Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference最新文献

Respiratory patterns present great variability, both in healthy subjects and in patients with different diseases and forms of nasal, oral, superficial or deep breathing. The analysis of this variability depends, among others, on the device used to record the signals that describe these patterns. In this study, we propose multivariable regression models to estimate tidal volume (V_T) considering different breathing patterns. Twenty-three healthy volunteers underwent continuous multisensor recordings considering different modes of breathing. Respiratory flow and volume signals were recorded with a pneumotachograph and thoracic and abdominal respiratory inductive plethysmographic bands. Several respiratory parameters were extracted from the volume signals, such as inspiratory and expiratory areas (Area_ins, Area_exp), maximum volume relative to the cycle start and end (VT_ins, VT_exp), inspiratory and expiratory time (T_ins, T_exp), cycle duration (T_tot), and normalized parameters of clinical interest. The parameters with the greatest individual predictive power were combined using multivariable models to estimate V_T. Their performance were quantified in terms of determination coefficient (R²), relative error (E_R) and interquartile range (IQR). Using only three parameters, the results obtained for the thoracic band (VT_exp, T_tot, Area_exp) were better than those obtained from the abdominal band (VT_exp, T_ins, Area_ins) with R² = 0.94 (IQR: 0.07); E_R = 6.99 (IQR: 6.12) vs R² = 0.91 (IQR: 0.09), E_R = 8.70 (IQR: 4.62). Overall performance increased to R² = 0.97 (IQR: 0.02) and E_R = 4.60 (IQR: 3.68) when parameters from the different bands were combined, further improving when was applied to segments with different inspiration-expiration patterns. In particular, the nose-nose E_R = 1.39 (IQR: 0.73), nose-mouth E_R = 2.11 (IQR: 1.23) and mouth-mouth E_R = 2.29 (IQR: 1.44) patterns showed the best results compared to those obtained for basal, shallow and deep breathing.Clinical relevance- Respiratory pattern variability can be described using multivariable regression model for tidal volume.

Microwave ablation (MWA) therapy is a well-known technique for locally destroying lung tumors with the help of computed tomography (CT) images. However, tumor recurrence occurs because of insufficient ablation of the tumor. In order to perform an accurate treatment of lung cancer, there is a demand to determine the tumor area precisely. To address the problem at hand, which involves accurately segmenting organs and tumors in CT images obtained during MWA therapy, physicians could benefit from a semantic segmentation method. However, such a method typically requires a large number of images to achieve optimal results through deep learning techniques. To overcome this challenge, our team developed four different (multiple) U-Net based semantic segmentation models that work in conjunction with one another to produce a more precise segmented image, even when working with a relatively small dataset. By combining the highest weight value of segmentation from multiple methods into a single output, we can achieve a more reliable and accurate segmentation outcome. Our approach proved successful in segmenting four different tissue structures, including lungs, lung tumors, and ablated tissues in CT medical images. The Intersection over Union (IoU) is employed to quantitatively evaluate the proposed method. The method shows the highest average IoU, with 0.99 for the background, 0.98 for the lung, 0.77 for the ablated, and 0.54 for the tumor tissue. The results show that employing multiple DL methods is superior to that of individual base-learner models for all four different tissue structures, even in the presence of the relatively small dataset.Clinical relevance- An essential issue of tumor ablation therapy is to know when the entire tumor tissue has completely been destroyed. However, as it is difficult to distinguish between destroyed and living tumor, this is hardly reliable in clinical practice during MWA therapy, especially when working with a small dataset. Improved AI segmentation methods can help to improve performance to reduce recurrence.

