Physiological measurement最新文献

Objective.Deep learning for continuous physiological signals, such as electrocardiography or oximetry, has achieved remarkable success in supervised learning scenarios where training and testing data are drawn from the same distribution. However, when evaluating real-world applications, models often fail to generalize due to distribution shifts between the source domain on which the model was trained and the target domain where it is deployed. A common and particularly challenging shift often encountered in reality is where the source and target domain supports do not fully overlap. In this paper, we propose a novel framework, named Deep Unsupervised Domain adaptation using variable nEighbors (DUDE), to address this challenge.Approach.We introduce a new type of contrastive loss between the source and target domains using a dynamic neighbor selection strategy, in which the number of neighbors for each sample is adaptively determined based on the density observed in the latent space. We use multiple real-world datasets as source and target domains, with target domains that included demographics, ethnicities, geographies, and comorbidities that were not present in the source domain.Main results.The experimental results demonstrate superior DUDE performance compared to baselines and with an improvement of up to 16% over the original Nearest-Neighbor Contrastive Learning of Visual Representations strategy.Significance.Our contribution provides evidence on the potential of using DUDE to bridge the crucial gap of domain adaptation in medicine, potentially transforming patient care through more precise and adaptable diagnostic tools.

Objective.Sit-to-stand (STS) and sit-to-walk (STW) movements are key functional tasks to master following lower limb amputation. They are core to activities of daily living, enabling patients to regain independence. Physiotherapists assess movement fluency (hesitation and smoothness) by observing STS and STW however, this relies on extensive experience and lacks objectivity. This study aimed to establish objective, accessible and scalable quantitative measurements of movement fluency in amputees using instrumented movement analysis.Approach.12 transfemoral amputees (six limited community and six community ambulators) and six typical individuals completed walking, STS and STW tasks. Movement fluency was assessed using published algorithms to obtain hesitation and smoothness in STS and STW.Main results.In STW, hesitation, and smoothness showed statistically significant differences among the three groups. Community ambulators were significantly less hesitant (p= 0.009) and smoother (p= 0.007) than the limited community ambulators, but significantly more hesitant (p< 0.001) and less smooth (p< 0.001) than typical individuals. In STS, the community ambulators were significantly smoother than the limited community ambulators (p< 0.001), but not significantly different from typical individuals (p= 0.68). Community ambulators walked significantly faster than limited community ambulators (p< 0.001) but significantly slower compared to typical individuals (p< 0.001).Significance.Assessment of movement after amputation is not just about walking speed. Other important functional tasks can differentiate amputees and therefore should be considered. An amputee must learn to master both the STS and STW tasks before they can independently walk. Quantifying movement fluency in functional tasks is important to understanding the restoration of function following limb loss, tracking rehabilitation, and classifying amputees. While the study's small sample size reflects its feasibility design, findings support future research with larger cohorts. Subsequent studies should incorporate power calculations to improve generalisability.

Objective.In the analysis of obstructive sleep apnea (OSA), the main clinical index is the apnea-hypopnea index (AHI), or the average rate of respiratory events during sleep. This rate fluctuates during sleep, due to a variety of factors, such as sleep phases, body position, and other physiological mechanisms. Two people with the same AHI may manifest OSA may manifest OSA in drastically different ways. Therefore, a computed degree of statistical uncertainty alongside the average AHI would be a useful addition to a comprehensive sleep report-. In the current literature, the AHI uncertainty was modeled as a Poisson process and empirically estimated using bootstrap sampling of inter-event times (or intervals). However, we observed that long wake bouts, stochastic outliers in the intervals' distribution, and events' dispersion directly influence the bootstrap sampling, with either empirical over-estimation or theoretical under-estimation. In some cases, the result is a spurious empirical estimate of both AHI and its uncertainty. In others, a broad AHI uncertainty can be the correct description of the underlying process, and a Poisson model would be ill-fitted.Approach.We propose here three methods that improve the estimation of AHI uncertainty based on bootstrap sampling, making it more robust to the presence of spurious intervals caused by long wake bouts and events' overdispersion. We examine the violation of Poisson assumptions as the main cause of discrepancy between theoretical and empirical estimates, and propose the Negative Binomial distribution as an alternative model.Main results.Compared to the original Poisson-based method, we proved that the Negative Binomial can be a better theoretical model of uncertainty. Furthermore, our proposed methodology improved the estimation error of both AHI (up to 91% of the recordings) and the discrepancy with theoretical confidence intervals, in both Poisson and Negative Binomial models.Significance.This work provides notable improvements in the theoretical models of AHI uncertainty and in the robustness of empirical estimates.

