Physiological measurement最新文献

Objective.The transient autonomic nervous system responses induced by electroconvulsive therapy (ECT) may serve as critical indicators of treatment efficacy and potential side effects; however, their precise characteristics remains unclear. Considering that the intense stimulation of ECT may disrupt the typical antagonistic relationship between the sympathetic and parasympathetic branches, this study aims to conduct a meticulous analysis of the rapid changes in heart rate variability (HRV) and HR during ECT, with a particular focus on their synchronized interplay.Methods.Pulse interval sequences were collected from 50 sessions of bitemporal ECT administered to 27 patients diagnosed with major depressive disorder. The average HR and ultra-short term HRV indices RMSSD and SDNN, as well as the Poincaré indices SD1, SD2 and SD2/SD1, were calculated using a 10 s sliding window with a step size of 1 s. In particular, the synchronous changes between SD1, SD2, SD2/SD1 and HR were analyzed.Results.The synchronous changes of the indices showed different characteristics over time. In particular, SD1, SD2 and HR increased significantly by 41.50 ± 11.45 ms, 33.97 ± 10.98 ms and 9.68 ± 2.00 bpm respectively between 8 and 20 s, whereas they decreased significantly by 19.89 ± 9.07 ms, 17.54 ± 8.54 ms and 3.80 ± 1.33 bpm respectively between 45 and 53 s after ECT stimulus onset. SD1 and SD2 both had highly significant positive correlations with HR in the above phases.Conclusion.The results suggest that bitemporal ECT induces the sympathetic and parasympathetic co-activation during the early ictal period and brief co-inhibition approximately 45 s after stimulus. Our findings may provide new insights comprehending the mechanisms of ECT and its associated cardiovascular risks.

Objective. Humanity faces many health challenges, among which respiratory diseases are one of the leading causes of human death. Existing AI-driven pre-diagnosis approaches can enhance the efficiency of diagnosis but still face challenges. For example, single-modal data suffer from information redundancy or loss, difficulty in learning relationships between features, and revealing the obscure characteristics of complex diseases. Therefore, it is critical to explore a method that can assist clinicians in detecting lesions early and in pre-diagnosing corresponding diseases.Approach.This paper introduces a novel network structure, strong constraint self-critical strategy network (SCSCS-Net), which can effectively extract image features from chest x-ray images and generate medical image descriptions, assist clinicians in analyzing patients' medical imaging information, deeply explore potential disease characteristics, and assist in making pre-diagnostic decisions. The SCSCS-Net consists of a reinforced cross-modal feature representation model and a self-critical cross-modal alignment model, which are responsible for learning the features interdependence between images and reports by using a multi-subspace self-attention structure and guiding the model in learning report generation strategies to improve the professionalism and consistency of medical terms in generated reports, respectively.Main results.We further compare our model with some advanced models on the same dataset, and the results demonstrate that our method achieves better performance. Finally, the CE and NLG metrics further confirm that the proposed method acquires the ability to generate high-quality medical reports with higher clinical consistency in generating medical reports.Significance.Our novel method has the potential to improve the early detection and pre-diagnosis of respiratory diseases. The model proposed in this paper allows to narrow the gap between artificial intelligence technology and clinical medical diagnosis and provides the possibility for in-depth integration.

Objectives.Aortic dilatation is a severe pathology that increases the risk of rupture and its hemodynamics could be accurately assessed by using the 4D flow cardiovascular magnetic resonance (CMR) technique but flow assessment under complex flow patterns require validation. The aim of this work was to develop anin vitrosystem compatible with CMR to assess the accuracy of volume flow measurements in dilated aortas.Approach.Two latex models, one with ascending and the other with abdominal aortic aneurysms were manufactured to ensure a constant and controlled net flow volume along the aortic length. A pneumatic piston driven by a stepper motor and controlled by an embedded system located in the control room modulated a pulsatile fluid flow using a pump with an elastic membrane placed in the magnet near the elastic models. All the visualization and measurement algorithms were integrated into a custom computer platform. 4D flow imaging was used to estimate the flow rate and volume through multiple aortic planes and compared to the reference assessed by weight method and to 2D flow measurements.Main results.The errors of flow volume assessment using 4D flow remained within reasonable limits along the length of the aortic models. Mean differences in net flow volume from the reference were less than 2 ml (range -4 to 6 ml), corresponding to mean relative differences of less than 4% (range -8% to 11%). Averaged net, forward and backward flow volume estimations along the aortic length were similar using 2D and 4D flow measurements (p> 0.05). Peak forward and backward flow rates increased in the dilated regions and were comparable to those observed in patients.Significance.The accuracy of flow volume estimates in complex flow patterns, such as those observed in patients with aneurysms, was validatedin vitrousing 4D flow.

A physiological signal-based Human-Computer Interaction (HCI) system provides a communication link between human emotional states and external devices. Accurately classifying these signals is vital for effective interaction, which requires extracting and selecting the most discriminative features to differentiate between various emotional states. This paper introduces the SMOTETomek-Correlated Interactive Reinforcement Learning (ST-CIRL) framework for anxiety classification, which leverages meta-descriptive statistics to enhance the state representation in the reinforcement learning process. Firstly, it addresses class imbalance using SMOTETomek and further reduces dimensionality by pruning redundant features. Secondly, the ST-CIRL framework enhances classification accuracy through the collaboration of multiple agents to select the most informative features using Interactive Reinforcement Learning (IRL). Further, the paper utilizes classifiers, including Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), and Light Gradient Boosting (LGBM) for anxiety classification. Thirdly, the hyperparameters of these machine learning algorithms are tuned using the Optuna approach to enhance model performance. The proposed ST-CIRL framework achieves a maximum accuracy of 95.35% and an F1-score of 95.49% using the LightGBM classifier. Furthermore, the results demonstrate that the proposed approach outperforms current state-of-the-art methods. These findings validate the efficacy of the SMOTETomek method and the innovative feature optimization approach, highlighting the potential of reinforcement learning in enhancing HCI systems and expanding its applicability in intelligent system design.