Obstructive sleep apnea is a disorder characterized by partial or complete airway obstructions during sleep. Our previously published algorithms use the minimally invasive nasal pressure signal routinely collected during diagnostic polysomnography (PSG) to segment breaths and estimate airflow limitation (using flow:drive) and minute ventilation for each breath. The first aim of this study was to investigate the effect of airflow signal quality on these algorithms, which can be influenced by oronasal breathing and signal-to-noise ratio (SNR). It was hypothesized that these algorithms would make inaccurate estimates when the expiratory portion of breaths is attenuated to simulate oronasal breathing, and pink noise is added to the airflow signal to reduce SNR. At maximum SNR and 0% expiratory amplitude, the average error was 2.7% for flow:drive, -0.5% eupnea for ventilation, and 19.7 milliseconds for breath duration (n = 257,131 breaths). At 20 dB and 0% expiratory amplitude, the average error was -15.1% for flow:drive, 0.1% eupnea for ventilation, and 28.4 milliseconds for breath duration (n = 247,160 breaths). Unexpectedly, simulated oronasal breathing had a negligible effect on flow:drive, ventilation, and breath segmentation algorithms across all SNRs. Airflow SNR ≥ 20 dB had a negligible effect on ventilation and breath segmentation, whereas airflow SNR ≥ 30 dB had a negligible effect on flow:drive. The second aim of this study was to explore the possibility of correcting these algorithms to compensate for airflow signal asymmetry and low SNR. An offset based on estimated SNR applied to individual breath flow:drive estimates reduced the average error to ≤ 1.3% across all SNRs at patient and breath levels, thereby facilitating for flow:drive to be more accurately estimated from PSGs with low airflow SNR.Clinical Relevance- This study demonstrates that our airflow limitation, ventilation, and breath segmentation algorithms are robust to reduced airflow signal quality.

Electromyogram (EMG) signals provide valuable insights into the muscles' activities supporting the different hand movements, but their analysis can be challenging due to their stochastic nature, noise, and non-stationary variations in the signal. We are pioneering the use of a unique combination of wavelet scattering transform (WST) and attention mechanisms adopted from recent sequence modelling developments of deep neural networks for the classification of EMG patterns. Our approach utilizes WST, which decomposes the signal into different frequency components, and then applies a non-linear operation to the wavelet coefficients to create a more robust representation of the extracted features. This is coupled with different variations of attention mechanisms, typically employed to focus on the most important parts of the input data by considering weighted combinations of all input vectors. By applying this technique to EMG signals, we hypothesized that improvement in the classification accuracy could be achieved by focusing on the correlation between the different muscles' activation states associated with the different hand movements. To validate the proposed hypothesis, the study was conducted using three commonly used EMG datasets collected from various environments based on laboratory and wearable devices. This approach shows significant improvement in myoelectric pattern recognition (PR) compared to other methods, with average accuracies of up to 98%.

Brain-computer interfaces (BCI) have the potential to improve the quality of life for persons with paralysis. Sub-scalp EEG provides an alternative BCI signal acquisition method that compromises between the limitations of traditional EEG systems and the risks associated with intracranial electrodes, and has shown promise in long-term seizure monitoring. However, sub-scalp EEG has not yet been assessed for suitability in BCI applications. This study presents a preliminary comparison of visual evoked potentials (VEPs) recorded using sub-scalp and endovascular stent electrodes in a sheep. Sub-scalp electrodes recorded comparable VEP amplitude, signal-to-noise ratio and bandwidth to the stent electrodes.Clinical relevance-This is the first study to report a comparision between sub-scalp and stent electrode array signals. The use of sub-scalp EEG electrodes may aid in the long-term use of brain-computer interfaces.

Sleep position affects sleep quality and the severity of different diseases. Classical methods to measure sleep position are complex, expensive, and difficult to use outside the laboratory. Wearables and smartphones can help to address these issues to track sleep position at home over several nights. In this study, we monitor high-resolution sleep position in 13 adolescents over 4 nights using smartphone accelerometer data. We aim to investigate the distribution of sleep positions and position changes in adolescents, study their variability across nights, and propose new measures related to nocturnal body movements. We developed a new index, the mean sleep angle change per hour, and calculated three other measures: position shifts per hour, mean time at each position, and periods of immobility. Our results indicate that participants spent 56% of the time on the side (32% right and 24% left), 32% in supine, and 12% in prone position, similar to what happens in adults. However, adolescents moved more than adults during sleep according to all measures. There was some variability between nights, but lower than the inter-subject variability. In conclusion, this work systematically analyzes sleep position over several nights in adolescents, a largely unstudied population, and offers innovative solutions and measures for high-resolution sleep position monitoring in a simple and cost-effective way.Clinical Relevance- Our study characterizes sleep position in adolescents and provides novel unobtrusive methods and quantitative indices to monitor high-resolution sleep position at home during multiple nights.