Objective.Hypertension is a leading cause of mortality worldwide, for which myriad treatment options are available. It is widely considered that continuous measurement of arterial blood pressure (BP) could improve the treatment of hypertension; however, chronically monitoring patient BP remains a significant challenge. In this study, we investigated a novel approach that uses an implantable electrode to generate an artifact signal for predicting arterial BP.Approach.In isoflurane anesthetized rats (n= 10, male), the right common carotid artery was instrumented with a multi-contact cuff electrode to acquire the artifact signal-termed the electro-vascular-gram (EVG) and the contralateral common carotid artery was catheterized to measure intra-arterial BP. The EVG signals were processed (e.g. extract Catch22 features) and applied to linear regression, random forest (RF) regressor, and convolutional neural network models to predict systolic and diastolic BP.Main results.Among the various models tested with the EVG data, the RF model + Catch22 features method achieved the highest performance, yielding predicted BP values (error < 5 mmHg) in 82.6%-100% and 84.1%-99.9% of the testing set for systolic and diastolic, respectively. A 5-fold cross-validation demonstrated similar performance by predicting BP values (error < 5 mmHg) in 91.5 ± 0.1% and 92.4 ± 0.1% of testing data for systolic and diastolic, respectively.Significance.This proof-of-concept study supports the feasibility of using an implantable electrode and machine learning models for potentially measuring arterial BP in continuous fashion. Further system development is warranted prior to clinical translation.

Objective.Caffeine is known to induce cerebral vasoconstriction. We used this effect in a pilot ultrasound-based healthy volunteer study to investigate the directionality of response of brain tissue pulsations (BTPs) with changing middle cerebral artery velocity (MCAv) following caffeine ingestion.Approach.BTPs were measured in healthy volunteers using transcranial tissue Doppler (TCTD) ultrasound and MCAv was measured using conventional transcranial Doppler ultrasound. Measurements of blood pressure, heart rate, and end-tidal carbon dioxide (EtCO₂) were also recorded. Data were collected at rest and at multiple timepoints over a 60 min period following ingestion of 250 mg of caffeine.Main results.A multivariate multilevel model identified significant decreases in mean MCAv of -0.17 (-0.21, -0.14) (cm s^-1) min^-1, ΔMCAv of -0.06 (-0.1, -0.04) (cm s^-1) min^-1, and EtCO₂of -0.02 (-0.04, -0.01) mmHg min^-1. Significant increases in mean arterial pressure of 0.21 (0.15, 0.28) mmHg min^-1and bulk BTP amplitude of 0.08 (0.02, 0.14)μm min^-1were observed. These changes confirm the expected physiological effects of caffeine and provide novel evidence of an inverse relationship between MCAv and BTP amplitude, suggesting that these variables respond in opposite directions following a vasoconstrictive challenge.Significance.We hypothesise that increased bulk BTP amplitude reflects a reduction in intracranial pressure (ICP), driven by caffeine-induced cerebral vasoconstriction, allowing greater brain tissue mobility. This interpretation is supported by magnetic resonance imaging studies, which show increased brain tissue motion with lowered ICP. Measurement of BTPs may provide real-time information on intracranial haemodynamics.

Objective.Monitoring of intracranial pressure (ICP) in a clinical environment is critically important to the stability of patients with various acute neurological illnesses and injury including ischemic stroke, hemorrhagic stroke, brain tumor, and traumatic brain injury. This is because changes in ICP can cause significant stress on the brain and surrounding tissue through complications such as cerebral ischemia or hemorrhage in the surrounding area. Most ICP measurement techniques are invasive, expensive, and have poor spatial resolution. There has been some preliminary evidence to suggest that regional oxygen saturation (rSO₂) measured non-invasively by near-infrared spectroscopy (NIRS) has a statistical link to invasively obtained ICP. Given the limited exploration of this potential link, this scoping review (ScR) aims to investigate the current body of literature exploring the association between cerebral NIRS measurements and ICP.Approach.A comprehensive investigation was conducted across six major databases, with accordance to the preferred reporting items for systematic reviews and meta-analyzes guidelines, in order to evaluate the primary question of: What is the relationship between NIRS-derived cerebral signals and ICP?.Main results. The search process identified 3791 distinct articles. After screening based on the predefined criteria, 10 studies were deemed eligible for inclusion. An additional two studies were identified by screening the citation lists of the included studies. Overall, the collection of articles selected for this systematic ScR indicates a potential positive correlation between some cerebral NIRS variables and ICP; however, significant discrepancies and significant limitations exist in the literature.Significance.This review identifies a significant knowledge gap in the current understanding of how non-invasive NIRS metrics relate to ICP and highlights the importance of conducting additional experimentation in the field.

