Physiological measurement最新文献

Objective.The detection of arterial pulsating signals at the skin periphery with Photoplethysmography (PPG) are easily distorted by motion artifacts. This work explores the alternatives to the aid of PPG reconstruction with movement sensors (accelerometer and/or gyroscope) which to date have demonstrated the best pulsating signal reconstruction.Approach.A generative adversarial network with fully connected layers is proposed for the reconstruction of distorted PPG signals. Artificial corruption was performed to the clean selected signals from the BIDMC Heart Rate dataset, processed from the larger MIMIC II waveform database to create the training, validation and testing sets.Main results.The heart rate (HR) of this dataset was further extracted to evaluate the performance of the model obtaining a mean absolute error of 1.31 bpm comparing the HR of the target and reconstructed PPG signals with HR between 70 and 115 bpm.Significance.The model architecture is effective at reconstructing noisy PPG signals regardless the length and amplitude of the corruption introduced. The performance over a range of HR (70-115 bpm), indicates a promising approach for real-time PPG signal reconstruction without the aid of acceleration or angular velocity inputs.

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 -RespiratoryEventsDetectionTransformer (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 and discontinuous adventitious sound 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.

Objective.Sleep staging is a crucial task in clinical and research contexts for diagnosing and understanding sleep disorders. This work introduces PhysioEx (Physiological Signal Explainer), a Python library designed to support the analysis of sleep stages using deep learning (DL) 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 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 DL-based sleep staging by linking model decisions to human-understandable concepts, such as American Academy of Sleep Medicine-defined rules.Significance.PhysioEx addresses the need for a standardized and accessible platform for sleep staging analysis, combining DL 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 pip⁶6https://pypi.org/project/physioex/., making it a valuable tool for researchers and practitioners in sleep medicine.

Objective.This paper presents a novel dual-branch framework for estimating blood pressure (BP) using photoplethysmography (PPG) signals. The method combines deep learning with clinical prior knowledge and models different time periods (morning, afternoon, and evening) to achieve precise, cuffless BP estimation.Approach.Preprocessed single-channel PPG signals are input into two feature extraction branches. The first branch converts PPG dimensions to 2D and uses pre-trained Mobile Vision Transformer-v2 (MobileViTv2) and Visual Geometry Group19 (Vgg19) backbones to extract deep PPG features based on the different mechanisms of systolic blood pressure (SBP) and diastolic blood pressure (DBP) formation. The second branch calculates multi-dimensional feature parameters based on the relationship between PPG waveforms and factors affecting BP. We fuse the features from both branches and consider diurnal BP variations, using AutoML strategy to construct specific SBP and DBP estimation models for the different periods. The algorithm was developed on the human resting state PPG and BP dataset (HRSD) and validated on the MIMIC-IV dataset for generalization performance.Main results.The mean absolute error (MAE) for BP estimation is 6.42 mmHg SBP and 4.96 mmHg DBP in the morning, 4.84 mmHg (SBP) and 3.73 mmHg (DBP) in the afternoon, and 2.65 mmHg (SBP) and 2.56 mmHg (DBP) in the evening. Performance on the MIMIC-IV database was 4.34 mmHg (SBP) and 3.11 mmHg (DBP). The method meets the standards of the Association for the Advancement of Medical Instrumentation and achieves Grade A of the British Hypertension Society (BHS) standards.Significance. This indicates that it is an accurate and reliable non-invasive BP monitoring technology, applicable for continuous health monitoring and cardiovascular disease prevention.

Objective. We study the changes in morphology of the photoplethysmography (PPG) signals-acquired from a select group of South Asian origin-through a low-cost PPG sensor, and correlate it with healthy aging which allows us to reliably estimate the vascular age and chronological age of a healthy person as well as the age group he/she belongs to.Approach. Raw infrared PPG data is collected from the finger-tip of 173 apparently healthy subjects, aged 3-61 years, via a non-invasive low-cost MAX30102 PPG sensor. In addition, the following metadata is recorded for each subject: age, gender, height, weight, family history of cardiac disease, smoking history, vitals (heart rate and SpO2). The raw PPG data is conditioned and 62 features are then extracted based upon the first four PPG derivatives. Then, correlation-based feature-ranking is performed which retains 26 most important features. Finally, the feature set is fed to three machine learning classifiers, i.e. logistic regression, random forest, eXtreme Gradient Boosting (XGBoost), and two shallow neural networks: a feedforward neural network and a convolutional neural network.Main results. For the age group classification problem, the ensemble method XGboost stands out with an accuracy of 99% for both binary classification (3-20 years vs. 20+ years) and three-class classification (3-18 years, 18-23 years, 23+ years). For the vascular/chronological age prediction problem, the ensemble random forest method stands out with a mean absolute error of 6.97 years.Significance. The results demonstrate that PPG is indeed a promising (i.e. low-cost, non-invasive) biomarker to study the healthy aging phenomenon.

