Physiological measurement最新文献

{"title":"Inpainting for artifact restoration in rPPG signals: a tool for real-world applicability in wellness and driver monitoring systems.","authors":"Félix Nieto-Del-Amor, Jose L Martinez-de-Juan, Gema Prats Boluda, Marc Escrig-Villalonga, Ursula Martinez-Iranzo, Cristina Herrera-Ligero","doi":"10.1088/1361-6579/ae60c1","DOIUrl":"10.1088/1361-6579/ae60c1","url":null,"abstract":"<p><p><i>Objective.</i>Photoplethysmography (PPG) and remote PPG (rPPG) are widely used non-invasive techniques for monitoring cardiovascular parameters. However, signal artifacts from motion, lighting variations, and environmental noise pose significant challenges for accurate physiological measurement, particularly in non-contact rPPG systems. To address these issues, we propose a novel generative inpainting framework designed to restore corrupted segments of PPG and rPPG signals.<i>Approach.</i>Our method leverages a large-scale synthetic dataset that spans a broad range of heart rates (30-180 bpm) and incorporates diverse artifact profiles to simulate real-world conditions. The inpainting model is built upon a custom Wasserstein GAN architecture, using a gradient penalty to ensure stable adversarial training. This selective reconstruction approach targets only the corrupted segments while preserving the integrity of high-quality signal portions.<i>Main results.</i>Results show that the proposed framework improves signal quality compared to corrupted signals. For synthetic datasets spanning heart rates from 30 to 180 bpm, signal-to-noise ratio increases from approximately -0.65 to -0.20 dB to 3.27-4.16 dB after inpainting, while the mean absolute error decreases from 0.08-0.09 to 0.05-0.06. Feature-level similarity also improves, with Fréchet Encoder Distance reduced from 0.12 to 0.03 for real PPG and from 0.07 to 0.01 for real rPPG, and consistent reductions observed across all synthetic heart-rate ranges (from 0.23-0.47 to 0.01-0.04). Heart-rate estimates derived from the reconstructed signals are statistically equivalent to those obtained from clean references.<i>Significance.</i>The proposed generative inpainting framework effectively restores degraded PPG and rPPG signals and preserves heart-rate estimates, supporting its use in non-critical physiological monitoring applications such as wellness monitoring and automotive contexts. Validation on real data was limited to relatively clean, resting-state recordings; further studies are required to assess performance under high-motion and real-world conditions.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147699557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of Guzik's and Porta's indices of heart rate asymmetry.","authors":"Yong-Ping Wang, Guo-Zhi Wang, Yen-Ying Kung, Cheryl C H Yang","doi":"10.1088/1361-6579/ae674d","DOIUrl":"https://doi.org/10.1088/1361-6579/ae674d","url":null,"abstract":"<p><p><i>Objective.</i>Guzik's and Porta's indices of heart rate asymmetry (HRA_GI, HRA_PI) quantify different aspects of R-R interval (RRI) dynamics. Although highly correlated, the two indices are not interchangeable and may provide partially independent information. To enable a direct and interpretable comparison between them, a connecting bridge is required.<i>Approach.</i>To investigate whether a magnitude-based index exists that aligns closely with the number-based HRA_PIand, if so, how this index differs from the magnitude-based HRA_GI, we analyze 5-minute RRI recordings obtained from 24 male and 29 female participants of different ages during spontaneous breathing, as well as from 14 young participants performing controlled breathing at 0.1 Hz and 0.25 Hz. The mean (Md, Ma) and standard deviation (SDd, SDa) of beat-to-beat deceleration and acceleration magnitudes were computed. Wang's index (HRA_WI) was defined as the percentage of Md relative to the sum of Md and Ma, whereas HRA_GIincorporates both the mean and the SD of these magnitudes.<i>Main results.</i>Across all conditions, Bland-Altman plots showed that the differences between HRA_WIand HRA_PI(-0.06 ± 1.01%) exhibited narrower limits of agreement with mean difference close to zero. The slopes of the regression lines for HRA_WIversus HRA_PIdid not differ significantly from the slope of the line of identity. HRA_GIwas significantly greater than HRA_WIduring 0.1-Hz breathing, but not during 0.25-Hz breathing, paralleling increases in both the Md and SDd during slow breathing. At the same time, the ratio SDd/Md was consistently greater than SDa/Ma, in accordance with the mathematical formulations underlying HRA_GIand HRA_WI.<i>Significance.</i>The magnitude-based index HRA_WIclosely matches the number-based HRA_PIacross a range of physiological conditions. Difference between HRA_GIand HRA_WIis primarily determined by disparities in the SD/M ratio of RRI decelerations relative to accelerations.