for overall progression. The current study adds to the understanding of the short-term progression in exercise capacity of patients diagnosed with cardiovascular disease throughout a CR program. The results are not only of interest for CR in general, but could be particularly relevant in the setting of home-based CR., Microelectronics, Circuits and Systems

Cardiovascular diseases (CVD) are often characterized by their multifactorial complexity. This makes remote monitoring and ambulatory cardiac rehabilitation (CR) therapy challenging. Current wearable multimodal devices enable remote monitoring. Machine learning (ML) and artificial intelligence (AI) can help in tackling multifaceted datasets. However, for clinical acceptance, easy interpretability of the AI models is crucial. The goal of the present study was to investigate whether a multi-parameter sensor could be used during a standardized activity test to interpret functional capacity in the longitudinal follow-up of CR patients. A total of 129 patients were followed for 3 months during CR using 6-min walking tests (6MWT) equipped with a wearable ECG and accelerometer device. Functional capacity was assessed based on 6MWT distance (6MWD). Linear and nonlinear interpretable models were explored to predict 6MWD. The t-distributed stochastic neighboring embedding (t-SNE) technique was exploited to embed and visualize high dimensional data. The performance of support vector machine (SVM) models, combining different features and using different kernel types, to predict functional capacity was evaluated. The SVM model, using chronotropic response and effort as input features, showed a mean absolute error of 42.8 m (±36.8 m). The 3D-maps derived using the t-SNE technique visualized the relationship between sensor-derived biomarkers and functional capacity, which enables tracking of the evolution of patients throughout the CR program. The current study showed that wearable monitoring combined with interpretable ML can objectively track clinical progression in a CR population. These results pave the road towards ambulatory CR., Circuits and Systems

Background: Cardiac rehabilitation (CR) is known for its beneficial effects on functional capacity and is a key component within current cardiovascular disease management strategies. In addition, a larger increase in functional capacity is accompanied by better clinical outcomes. However, not all patients respond in a similar way to CR. Therefore, a patient-tailored approach to CR could open up the possibility to achieve an optimal increase in functional capacity in every patient. Before treatment can be optimized, the differences in response of patients in terms of cardiac adaptation to exercise should first be understood. In addition, digital biomarkers to steer CR need to be identified. Objective: The aim of the study was to investigate the difference in cardiac response between patients characterized by a clear improvement in functional capacity and patients showing only a minor improvement following CR therapy. Methods: A total of 129 patients in CR performed a 6-minute walking test (6MWT) at baseline and during four consecutive short-term follow-up tests while being equipped with a wearable electrocardiogram (ECG) device. The 6MWTs were used to evaluate functional capacity. Patients were divided into high- and low-response groups, based on the improvement in functional capacity during the CR program. Commonly used heart rate parameters and cardiac digital biomarkers representative of the heart rate behavior during the 6MWT and their evolution over time were investigated. Results: All participating patients improved in functional capacity throughout the CR program (P<.001). The heart rate parameters, which are commonly used in practice, evolved differently for both groups throughout CR. The peak heart rate (HR peak) from patients in the high-response group increased significantly throughout CR, while no change was observed in the low-response group (F 4,92=8.321, P<.001). Similar results were obtained for the recovery heart rate (, Circuits and Systems

Cardiorespiratory monitoring is crucial for the diagnosis and management of multiple conditions such as stress and sleep disorders. Therefore, the development of ambulatory systems providing continuous, comfortable, and inexpensive means for monitoring represents an important research topic. Several techniques have been proposed in the literature to derive respiratory information from the ECG signal. Ten methods to compute single-lead ECG-derived respiration (EDR) were compared under multiple conditions, including different recording systems, baseline wander, normal and abnormal breathing patterns, changes in breathing rate, noise, and artifacts. Respiratory rates, wave morphology, and cardiorespiratory information were derived from the ECG and compared to those extracted from a reference respiratory signal. Three datasets were considered for analysis, involving a total 59 482 one-min, single-lead ECG segments recorded from 156 subjects. The results indicate that the methods based on QRS slopes outperform the other methods. This result is particularly interesting since simplicity is crucial for the development of ECG-based ambulatory systems., Circuits and Systems

Objective: Automated seizure detection is a key aspect of wearable seizure warning systems. As a result, the quality of life of refractory epilepsy patients could be improved. Most state-of-the-art algorithms for heart rate-based seizure detection use a so-called patient-independent approach, which do not take into account patient-specific data during algorithm training. Although such systems are easy to use in practice, they lead to many false detections as the ictal heart rate changes are patient-dependent. In practice, only a limited amount of accurately annotated patient data is typically available, which makes it difficult to create fully patient-specific algorithms. Methods: In this context, this study proposes for the first time a new transfer learning approach that allows to personalize heart rate-based seizure detection by using only a couple of days of data per patient. The algorithm was evaluated on 2,172 h of single-lead ECG data from 24 temporal lobe epilepsy patients including 227 focal impaired awareness seizures. Results: The proposed personalized approach resulted in an overall sensitivity of 71% with 1.9 false detections per hour. This is an average decrease in false detection rate of 37% compared to the reference patient-independent algorithm using only a limited amount of personal seizure data. The proposed transfer learning approach adapts faster and more robustly to patient-specific characteristics than other alternatives for personalization in the literature. Conclusion: The proposed method allows an easy implementable solution to personalize heart rate-based seizure detection, which can improve the quality of life of refractory epilepsy patients when used as part of a multimodal seizure detection system., Circuits and Systems

Tetralogy of Fallot (ToF) is a congenital structural heart disease. While early diagnosis and corrective surgery allow most patients to live normal lives, some patients slowly deteriorate. The current inability to quantify the deterioration and predict these events prompts a data driven approach. Laplacian Eigenmaps (LEs) are a dimensionality reduction technique that can be used to project multi-lead ECGs onto a lower dimensional space. This pilot study aims to evaluate the ability of LEs to characterize deterioration of ToF patients. A general LE model is constructed, based on the 12-lead ECG recordings of 20 healthy controls. A set of distance metrics are developed to quantify the overall changes between different ECG recordings within this LE model. Statistically significant differences between control and ToF subjects were observed for most of the distance metrics. The analysis of changes over time in ToF patients indicates a general trend of increased distance over time in all the metrics, which can be related to a worsening condition. This indicates the relevance of LEs in multi-lead ECG processing, particularly for deterioration analysis., Signal Processing Systems