Objective.Patients with pulmonary fibrosis (PF) often experience long waits before getting a correct diagnosis, and this delay in reaching specialized care is associated with increased mortality, regardless of the severity of the disease. Early diagnosis and timely treatment of PF can potentially extend life expectancy and maintain a better quality of life. Crackles present in the recorded lung sounds may be crucial for the early diagnosis of PF.Approach.This paper describes an automated system for differentiating lung sounds related to PF from other pathological lung conditions using the average number of crackles per breath cycle (NOC/BC). The system is divided into four main parts: (1) pre-processing, (2) separation of crackles from normal breath sounds using the iterative envelope mean fractal dimension filter, (3) crackle verification and counting, and (4) estimating NOC/BC. The system was tested on a dataset consisting of 48 (24 fibrotic and 24 non-fibrotic) subjects and the results were compared with an assessment by two expert respiratory physicians. The set of high-resolution computed tomography images, reviewed by two expert radiologists for the presence or absence of PF, was used as the ground truth for evaluating the PF and non-PF classification performance of the system.Main results.The overall performance of the automatic classifier based on receiver operating curve-derived cut-off value for average NOC/BC of 18.65 (AUC = 0.845, 95% CI 0.739-0.952,p< 0.001; sensitivity = 91.7%; specificity = 59.3%) compares favourably with the averaged performance of the physicians (sensitivity = 83.3%; specificity = 56.25%).Significance.Although radiological assessment should remain the gold standard for diagnosis of fibrotic interstitial lung disease (ILD), the automatic classification system has strong potential for diagnostic support, especially in assisting general practitioners in the auscultatory assessment of lung sounds to prompt further diagnostic work up of patients with suspect of ILD.

Objective. Heart rate variability (HRV) is an important indicator of cardiac autonomic function. Given its clinical significance, reliable HRV assessment is crucial. Here, we assessed test-retest stability, as a key aspect of reliability, quantifying the consistency of a measure when repeated under the same conditions.Approach. This observational study includes healthy individuals. A 20 min electrocardiogram was recorded at rest in a supine position and during deep breathing in two lab sessions within one week, at the same time of day. HRV indices from time domain, frequency domain, nonlinear dynamics, and information-theoretic complexity were assessed using a validated toolbox. Additionally, heart rate variations per respiratory cycle were evaluated during deep breathing. Lifestyle factors such as perceived stress, mood, physical activity, sleep quality were assessed prior to both sessions. Intra-class correlation (ICC) and coefficients of variation (CVs) were used to assess the concordance between the two measurements and the relative deviation, respectively.Main results. From 62 screened individuals, 51 participants were recruited from the local community. One participant opted out for personal reasons, and another with frequent premature beats was excluded, leaving a final sample of 49 individuals. Most self-rated psychological and lifestyle indicators showed substantial agreement, though participants reported less stress and better mood in the second session. At rest, ICC of HRV ranged from 0.50 to 0.83, with CV from 5% to 41%. Spectral HRV measures were less reliable than time domain parameters. Nonlinear and time domain features had substantial to nearly perfect agreement. Complexity measures had low CVs but limited test-retest correlation. The stability indices of HRV during deep breathing were not significantly different from those during rest. Test-retest differences in root mean square of the successive beat-to-beat interval difference were not sufficiently explained by lifestyle factors.Significance.Test-retest stability of HRV depends considerably on chosen measures. Our data suggest that HRV can be assessed reliably using time-domain indices at rest.

