Electromyographic (EMG) measurements of the respiratory muscles provide a convenient and noninvasive way to assess respiratory muscle function and detect patient activity during assisted mechanical ventilation. However, surface EMG measurements of the diaphragm and intercostal muscles are substantially contaminated by cardiac activity due to the vicinity of the cardiac muscles. Many algorithmic solutions to this problem have been proposed, yet a conclusive performance comparison of the most promising candidates currently is missing. The objective of this work is to provide a quantitative performance comparison of six previously proposed cardiac artifact removal algorithms operating on singlechannel EMG measurements, and two newly proposed, improved versions of these algorithms. Algorithmic performance is evaluated quantitatively based on four different measures of separation success, using both synthetic validation signals and electromyographic measurements of the respiratory muscles in eight subjects. The compared algorithms are two versions of the empirical template subtraction algorithm, two model-based Bayesian filtering procedures, a wavelet denoising approach, an empirical mode decomposition (EMD) based approach, and classical high-pass filtering. Different algorithms perform well with respect to different performance measures. Template subtraction algorithms yield the best results if the characteristics of the raw signal are of interest, while filtering algorithms like simple high-pass filtering, wavelet denoising, and EMD-based denoising show superior performance for calculating a cleaned envelope signal. No algorithm completely removes the cardiac interference, but the characteristic errors introduced by the considered algorithms differ. Hence, the choice of the algorithm to use should be made depending on the target application. Finally, we also demonstrate that our empirical SNR measure, which can be calculated without knowledge of the true, undisturbed signals, correlates strongly with the exact reconstruction error. Thus, it represents a reliable indicator for algorithm performance on real measurement data.

Background: Inspiratory patient effort under assisted mechanical ventilation is an important quantity for assessing patient–ventilator interaction and recognizing over and under assistance. An established clinical standard is respiratory muscle pressure $$\textit{P}_{\mathrm{mus}}$$Pmus , derived from esophageal pressure ( $$\textit{P}_{\mathrm{es}}$$Pes ), which requires the correct placement and calibration of an esophageal balloon catheter. Surface electromyography (sEMG) of the respiratory muscles represents a promising and straightforward alternative technique, enabling non-invasive monitoring of patient activity.Methods: A prospective observational study was conducted with patients under assisted mechanical ventilation, who were scheduled for elective bronchoscopy. Airway flow and pressure, esophageal/gastric pressures and sEMG of the diaphragm and intercostal muscles were recorded at four levels of pressure support ventilation. Patient efforts were quantified via the $$\textit{P}_{\mathrm{mus}}$$Pmus -time product ( $${\mathrm{PTP}}_{\mathrm{mus}}$$PTPmus ), the transdiaphragmatic pressure-time product ( $${\mathrm{PTP}}_{\mathrm{di}}$$PTPdi ) and the EMG-time products (ETP) of the two sEMG channels. To improve the signal-to-noise ratio, a method for automatically selecting the more informative of the sEMG channels was investigated. Correlation between ETP and $${\mathrm{PTP}}_{\mathrm{mus}}$$PTPmus was assessed by determining a neuromechanical conversion factor $$\textit{K}_{\mathrm{EMG}}$$KEMG between the two quantities. Moreover, it was investigated whether this scalar can be reliably determined from airway pressure during occlusion maneuvers, thus allowing to quantify inspiratory effort based solely on sEMG measurements.Results: In total, 62 patients with heterogeneous pulmonary diseases were enrolled in the study, 43 of which were included in the data analysis. The ETP of the two sEMG channels was well correlated with $${\mathrm{PTP}}_{\mathrm{mus}}$$PTPmus ( $$\textit{r}={0.79\pm 0.25}$$r=0.79±0.25 and $$\textit{r}={0.84\pm 0.16}$$r=0.84±0.16 for diaphragm and intercostal recordings, respectively). The proposed automatic channel selection method improved correlation with $${\mathrm{PTP}}_{\mathrm{mus}}$$PTPmus ( $$\textit{r}={0.87\pm 0.09}$$r=0.87±0.09 ). The neuromechanical conversion factor obtained by fitting ETP to $${\mathrm{PTP}}_{\mathrm{mus}}$$PTPmus varied widely between patients ( $$\textit{K}_{\mathrm{EMG}}= {4.32\pm 3.73}\,{\hbox {cm}\hbox {H}_{2}\hbox {O}/\upmu \hbox {V}}$$KEMG=4.32±3.73cm2O/μV ) and was highly correlated with the scalar determined during occlusions ( $$\textit{r}={0.95}$$r=0.95 , $$\textit{p}<{.001}$$p<.001 ). The occlusion-based method for deriving $${\mathrm{PTP}}_{\mathrm{mus}}$$PTPmus from ETP showed a breath-wise deviation to $${\mathrm{PTP}}_{\mathrm{mus}}$$PTPmus of $${0.43\pm 1.73}\,{\hbox {cm}\hbox {H}_{2}\hbox {O}\,\hbox {s}}$$0.43±1.73cm2Os across all datasets.Conclusion: These results support the use of surface electromyography as a non-invasive alternative for monitoring breath-by-breath inspiratory effort of patients under assisted mechanical ventilation.