Objective. Hemodynamic monitoring is essential in preclinical research. Currently available techniques are either invasive or complex to implement. Inductive plethysmography (IP) provides an alternative for estimating stroke volume and cardiac output, as the IP signal includes ventilatory and cardiogenic oscillations (COS). COS monitoring, also defined as thoracocardiography (TCG), has been validated in humans and large laboratory animals. A recent study demonstrated proof of concept in COS extraction from the TCG signal recorded during respiratory pauses in mechanically-ventilated laboratory rats using a high-resolution IP device. The present study aims to develop an ensemble averaging (EA) algorithm, triggered by the electrocardiogram (ECG)R-peak, to extract COS from TCG signals in rats and continuously estimate stroke volume and cardiac output.Approach. After an evaluation of the IP device using the EA technique on a mechanical test bench, the applicability of the EA technique was tested in anesthetized rats without ventilatory support during a pharmacological challenge. The ability of the algorithm to track stroke volume and cardiac output changes during the hemodynamic test was also evaluated.Main results. Metrological evaluation of the IP device using the EA technique demonstrated linearity across the physiological operating range and resolution sufficient to detect volume changes of less than 10% of typical physiological values. Although the assumptions underlying the use of EA cannot be fully satisfied for COS extraction-due to quasi-synchrony with the ECGR-peak and signal non-stationarities-the method enabled extraction of satisfactory average COS waveforms, from which the system reliably captured positive and negative inotropic effects consistent with reference measurements during the pharmacological protocol.Significance. The evaluated algorithm demonstrates advancement over previous studies by enabling hemodynamic monitoring under usage conditions. Further studies are needed to extend its applicability to complex and physiologically relevant scenarios, positioning this technology as a potential non-invasive tool for preclinical research.

Objective. sleep staging is essential for diagnosing sleep disorders and managing sleep health. Traditional methods require time-consuming manual scoring. Recent photoplethysmography (PPG)-based deep learning models perform well on local datasets but struggle with external generalization due to data drift.Approach. this study evaluates multi-source domain training for improving out-of-distribution generalization in four-class sleep staging (wake, light, deep, rapid eye movement) from raw PPG time-series. The trained deep learning model is denoted SleepPPG-Net2. Additionally, we examined the impact of demographic factors, ethnicity, and obstructive sleep apnea (OSA) on performance. SleepPPG-Net2 was benchmarked against two state-of-the-art models.Main results. SleepPPG-Net2 outperformed benchmark models, improving generalization performance (Cohen's kappa) by up to 21%. Performance disparities were observed in relation to age, sex, and OSA severity.Significance. SleepPPG-Net2 enhances PPG-based sleep staging and provides insights into demographic and clinical influences on model performance.

Objective. Pulse arrival time (PAT) is known to be correlated with blood pressure. Although PAT can be measured using electrocardiography (ECG), photoplethysmography (PPG), and other signals commonly available in clinical settings, recent literature has noted that devices recording these waveforms are often subject to many hardware-specific factors related to digital filtering, clock synchronization, temporal resolution, and latency. These factors can introduce relative timing errors between the ECG and PPG signals, resulting in a situation where traditional approaches for PAT measurement will not work as intended.Approach. In this work, we propose a methodology that accounts for these confounding factors and generates precise measurements of PAT using standard bedside monitoring equipment. This technique involves using heart rate variability to match heartbeats across waveforms and experimentally profiling the timing systems of bedside medical devices to correct various timing-related artifacts. To improve the precision of the resulting PAT measurements, we model temporal uncertainties stemming from the finite temporal resolution of the waveform samples.Main results. We apply this approach to a dataset comprising approximately 1.6 million hours of continuous ECG and PPG data from over 10 000 unique patients in a pediatric intensive care unit. After demonstrating that the observed timing artifacts are consistent across the entire dataset, we show that accounting for them results in more reasonable distributions of PAT measurements across age groups.Significance. It is our hope that this work will spur discussion around the standardization of PAT measurement using routinely collected signals in a clinical environment.

Objective: To develop a comprehensive physiological dataset for assessing internal and external stress and to propose robust automated stress recognition methods based on photoplethysmographic (PPG) signals. Approach. We established the Internal and External Stress Dataset (IESD), comprising PPG signals from 107 participants subjected to four distinct stress-inducing paradigms. Exploratory analyses revealed significant differences in heart rate variability (HRV) across these paradigms, underscoring the necessity for advanced methods capable of differentiating various stress types. To address this, we introduced a transfer learning-based inter-paradigm stress recognition model utilizing a Domain Adversarial Neural Network (DANN) combined with Maximum Mean Discrepancy (MMD) for robust feature extraction. Main results. Analysis identified significant differences between internal and external stress, as well as among different external paradigms. Our proposed model demonstrated superior accuracy in recognizing homologous stress compared to heterologous stress within the same target domain, achieving accuracies of 73.86% (TSST to ST) and 60.41% (TSST to VWT). Moreover, the deep feature extraction significantly improved recognition performance and robustness across both intra- and inter-paradigm contexts. Significance. This study provides a valuable dataset and advanced methodology to enhance automated stress detection capabilities, effectively differentiating internal and external stress. The application of deep learning significantly improves recognition accuracy, offering promising prospects for future research and practical applications in stress monitoring.