Objective.Electrical impedance tomography (EIT) is a non-invasive technique used for lung imaging. A significant challenge in EIT is reconstructing images of deeper thoracic regions due to the low sensitivity of boundary voltages to internal conductivity variations. The current injection pattern is decisive as it influences the current path, boundary voltages, and their sensitivity to tissue changes.Approach.This study introduces a novel current injection pattern with radially placed electrodes excited in a rotating radial pattern. The effectiveness of the proposed pattern was investigated using a 3D computational model that mimics the human thorax, replicating its geometry and tissue electrical properties. To examine the detection of lung anomalies, models representing both healthy and unhealthy states, including cancer-like anomalies in three different positions, were developed. The new pattern was compared to common patterns-adjacent, skip 1, and opposite-using finite element analysis. The comparison focused on the current density within lung nodules and the sensitivity to changes in anomaly positions.Main results.Results showed that the new pattern achieved the maximum current density within anomalies compared to surrounding tissues, with peak values near the closest electrode pairs to the anomalies. Specifically, current density magnitudes reached72.73⋅10-9A⋅m,145.24⋅10-9A⋅m, and26.43⋅10-9A⋅mfor the three different positions, respectively. Furthermore, the novel pattern's sensitivity to anomaly position changes surpassed the common patterns.Significance.These results demonstrate the efficiency of the proposed injection pattern in detecting lung anomalies compared to the common injection patterns.

Objective.Abnormal regional lung ventilation can lead to undesirable outcomes during the induction of anesthesia. Head rotated ventilation has proven to change the airflow of upper airway tract and be effective in increasing the tidal volume. This study aimed to investigate the influence of head rotated mask ventilation on regional ventilation distribution during the induction phase of anesthesia.Approach.Ninety patients undergoing anesthesia induction were randomly assigned to receive either neutral head (neutral-head group) or rotated right side head (rotated-head group) mask ventilation. Pressure-controlled mode was used in all mechanical ventilation. The regional lung ventilation was monitored by electrical impedance tomography. The primary outcome was the ratio of left/right lung ventilation distribution. The secondary outcomes were global inhomogeneity index (GI), center of ventilation (CoV, 100% = entirely dorsal), and the regional lung distribution differences between spontaneous and mask ventilation.Main results.Forty-two patients with neutral-head and 38 with rotated-head mask ventilation were analyzed finally. Compared with spontaneous ventilation, mask positive-pressure ventilation caused significant changes in the ratio of left/right lung ventilation distribution [0.85 (0.27) versus 0.94 (0.30);P= 0.022]. However, there were no differences in the ratio of left/right lung ventilation distribution between neutral and rotated head groups (P= 0.128). When compared with spontaneous ventilation, mask ventilation caused regional distributions of ventilation shifts towards ventral lung areas (CoV: 45.7 ± 5.0% versus 39.2 ± 4.8%;P< 0.001), and significant lung ventilation inhomogeneity (GI: 0.40 ± 0.07 versus 0.49 ± 0.14;P< 0.001). Compared with neutral-head mask ventilation, rotated-head mask ventilation was associated with higher expiratory tidal volume (TVe) (575.1 ± 148.6 ml versus 654.2 ± 204.0 ml;P= 0.049).Significance.Mask positive ventilation caused regional lung ventilation changes. When compared with neutral-head mask ventilation, rotated-head mask ventilation did not improve the regional ventilation towards to left lung. However, rotated-head mask ventilation was associated with higher TVe, and has the potential for better oxygenation.Trial Registration.This study was registered on Chinese Clinical Trial Registry on 6 August, 2024 (ChiCTR2400087858).

Heart rate variability (HRV) analysis during sleep plays a key role for understanding autonomic nervous system function and assessing cardiovascular health. The UNICA Sleep HRV analysis (UNICA-HRV) tool is a novel, open-source MATLAB tool designed to fill the gap in current HRV analysis tools. In particular, the integration of ECG and HRV data with hypnogram information, which illustrates the progression through the different sleep stages, eases the computation of HRV metrics in polysomnographic recordings. This integration is crucial for accurate phase-specific analysis, as autonomic regulation changes markedly across different sleep stages. The tool supports single- and multiple-subject analyses and is tailored to enhance usability and accessibility for researchers and clinicians without requiring extensive technical expertise. It implements and supports a variety of data inputs and configurations, allowing for flexible, detailed HRV analyses across sleep stages, employing classical and advanced metrics, such as time-domain, frequency-domain, non-linear, complexity, and Poincaré plot indexes. Validation of the tool against established tools like Kubios and PhysioZoo indicates its robustness and precision in generating reliable HRV metrics, that are essential not only for sleep research, but also for clinical diagnostics. The introduction of UNICA-HRV represents a significant simplification for sleep studies, and its open-source nature (licensed under a Creative Commons Attribution 4.0 International License) allows to easily extend the functionality to other needs.