Physiological measurement最新文献

Objective.Electrocardiogram (ECG) analysis is vital for the diagnosis of cardiac conditions and monitoring human physiological states. However, challenges such as signal perturbations, inconsistent quality, and signal inference undermine the reliability of ECG analysis. Despite advances in large language models (LLMs), their application in enhancing ECG-based physiological measurements remains underexplored. To address these challenges, the objective is to develop a novel multimodal framework that integrates ECG signals with textual instructions for robust denoising and signal quality assessment, enabling effective physiological analysis across diverse tasks.Approach.We propose cross-modal attention (CMA)-ECG, a multimodal framework that employs a hybrid cross-attention mechanism to align ECG and text features with task-specific heads, combined with a pre-trained LLM for contextual enhancement. The framework leverages pretrained LLMs with 7B parameters, balancing accuracy and computational requirements for practical deployment.Main results.Extensive experiments on multiple datasets demonstrate that CMA-ECG achieves state-of-the-art (SOTA) performance in robustness to perturbations, quality assessment, and denoising. CMA-ECG achieves up to 8.8% higher area under the ROC curve in quality assessment and 20% lower mean squared error in denoising compared to SOTA baselines, ensuring reliable ECG processing.Significance.This approach advances ECG analysis by integrating signal and contextual data, offering a robust solution for physiological monitoring and analysis, ensuring reliable ECG processing.

Objective. This exploratory study investigates cyclical changes in physiological features across the menstrual cycle in women with epilepsy, focusing on their potential relationship with seizure occurrence.Approach. Nocturnal data during sleep were collected from two women with ovulatory cycles and compared with data from healthy controls, two non-ovulatory women, one postmenopausal woman, and two male patients. The aim was to characterize signal patterns across different reproductive states and to explore whether menstrual-related rhythms correspond to seizure timing. Circular statistics mapped signals onto an angular scale, allowing identification of biphasic patterns linked to ovulation, while machine learning algorithms identified ovulatory phases.Main Results. In ovulatory participants, seizure activity predominantly occurred around the late luteal and early follicular phases (p < 0.05), and non-uniform and biphaisc trends were observed in temperature, resembling patterns in healthy participants. In contrast, individuals taking enzyme-inducing antiepileptic drugs showed disrupted physiological rhythms. Although hormonal fluctuations appear to drive cyclical patterns, additional rhythms (e.g. weekly) were also observed, suggesting multifactorial influences.Significance. These preliminary findings underscore the need to account for menstrual and other biological cycles in seizure forecasting models and provide a foundation for future studies involving larger cohorts.

Objective.Sodium (Na) overconsumption has been associated with hypertension risk and progression. Human soft tissue and bone are recognized as quickly and slowly exchangeable compartments for sodium storage. How such a distribution regulates blood pressure remains unknown. This study performedin vivoNa measurements on human subjects who underwent dietary intervention, utilizing a compact neutron generator-based neutron activation analysis system. It aimed to evaluate the performance of this innovative system for body Na assessment.Approach. Participants were provided with low and high sodium diets. Baseline measurements were taken before each intervention feeding period, and follow-up measurements were conducted afterwards. The human hands were irradiated for 20 min, followed by 2 cycles of Na gamma ray collection. A biokinetic model was used to calculate sodium concentrations in soft tissue and bone, reflecting sodium accumulation in the two compartments.Main results. For soft tissue, Na levels after low Na diet decreased from baseline in half of the subjects, with reductions ranging from 8% to 55%. The other half of participants exhibited relatively stable Na content. Among participants consuming high Na diet, all participants had elevated Na in soft tissue compared to those on low Na diet. By contrast, Na in bone showed no significant changes from baseline and follow-up for either dietary intervention. Bone Na concentrations ranged from approximately 1000-2000 ppm.Significance. For the first time, Na in soft tissue and bone was measured in humans using neutron activation analysis in response to dietary interventions. This study demonstrates thatin vivoneutron activation analysis can be used to measure Na concentration in both soft tissue and bone. It successfully detects Na alteration in soft tissue and explores the biokinetics of Na retention following dietary interventions. Measuring soft tissue and bone sodium content is a potentially useful approach to study diet and disease links affected by sodium.