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147819479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The effects of aging on left ventricular diastolic function evaluated with 4D flow MRI: a novel approach using mitral velocity and propagation velocity measurements.","authors":"Luz Valentina Stipechi, Damian Craiem, Umit Gencer, Mariano E Casciaro, Jerome Lamy, Jean-Sébastian Hulot, Emmanuel Messas, Gilles Soulat, Elie Mousseaux","doi":"10.1088/1361-6579/ae674e","DOIUrl":"https://doi.org/10.1088/1361-6579/ae674e","url":null,"abstract":"<p><strong>Objective: </strong>&#xD;Assessing diastolic function (DF) using 4D-Flow MRI may offer valuable physiological insights during left ventricular (LV) filling. We aimed to test DF parameters typically obtained with echocardiography (TTE) but derived from 4D-Flow MRI, including inflow velocity, flow filling rate, and propagation velocity (VP), by characterizing LV diastolic filling associated with aging. &#xD;Approach:&#xD;Sixty healthy volunteers (34 women, 26 men; mean age, 52±18 years; range: 20-80 years) underwent cardiac 4D-Flow MRI and TTE as part of cardiac ageing studies. Early (E) and atrial (A) mitral inflow peak velocities were obtained at the leaflet tips with and without normal projection (E and ALT_PROJ, E and ALT_NON-PROJ). Peak early and atrial filling rates (PEFR, PAFR) were derived from flow curves. VP was calculated mimicking TTE approach (VP_SLOPE) and by taking the slope of a plane fitting the velocity curves on a 3D streamline within the LV (VP_PLANE). Associations between age, velocity-derived indices related to DF and LV geometry were assessed.&#xD;Main results:&#xD;All 4D-Flow velocity parameters were associated with age (p<0.001). E/ALT_NON-PROJ and E/ALT_PROJ ratios correlated with TTE (r=0.69 and r=0.67 respectively, p<0.001). PEFR showed a stronger inverse association with age (r=-0.75, p<0.001) than TTE peak velocities (r=-0.19, p=0.149). VP_PLANE correlated better with age (r=-0.47, p<0.001) than VP_SLOPE (r=-0.26, p<0.05) and with indicators of DF such as E/E'TTE, PEFR/PAFR ratio and PEFR normalized to filling volume. &#xD;Significance:&#xD;Indices derived from 4D-Flow MRI were sensitive to age-related variations in LV filling dynamics, indicating potential for validation in pathological cohorts with confirmed diastolic dysfunction.&#xD.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147819512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perioperative hypoxaemia early warning based on high-frequency waveform fusion and deep learning.","authors":"Chengbo Wang, Wei Chen, Ming Yu, Limin Dong, Bin Liu, Guang Zhang","doi":"10.1088/1361-6579/ae669f","DOIUrl":"https://doi.org/10.1088/1361-6579/ae669f","url":null,"abstract":"<p><strong>Objective: </strong>The accurate prediction of impending intraoperative hypoxaemic events is paramount for patient safety. Current models relying on structural parameters exhibit limitations, including low sampling frequency, weak temporal coherence, and high data attrition rates. Consequently, long-term sequence, high-frequency waveform data are utilised in this study to construct a deep learning-based hypoxaemia prediction model, by which conventional shortcomings are addressed whilst predictive accuracy and robustness are enhanced.&#xD;Approach. Respiratory, blood oxygenation, and electrocardiogram waveforms were extracted from the VitalDB database. Two processing methods were employed: extraction of waveform-derived variables to construct numerical datasets; and utilisation of the Gramian Angular Summation Field (GASF) and the four-quadrant matrix method to construct image-based datasets.Through multiple dataset construction methods, five datasets were constructed. An LSTM algorithm was employed, using a 5-minute learning window and prediction windows ranging from 1 to 13 minutes, to conduct a comprehensive performance evaluation.&#xD;Main results. Optimal performance was achieved by all models within a one-minute prediction window. Superior accuracy (0.932), AUC (0.953), and stability (maximum AUC variance 0.067) were demonstrated by the 'Multimodal image model', whilst the poorest performance was exhibited by the 'Structured only model'. Moreover, compared to singlemodal models, multimodal models incorporating Structured parameters yield only marginal improvements. Consequently, singlemodal data derived solely from raw waveforms are suggested as sufficient for prediction requirements, by which greater application potential is held due to enhanced computational efficiency.&#xD;Significance. This study systematically demonstrated the significant advantages of high-frequency waveform data. Results indicate that waveform processing methods based on the Gramian Angular Summation Field (GASF) and the four-quadrant matrix approach can effectively enhance model stability and performance. Furthermore, the singlemodal model relying solely on waveform data, excluding structured parameters, can meet clinical prediction requirements while reducing computational costs. This study provides novel data structures and methodologies for perioperative hypoxaemia prediction.