Objective: The quantification of inspiratory patient effort in assisted mechanical ventilation is essential for the adjustment of ventilatory assistance and for assessing patient-ventilator interaction. The inspiratory effort is usually measured via the respiratory muscle pressure ( P $_{\mathsf{mus}}$ ) derived from esophageal pressure ( P $_{\mathsf{es}}$ ) measurements. As yet, no reliable non-invasive and unobtrusive alternatives exist to continuously quantify P $_{\mathsf{mus}}$ . Methods: We propose a model-based approach to estimate P $_{\mathsf{mus}}$ non-invasively during assisted ventilation using surface electromyographic (sEMG) measurements. The method combines the sEMG and ventilator signals to determine the lung elastance and resistance as well as the neuromechanical coupling of the respiratory muscles via a novel regression technique. Using the equation of motion, an estimate for P $_{\mathsf{mus}}$ can then be calculated directly from the lung mechanical parameters and the pneumatic ventilator signals. Results: The method was applied to data recorded from a total of 43 ventilated patients and validated against P $_{\mathsf{es}}$ -derived P $_{\mathsf{mus}}$ . Patient effort was quantified via the P $_{\mathsf{mus}}$ pressure-time-product (PTP). The sEMG-derived PTP estimated using the proposed method was highly correlated to P $_{\mathsf{es}}$ -derived PTP ( $\mathsf{r}=\text{0.95}\pm \text{0.04}$ ), and the breath-wise deviation between the two quantities was $-\text{0.83}\pm \text{1.73}\,\text{cmH}_\text{2}\text{O}\text{s}$ . Conclusion: The estimated, sEMG-derived P $_{\mathsf{mus}}$ is closely related to the P $_{\mathsf{es}}$ -based reference and allows to reliably quantify inspiratory effort. Significance: The proposed technique provides a valuable tool for physicians to assess patients undergoing assisted mechanical ventilation and, thus, may support clinical decision making.

Diabetic retinopathy (DR) is a leading cause of vision loss. Therefore, screening for early signs and assessment of the DR severity is crucial and extensively studied. To support clinicians, screening could be automated by algorithms that can, for example, refer difficult decisions to specialists for further investigation. However, frequently used neural networks (NNs) typically do not know when they do not know and approximate Bayesian NNs often equally do not suffice to provide well-calibrated uncertainty estimates. Thus, in this work, we investigate whether and how to use deep kernel learning (DKL) which we designed as a hybrid combination of the state-of-the-art EfficientNet-B0 and a Gaussian process (GP) layer to improve the quality of uncertainty estimates in referral-based DR screening. To this end, we first analyze the necessity for recently proposed extensions to the DKL framework to resolve miscalibrated uncertainties, despite the theoretical superiority of GPs to uncertainty quantification. Our subsequent comprehensive comparison of the curated DKL’s performance to that of the most common approximate Bayesian NNs shows our DKL models to particularly improve the detection of near out-of-distribution (OOD) samples containing other eye diseases through epistemic uncertainty information, but also enhance the calibration of aleatoric in-distribution uncertainty and diagnostic performance. Hence, it can provide a substantial benefit for safety-critical medical applications, like automated DR screening, particularly by potentially reducing the risk of missing diseases other than DR due to the improved near-OOD detection performance.

An important aspect of mechanical ventilation is the recognition and quantification of spontaneous respiratory effort. However, measurement of flows and pressures often used for this purpose is prone to error. A promising alternative is to detect diaphragmatic contractions, directly. A method recently proposed is to acquire the diaphragm EMG signals using surface electrodes. However, this method is often limited by disturbances and electrode placements for some applications in which the patient is moving such as rehabilitation or breathing training. In this work, we present a novel noninvasive method that addresses these problems. This method is based on a novel dry electrode belt, which can be used to comfortably derive EMG signals from the thorax, in combination with a developed electrical measurement system. The modular multi-channel system is capable of simultaneously deriving and digitizing 32 differential EMG channels and sending them to a PC. A specific digital signal processing chain allows combining the data into one robust overall signal. In addition, the signals derived from the thorax can be used to obtain information regarding the spatio-temporal propagation of the diaphragm EMG. To verify the functionality, the system is characterized. Subsequently, subject measurements are performed. From these, the spatio-temporal propagation of diaphragm EMG on the thorax can be identified. For better visualization, this propagation is graphically displayed in a 3D model. In addition, it is shown how the combination of all signals can be used to obtain a robust overall signal that can be used to control ventilators.