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.

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 suggest that the traditional measures could be used in combination with the proposed CPC biomarkers to improve weaning readiness.

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.

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.