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147778064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic sleep staging from CPAP airflow using a dual fusion multi-period convolutional neural network.","authors":"Hsin-Yu Chen, Muneeb Ahsan, Andrey V Zinchuk, Aatif Husain, Henry K Yaggi, Hau-Tieng Wu, Cheng-Yao Chen","doi":"10.1088/1361-6579/ae60df","DOIUrl":"10.1088/1361-6579/ae60df","url":null,"abstract":"<p><p><i>Background</i>: Continuous positive airway pressure (CPAP) therapy is the standard treatment for obstructive sleep apnea-hypopnea syndrome, yet its use as a passive sleep dynamics monitoring remains limited. CPAP devices record only airflow signals, called CPAP-flow, which constantly interact with the pressure delivered by the device. This interaction renders the signal vulnerable to device-related artifacts and inter-/intra-patient variability, posing significant challenges to its repurposing for monitoring sleep dynamics.<i>Methods</i>: Motivated by neural network-based studies of sleep-wake transition from CPAP-flow, we leverage existing physiological knowledge and introduce a<i>dual fusion multi-period convolutional neural network (DFMP-CNN)</i>model. This deep learning architecture leverages multiple period-specific convolutional kernels and a dual-fusion mechanism to jointly encode known short- and long-range temporal dependencies in CPAP-flow, overcoming limitations of traditional fixed-scale models.<i>Results</i>: Extensive experiments demonstrate that DFMP-CNN achieves state-of-the-art performance in CPAP-based sleep staging. On the Yale dataset, it achieves 78.5% accuracy (Cohen's<i>κ</i> = 0.605), with a best case of<i>κ</i> = 0.886; on the Duke dataset, it reaches 73.6% accuracy (<i>κ</i> = 0.524), with a best case of<i>κ</i> = 0.805. Cross-dataset evaluations confirm the model's transferability across clinical centers and device types, while feature and fusion ablation studies highlight its robustness.<i>Conclusions</i>: DFMP-CNN provides an unobtrusive approach for sleep monitoring using CPAP devices, providing a dual-purpose platform for therapy and longitudinal assessment. Significance: the robust performance of DFMP-CNN across datasets and device types underscores its potential to improve clinical assessment and optimize therapy management.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147699512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parameterized inversion of electrical impedance tomography with sparse and dense case sampling.","authors":"Jessie M Sheflin, Sankalp K Ganeshan, Amadou Bah, Claire C Onsager, Alan V Sahakian, Martin Bulst, Matthew A Grayson","doi":"10.1088/1361-6579/ae66c6","DOIUrl":"https://doi.org/10.1088/1361-6579/ae66c6","url":null,"abstract":"<p><strong>Objective: </strong>When electrical impedance tomography is applied to a known system, such as the human body, a parameterized model is shown to produce a more accurate reconstruction than a conductivity map. Furthermore, if the number of free parameters is less than the total number of independent measurements, the sensitivity volume method can be employed to identify a significantly reduced number of data measurements with the highest value for distinguishing these parameters.</p><p><strong>Approach: </strong>To achieve direct parametric inversion from this reduced set of measurements, a simple algorithm establishes the correspondence between training data and parameterized model cases. Here two training algorithms will be demonstrated. For sparse sampling, the parameters associated with each trained case are interpolated to generate a high density of invertible data cases. For dense sampling, enough cases are directly measured that a simple nearest-neighbor search in data space can invert the data.</p><p><strong>Main result: </strong>Once the training is established, a simple nearest-neighbor query in data space, has a one-to-one correspondence with the model parameters for reconstruction. Sparse sampling is demonstrated with an insulating cylinder in a saltwater tub whose diameter and angular position constitute a two-dimensional (2D) model space, and whose reduced high-value data space consists of 9 independent tetrapolar data measurements made with 15 available electrodes. Dense sampling is demonstrated with a mechanical goldfish in a saltwater tub whose coordinates and orientation define a 3D model space, and whose reduced high-value data space consists of 16 tetrapolar data measurements made from 128 available electrodes.