Objective.Accurate and non-invasive estimation of core body temperature (CBT) is essential for preventing heat-related illnesses during physical activity and thermal stress. The objective of this work is to develop and evaluate a framework for real-time CBT estimation using only heart rate (HR) data, enabling a lightweight solution suitable for deployment on wearable devices.Approach.We propose a multi-model Kalman filtering (KF) framework with variance-based fusion. Two variants were developed: a supervised Physiological State-Specific KF (PSSK) that uses activity labels (rest, exercise, recovery) to train distinct models, and an unsupervised trial clustering-based KF (TCBK) that clusters trials based on HR-CBT features to capture latent physiological variability without state annotations. Both models were evaluated on two independent datasets and compared against baseline methods.Main results.In within-dataset evaluations, TCBK achieved the highest accuracy with a root mean square error (RMSE) of 0.38∘C (Dataset 1) and 0.41∘C (Dataset 2). In cross-dataset generalization, PSSK demonstrated superior robustness with an RMSE of 0.88∘C, whereas the TCBK model's error increased to 1.56∘C. Both proposed models outperformed the established Buller and Falcone models.Significance.This work demonstrates that lightweight, HR-only models can provide accurate CBT estimation by incorporating state- or context-aware modeling. The framework offers a practical and deployable solution for continuous thermal strain monitoring in occupational and athletic settings, providing a balance between performance and real-world applicability for wearable technology.

Introduction.Neurovascular coupling (NVC) represents multiple mechanisms that adapt cerebral blood flow to neural activity. This study hypothesized that two NVC paradigms active hand movement (AHM) and active elbow flexion (AEF) would elicit similar hemodynamic responses.Methods.Seventeen healthy subjects (9 females, mean age: 34 ± 3 years) performed both motor paradigms. Each session began with a 1.5 min rest (baseline), followed by 1 min of motor paradigm (T1), and a 1.5 min recovery (T2). Transcranial Doppler was used to monitor cerebral blood velocity (CBv) in middle cerebral artery. Arterial blood pressure (ABP), heart rate (HR), and end-tidal CO₂(ETCO₂) were continuously monitored. Data were analyzed using two-way repeated measures ANOVA (p< 0.05).Results.Both AEF and AHM elicited significant increases in CBv over time (p< 0.05), with similar temporal profiles between paradigms. For AEF, CBv in the dominant hemisphere increased from 100% ± 1 at baseline to 104% ± 4 at T1 (p< 0.05) and returned to 98% ± 4 at T2. Similarly, AHM increased CBv from 100% ± 1 at baseline to 105% ± 6 at T1 (p< 0.05) and 98% ± 4 at T2. Significant reductions in cerebrovascular resistance and critical closing pressure were observed at T1 compared to baseline, followed by an increase at T2 (p< 0.05). HR showed significant changes, while resistance area product, ABP, and ETCO₂remained stable throughout the experiment.Conclusion.AHM produced hemodynamic responses comparable to AEF, with an increase in CBv through vasodilation via non-myogenic responses. In this study we demonstrated that the maneuver is a valid alternative to AEF in NVC studies.

Objective.Wrist-worn photoplethysmography (PPG) enables scalable, long-term unobtrusive sleep monitoring through the expression of sympathetic and parasympathetic activity in heart rate variability. However, interindividual differences in the sympatho-vagal balance may inherently limited general PPG-based sleep staging models. This study investigates whether learning individual autonomic representations through model personalization can improve PPG-based automated sleep staging performance.Approach.Concurrent wrist-worn PPG and wearable electroencephalography (EEG) were collected during home monitoring for up to seven nights in a heterogeneous sleep-disordered population (n= 59). Personalization was performed through finetuning (i.e. partial retraining) a general PPG-based model by coupling the subject-specific PPG data with the wearable EEG stage classifications. Performance of the general and personalized models were compared on PPG acquired during a gold-standard clinical polysomnography, testing their agreement on 4-stage classification (W/N1+N2/N3/REM) with the manual scoring.Main result.Overall performance increased in 82.5% of the subjects, with significantly improved performance reached when personalizing the model on three or more training nights. Performance increased with personalization on additional training nights for each stage: wake (β= .005,p< .001), N1+N2 (β= .003,p< .001), N3 (β= .004,p< .001), and REM (β= .005,p< .001). Effects were strongest for younger individuals (β= .009,p< .001) and patients with insomnia (β= .011,p< .001). Personalization greatly impacted the derived sleep macrostructural sleep parameters, with considerable improvement in N3 sleep classification, and in capturing rapid eye movement (REM) sleep fragmentation.Significance.Personalization can overcome one-size-fits-all limitations of a general model and should be considered for PPG-based sleep staging when an altered autonomic modulation is expected that deviates from the general model's global representation.