Objective.This study aims to evaluate the efficacy of wearable physiology and movement sensors in identifying a spectrum of challenging behaviors, including self-injurious behavior, in children and teenagers with autism spectrum disorder (ASD) in real-world settings.Approach.We utilized a long-short-term memory network with features derived using the wavelet scatter transform to analyze physiological biosignals, including electrodermal activity and skin temperature, alongside three-dimensional movement data captured via accelerometers. The study was conducted in naturalistic environments, focusing on participants' daily activities.Main results.Our findings indicate that the best performance in detecting challenging behaviors was achieved using movement data. The results showed a sensitivity of 0.62, specificity of 0.71, F1-score of 0.36, and an area under the ROC curve of 0.71. These results are particularly significant given the study's focus on real-world scenarios and the limited existing research in this area.Significance.This study demonstrates that using wearable technology to record physiological and movement signals can detect challenging behaviors in children with ASD in real-world settings. This methodology has the potential to greatly improve the management of these behaviors, thereby enhancing the quality of life for children with ASD and their caregivers. This approach marks a significant step forward in applying the outcome of ASD research in practical, everyday environments.

Objective.In recent years, wearable devices such as smartwatches and smart patches have revolutionized biosignal acquisition and analysis, particularly for monitoring electrocardiography (ECG). However, the limited power supply of these devices often precludes real-time data analysis on the patch itself.Approach.This paper introduces a novel Python package, tinyHLS (High Level Synthesis), designed to address these challenges by converting Python-based AI models into platform-independent hardware description language code accelerators. Specifically designed for convolutional neural networks, tinyHLS seamlessly integrates into the AI developer's workflow in Python TensorFlow Keras. Our methodology leverages a template-based hardware compiler that ensures flexibility, efficiency, and ease of use. In this work, tinyHLS is first-published featuring templates for several layers of neural networks, such as dense, convolution, max and global average pooling. In the first version, rectified linear unit is supported as activation. It targets one-dimensional data, with a particular focus on time series data.Main results.The generated accelerators are validated in detecting atrial fibrillation on ECG data, demonstrating significant improvements in processing speed (62-fold) and energy efficiency (4.5-fold). Quality of code and synthesizability are ensured by validating the outputs with commercial ASIC design tools.Significance.Importantly, tinyHLS is open-source and does not rely on commercial tools, making it a versatile solution for both academic and commercial applications. The paper also discusses the integration with an open-source RISC-V and potential for future enhancements of tinyHLS, including its application in edge servers and cloud computing. The source code is available on GitHub:https://github.com/Fraunhofer-IMS/tinyHLS.

Objective: Sleep staging is a crucial task in clinical and research contexts for diagnosing and understanding sleep disorders. This work introduces PhysioEx, a Python library designed to support the analysis of sleep stages using deep learning and Explainable AI (XAI). Approach: PhysioEx provides an extensible and modular API for standardizing and automating the sleep staging pipeline, covering data preprocessing, model training, testing, fine-tuning, and explainability. It supports both low-resource devices and high-performance computing clusters and includes pretrained models based on the Sleep Heart Health Study (SHHS) dataset. These models support single-channel EEG and multichannel EEG-EOG-EMG configurations and are easily adaptable to custom datasets. PhysioEx also features a command-line interface toolbox allowing users to streamline the model development and deployment. The library offers a range of XAI post-hoc methods to explain model decisions and align them with expert knowledge. Main results: PhysioEx benchmark state-of-the-art sleep staging models in a standard pipeline. Enabling a fair comparison between them both on the training source and out-of-domain sources. Its XAI techniques provide insights into deep learning-based sleep staging by linking model decisions to human-understandable concepts, such as AASM-defined rules. Significance: PhysioEx addresses the need for a standardized and accessible platform for sleep staging analysis, combining deep learning and XAI. By supporting modular workflows and explainable insights, it bridges the gap between machine learning models and clinical expertise. PhysioEx is publicly available and installable via pip, making it a valuable tool for researchers and practitioners in sleep medicine.

Background and objective: In contrast to respiratory sound classification, respiratory phase and adventitious sound event detection provides more detailed and accurate respiratory information, which is clinically important for respiratory disorders. However, current respiratory sound event detection models mainly use convolutional neural networks to generate frame-level predictions. A significant drawback of the frame-based model lies in its pursuit of optimal frame-level predictions rather than the best event-level ones. Moreover, it demands post-processing and is incapable of being trained in an entirely end-to-end fashion. Based on the above research status, this paper proposes an event-based Transformer method - Respiratory Events Detection Transformer (REDT) for multi-class respiratory sound event detection task to achieve efficient recognition and localization of the respiratory phase and adventitious sound events.

Approach: Firstly, REDT approach employs the Transformer for time-frequency analysis of respiratory sound signals to extract essential features. Secondly, REDT converts these features into timestamp representations and achieves sound event detection by predicting the location and category of timestamps.

Main results: Our method is validated on the public dataset HF_Lung_V1. The experimental results show that our F1 scores for inspiration, expiration, Continuous Adventitious Sound(CAS) and Discontinuous Adventitious Sound(DAS) are 90.5%, 77.3%, 78.9%, and 59.4%, respectively.

Significance: These results demonstrate the method's significant performance in respiratory sound event detection.