</p><p><strong>Significance: </strong>The parametric method demonstrated here reduces the necessary number of data meeasurements by orders of magnitude compared to standard EIT to achieve higher accuracy within the parametric representation, and can, in principle, be expanded to complex 3D systems such as organs within the human body to achieve fast, high fidelity parametric reconstructions.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147778129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability of resting-state photoplethysmogram-based pulse rate variability in lifespan samples: Implications for cardiovascular research.","authors":"Xuewei Han, Xi Li, Alexander Volodarskiy, David Slotwiner, Yihong Zhao","doi":"10.1088/1361-6579/ae66c7","DOIUrl":"https://doi.org/10.1088/1361-6579/ae66c7","url":null,"abstract":"<p><strong>Objective: </strong>Pulse rate variability (PRV), derived from photoplethysmography, offers a scalable approach to studying cardiac autonomic regulation. However, the reliability of PRV measures across human lifespan has not been systematically evaluated, limiting their application in cardiovascular research.&#xD;Approach: Pulse wave data of 914 healthy young subjects from the Human Connectome Project (HCP) young adults were analyzed. PRV was derived from four 15-minute resting-state fMRI sessions using NeuroKit2. Test-retest reliability of 86 PRV metrics across time, frequency, and nonlinear domains was assessed using intraclass correlation coefficients (ICCs). Findings were validated in independent developmental (HCP-D; n=536; ages 5-21) and aging (HCP-A; n=652; ages 36-100+) cohorts to evaluate lifespan generalizability. Sex-specific and race-specific analyses were also performed. &#xD;Main Results: We analyzed 914 healthy young adults (mean age 28.7±3.7 years; n=489, 53.5% female), of whom 75.6% self-identified as White, 13.1% as African American, and 11.3% as Other. Of 86 PRV metrics, 62 (72.1%) showed excellent reliability (ICC ≥ 0.75) across both days, with higher stability within-day than across days. Time-domain measures (e.g., Prc80NN, pNN20, MeanNN, MedianNN) and nonlinear measures (e.g., ShanEN, IALS, and PSS) were highly reliable with ICC ≥ 0.90. In the frequency domain, HFn and LFn performed best (ICC ≥ 0.85). The reliability patterns were highly consistent across developing and aging cohorts and did not significantly differ across Sex and race subgroups among highly reliable PRVs.&#xD;Significance: A substantial proportion of PRV metrics showed excellent reliability across the lifespan, with broadly similar patterns across sex and racial groups, supporting their use in research settings.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147778132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Turning glasses into sensors: capacitive facial expression recognition under frame geometry constraints.","authors":"Francesco Latino, Matteo Rossi, Andrea Costanzo Palmisciano, Andrea Farabbi, Athul Krishnan, Niccolò Antonello, Luca T Mainardi, Pietro Cerveri","doi":"10.1088/1361-6579/ae669e","DOIUrl":"https://doi.org/10.1088/1361-6579/ae669e","url":null,"abstract":"<p><strong>Objective: </strong>Wearable facial expression recognition requires sensing modalities that are unobtrusive, illumination-independent, and compatible with everyday eyewear form factors. Existing optical and electromyographic approaches are limited by line-of-sight requirements, skin contact, or restricted Action Unit (AU) coverage. This work investigates the feasibility of non-contact capacitive sensing for facial muscle activity monitoring within the strict geometric constraints of standard eyewear.</p><p><strong>Approach: </strong>We developed FERGlasses, integrating eight loading-mode capacitive channels via a custom flexible PCB and active shielding to detect skin-to-frame displacement. A validation study with 40 participants was conducted to elicit seven Facial Action Coding System (FACS)-defined AUs. Signal fidelity was assessed using independent Random Forest regressors and benchmarked against commercial optical-proximity (OCOsense) and computer-vision (Py-Feat) standards.</p><p><strong>Main results: </strong>The system demonstrated high agreement for upper-face activity, achieving median cosine similarities of 0.97 for the Outer Brow Raiser (AU02) and 0.87 for the Nose Wrinkler (AU09), while lower-face actions such as the Chin Raiser (AU17) yielded a median of 0.33, consistent with mechanical signal attenuation along the frame. Channel-ablation analysis quantified the specific anatomical contributions of each electrode group, identifying eyebrow and rhinion sensors as primary signal drivers for upper-face and perinasal actions, respectively, and temple sensors as critical for cheek raiser detection.</p><p><strong>Significance: </strong>This study provides the first metrological validation of multi-channel capacitive sensing for AU-level recognition in eyewear. The results establish the modality as a robust, privacy-preserving, and illumination-independent alternative to optical methods for longitudinal physiological monitoring, with the current prototype serving as a wired research platform and full consumer-grade integration identified as a future engineering objective.