Objective.To evaluate the feasibility of seismocardiography (SCG)-based estimation of hemodynamic parameters during submaximal cycle ergometer exercise across different body mass index (BMI) groups.Approach.Sixty healthy adults (n= 15 per BMI group: underweight, normal weight, overweight, obese) performed a YMCA submaximal cycling test while SCG signals were recorded using a chest-mounted accelerometer. Transthoracic bioimpedance (PhysioFlow) served as reference. Time-domain features from tri-axial SCG signals were used in subject-specific random forest regressors to estimate stroke volume (SV), heart rate (HR), cardiac output (CO), and cardiac index. Performance was evaluated across baseline, exercise, and post-exercise phases using the mean absolute percentage error (MAPE) and coefficient of determination (R²).Main results.While SCG signals were successfully acquired across all phases, estimation performance varied significantly by physiological state. Models achieved MAPEs below 8% for all parameters overall. However, model reliability was condition-dependent, with optimal performance during post-exercise recovery (medianR²= 0.75 for HR and CO; 0.42 for SV) with reduced reliability during active cycling. SCG features demonstrated limited sensitivity to BMI variations compared to reference hemodynamic parameters, which may limit personalized estimation accuracy across diverse body compositions.Significance.SCG acquisition is technically viable during exercise, but reliable hemodynamic estimation under high-motion conditions remains limited due to motion artifacts and physiological variability. Post-exercise recovery provides optimal conditions for SCG-based monitoring. SCG shows promise as a lightweight approach for cardiovascular assessment in recovery or low-motion scenarios rather than during active exercise. Further validation using gold-standard methods is warranted.

Objective. Biological signals can be used to record sleep activities and can be used to identify sleep disorders. Insomnia is a sleep disorder that can be detected using supervised learning models developed using biological signal analysis. The baseline insomnia detection models segmented input signals based on various sleep stages, in which an imbalance in classes of the different subsets was visible.Approach. Leaning on sleep annotations for training data generation can overcome using electroencephalogram (EEG) augmentation, which trains the machine learning model based on the diverse nature of input EEG. The proposed work aims to generate a heterogeneity in the decomposed frequencies of EEG data using sub-band augmentation. The presented approach imposes the characteristics of various EEG frequencies when developing new data.Results. An excellent classification accuracy of 0.91, 0.90, and 0.866 can be visible in sub-band augmentation using signal scaling followed by noise addition and sliding window, respectively. An ensemble-bagged decision tree (EBDT) classifier was employed in developing the identification model incorporating all the sub-band augmentations with a significant accuracy of 0.986, a sensitivity of 1.0, and a specificity of 0.97. The proposed model also examines the features from smaller time segments of EEG in developing the training data for EBDT and shows an accuracy, sensitivity, and specificity corresponding to 0.97, 0.95, and 1.0.Significance. The presented model is simple, independent of supplementary data like sleep annotations describing sleep stages, and more suitable for disease detection bearing small datasets in training-data enhancement for classification.

Objective. The accurate assessment of cognitive impairment plays a vital role in more targeted treatments for Dementia. Eye movement analysis is a non-invasive and objective method that offers fine-grained insight into cognitive functioning, complementing conventional screening tools. However, single-task eye-tracking paradigms and simplistic analysis methods limit the potential for comprehensive and fine-grained assessment of cognitive impairment. To address this limitation, we propose a multilevel saccade paradigm combined with differential analysis and an attention-based neural network to enhance eye-tracking-based cognitive impairment assessment.Approach. Firstly, a set of saccade-based paradigms with graded difficulty levels is developed, including prosaccade, antisaccade, and random pro-/antisaccade paradigms. Each paradigm incorporates eye movement assessments in both horizontal and vertical directions. Secondly, we recruit 90 subjects for eye-tracking assessments to build a large-scale dataset. The subjects consisted of 36 healthy young controls, 15 healthy elderly controls, 23 individuals with mild cognitive impairment, and 16 individuals with dementia. Each subject completed the Montreal Cognitive Assessment (MoCA). Third, the Mann-WhitneyUtest is employed to identify eye movement features that show significant differences across the four groups. Correlation analysis with MoCA scores further validated the effectiveness of these eye movement features in distinguishing cognitive impairment. Finally, XGBoost is employed to perform classification and to validate the effectiveness of the eye movement feature selection scheme derived from the difficulty-graded saccade paradigms. An attention-based neural network is also integrated to enhance classification accuracy and improve feature selection by identifying the most informative eye movement features.Main results. The model achieved an area under the receiver operating characteristic curve of 0.94, a classification accuracy of 0.80, and a Matthews correlation coefficient of 0.73. Among all features extracted from the different saccade paradigms, the time to first correct AOI and saccade latency parameters from the random pro-antisaccade paradigm demonstrate the highest contribution to classification performance.Significance. By integrating graded saccade paradigms with statistical analysis and attention neural network, this study enhances the granularity and accuracy of eye-tracking-based cognitive assessment, offering a scalable and non-invasive tool for early detection and monitoring of cognitive decline.