Through the recent years, tissue engineering has been proven as a solid substitute of autografts in the stimulation of bone tissue regeneration, through the development of three dimensional (3D) porous matrices, commonly known as scaffolds. In this work, we analysed two scaffold structures with 500μm pore size, by performing computational fluid dynamics simulations, to compare permeability, Wall Shear Stress (WSS), velocity and pressure distributions. Taking into account those parameters the geometry named as "PCL-50" was the best to anticipate showing a superior performance in supporting cell growth due to the improved flow characteristics in the scaffold.Clinical Relevance- Bone defects that require invasive surgical treatment with high risks in terms of success and effectiveness. Bone tissue engineering (BTE) in combination with the use of computational fluid dynamics (CFD) analysis tools aim to assist in designing optimal scaffolds that better promote bone growth and repair. The fluid dynamic characteristics of a porous scaffold plays a vital role in cell viability and cell growth, affecting the osteogenic performance of the scaffold.

Spinal motor neurons receive a wide range of input frequencies. However, only frequencies below ca. 10 Hz are directly translated into motor output. Frequency components above 10 Hz are filtered out by neural pathways and muscle dynamics. These higher frequency components may have an indirect effect on motor output, or may simply represent movement-independent oscillations that leak down from supraspinal areas such as the motor cortex. If movement-independent oscillations leak down from supraspinal areas, they could provide a potential control signal in movement augmentation applications. We analysed high-density electromyography (HD-EMG) signals from the tibialis anterior muscle while human subjects performed various mental tasks. The subjects performed an isometric dorsiflexion of the right foot at a low level of force while simultaneously (1) imagining a movement of the right foot, (2) imagining a movement of both hands, (3) performing a mathematical task, or (4) performing no additional task. We classified the channel-averaged HD-EMG signals and the cumulative spike train (CST) of motor-units using a filter bank and a linear classifier. We found that in some subjects, the mental task can be classified from the channel-averaged HD-EMG signals and the CST in oscillations above 10 Hz. Furthermore, we found that these oscillation modulations are incompatible with a systematic and task-dependent change in force level. Our preliminary findings from a limited number of subjects suggest that some mental task-induced oscillations from supraspinal areas leak down to spinal motor neurons and are discriminable via EMG or CST signals at the innervated muscle.

The present study aims to design and fabricate a system capable of generating heterogeneities on the epicardial surface of an isolated rabbit heart perfused in a Langendorff system. The system consists of thermoelectric modules that can be independently controlled by the developed hardware, thereby allowing for the generation of temperature gradients on the epicardial surface, resulting in conduction slowing akin to heterogeneities of pathological origin. A comprehensive analysis of the system's viability was performed through modeling and thermal simulation, and its practicality was validated through preliminary tests conducted at the experimental cardiac electrophysiology laboratory of the University of Valencia. The design process involved the use of Fusion 360 for 3D designs, MATLAB/Simulink for algorithms and block diagrams, LTSpice and Altium Designer for schematic captures and PCB design, and the integration of specialized equipment for animal experimentation. The objective of the study was to efficiently capture epicardial recordings under varying conditions.Clinical relevance- The proposed system aims to induce local epicardial heterogeneities to generate labeled correct signals that can serve as a golden standard for improving algorithms that identify and characterize fibrotic substrates. This improvement will enhance the efficacy of ablation processes and potentially reduce the ablated surface area.

Major Depressive Disorder (MDD) is highly prevalent and characterized by often debilitating behavioral and cognitive symptoms. MDD is poorly understood, likely due to considerable heterogeneity and self-report-driven symptomatology. While researchers have been exploring the ability of machine learning to screen for MDD, much less attention has been paid to individual symptoms. We posit that understanding the relationship between objective data streams and individual depression symptoms is important for understanding the considerable heterogeneity in MDD. Thus, we conduct a comprehensive comparative study to explore the ability of machine learning to predict nine self-reported depressive symptoms with call and text logs. We created time series from the logs of over 300 participants by aggregating communication attributes- average length, count, or contacts- every 4, 6, 12, or 24 hours. We were most successful predicting movement irregularities with a balanced accuracy of 0.70. Further, we predicted suicidal ideation with a balanced accuracy of 0.67. Outgoing texts proved to be the most useful log type. This study provides valuable insights for future mobile health research aimed at personalizing assessment and intervention for MDD.