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147778206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Noninvasive left ventricular end-diastolic pressure assessment using a novel workflow and device in primary care settings to enhance heart failure diagnosis.","authors":"Faisal Amlani, Thomas Cheek, Rashid Alavi","doi":"10.1088/1361-6579/ae64a8","DOIUrl":"https://doi.org/10.1088/1361-6579/ae64a8","url":null,"abstract":"<p><strong>Objective: </strong>Heart failure (HF) is underdiagnosed in high-risk patients, motivating the development of screening workflows towards earlier identification. The objective of this study is to evaluate the feasibility and screening yield of a non-provider-based, noninvasive left ventricular end-diastolic pressure (LVEDP) assessment as a marker of HF risk within routine outpatient primary care settings.</p><p><strong>Approach: </strong>A dedicated, screening-only \"heart health clinic\" workflow, using noninvasive estimation of LVEDP and the Kansas City Cardiomyopathy Questionnaire (KCCQ-12), was assessed. Primary care patients at high-risk for HF were contacted directly and scheduled for focused screening visits performed by trained medical assistant \"superusers,\" independent of a provider visit.</p><p><strong>Main results: </strong>Of n = 1 238 patients who arrived for screening, n = 1 141 (92.2%) had conclusive LVEDP estimates. LVEDP was estimated to be elevated (defined as > 18 mmHg) in 40.1% of screened patients, with a higher prevalence in women than men (46.6% vs. 31.9%; p < 0.0001). Age and body mass index were found to be similar between elevated and non-elevated LVEDP groups. Among patients with elevated LVEDP, 426 (93.0%) completed all KCCQ-12 subdomains, with Overall Summary (OS) scores classifying 42.3% as asymptomatic Stage-B HF (KCCQ-OS = 100), 45.1% as New York Heart Association (NYHA) I (KCCQ-OS 80-99), and the rest as NYHA II-IV (KCCQ-OS < 80).</p><p><strong>Significance: </strong>These findings indicate that the overall workflow does not introduce significant bias, supporting the practicality and feasibility of incorporating noninvasive LVEDP assessment into scalable HF risk screening in general outpatient populations.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147778114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A domain adversarial network for small-sample obstructive sleep apnea detection using a single-lead piezoelectric sensor.","authors":"Xuefeng Song, Xiaoxin Lan, Tianyuan Hou, Hongyan Liu, Yuhang Wang, Junye Tong, Siqi Jia, Haibo Yuan, Yi Xin","doi":"10.1088/1361-6579/ae5e17","DOIUrl":"10.1088/1361-6579/ae5e17","url":null,"abstract":"<p><p><i>Objective.</i>In recent years, increasing attention to sleep health has accelerated development of wearable devices for home monitoring. Two critical challenges remain: providing an unobtrusive sensing solution suitable for long-term deployment, and designing algorithms that generalize across diverse users and acoustic environments when annotated data are limited.<i>Approach.</i>We develop a single-lead bone-conduction monitoring system and a distribution-aware detection model. The wearable system uses a piezoelectric sensor at the lateral throat to capture tracheal vibrations for continuous overnight monitoring, which improves user comfort relative to multi-lead polysomnography (PSG). For robust event recognition, we propose the convolutional memory adaptive prototypic network (CMAP), which combines convolutional-recurrent feature extraction with domain-adversarial training and a prototypical constraint to learn domain-invariant representations under limited labels. We evaluated our solution with a cohort of 95 participants undergoing simultaneous PSG and wearable monitoring.<i>Main results.</i>For snore and breath sound event detection during sleep, the model attained precision of 0.90 and recall of 0.93. The estimated Apnea-Hypopnea Index (AHI) from our system correlated strongly with PSG-derived AHI (Pearson<i>r</i>= 0.94,<i>p</i>< 0.001). The model achieved 83.2% accuracy in four-class severity classification across healthy, mild, moderate and severe obstructive sleep apnea (OSA).<i>Significance.</i>These results indicate that a single-sensor, distribution-aware approach can provide a reliable acoustic surrogate for AHI and clinically relevant severity classification. The proposed wearable and CMAP model offer a practical, comfortable, and cost-effective solution for early clinical triaging, scalable home-based OSA screening and longitudinal monitoring with low user burden.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147654863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}