Physiological measurement最新文献

{"title":"Blood-sweat glucose dynamics during oral glucose tolerance testing: temporal delays, variability, and implications for physiological measurement.","authors":"Karol Kurpiejewski, Maciej Bagiński, Monika Nosowicz, Karolina Piecyk","doi":"10.1088/1361-6579/ae88b6","DOIUrl":"10.1088/1361-6579/ae88b6","url":null,"abstract":"<p><p><i>Objective.</i>Sweat has been proposed as a non-invasive alternative biofluid for glucose monitoring; however, its reliability as a physiological measurement remains unclear because the temporal and quantitative relationship between sweat glucose with blood glucose is not fully understood. This study is aimed at investigate the dynamics of blood and sweat glucose during a standard oral glucose tolerance test (OGTT) in healthy adults.<i>Approach.</i>Thirty-five healthy participants underwent a standard OGTT. Blood glucose was measured using a commercial glucometer, while sweat glucose was quantified via enzymatic colorimetric assay combined with a spectrophotometric analysis. Correlations, blood-to-sweat glucose ratios, and temporal delays between compartments were analyzed.<i>Main results.</i>A moderate positive correlation between fasting blood and fasting sweat glucose was observed after exclusion of outliers (<i>n</i>= 32;<i>r</i>= 0.44,<i>p</i>= 0.005). Peak glucose levels showed weaker associations (<i>n</i>= 35;<i>r</i>= 0.35,<i>p</i>= 0.02), accompanied by substantial inter-individual variability. Blood-to-sweat glucose ratios varied widely (fasting median: 55; post-OGTT median: 38). A pronounced temporal delay between peak blood and sweat glucose was observed, ranging from 10 to 90 min, with 60 min being the most frequent value.<i>Significance.</i>Sweat glucose reflects systemic glucose dynamics in a delayed and highly individualized manner. From a physiological measurement perspective, these findings indicate that sweat glucose cannot be considered a direct surrogate of blood glucose, particularly during dynamic glycemic changes. However, it may provide complementary information under controlled or baseline conditions. The results highlight fundamental limitations and considerations for interpreting sweat-based glucose measurements.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148423159","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":"Anchor-free temporal localization of apnea events from EEG/EOG with state-space models.","authors":"Zahra Elmi, Soheila Elmi","doi":"10.1088/1361-6579/ae8ca8","DOIUrl":"10.1088/1361-6579/ae8ca8","url":null,"abstract":"<p><p><i>Objective.</i>Reduced-channel polysomnography (PSG) and electroencephalography/electrooculography (EEG/EOG) may support obstructive sleep apnea (OSA) screening, but learning-based systems rely on epoch-level classification and generalize poorly across datasets. We introduce ApneaTime, an anchor-free temporal localization framework for apnea/hypopnea boundary estimation from EEG/EOG with auxiliary sleep-stage prediction.<i>Approach.</i>ApneaTime combines multi-resolution time-frequency convolutional encoding, a state-space sequence backbone, and an anchor-free center-offset head for variable-duration events. Self-supervised pretraining, weak supervision, domain-adversarial learning, and contrastive/prototype regularization are used to improve robustness under limited event labels and cohort shift. Evaluation includes event-level localization, subject-level apnea-hypopnea index (AHI) estimation, OSA severity stratification, nightly event-count agreement, calibration, and cross-dataset transfer.<i>Main results.</i>In in-dataset evaluation, ApneaTime improved event1 fromto, mean average precision fromto, and mean intersection-over-union fromtocompared with a CNN+LSTM baseline. Under SHHS-to-MESA transfer, event1 increased fromtoand mean average precision fromto. On the SHHS held-out test set, AHI mean absolute error wasevents/h with a mean bias ofevents/h. Severity stratification achievedaccuracy,macro-1, and weighted, while nightly event-count mean absolute deviation wasevents. Under transfer, AHI mean absolute error wasevents/h and severity accuracy was. Expected calibration error decreased fromfor CNN+LSTM tofor ApneaTime andafter temperature scaling. The model containedmillion parameters and achieved areal-time factor on an NVIDIA Tesla V100 GPU.<i>Significance.</i>ApneaTime supports calibrated, screening-oriented event localization and subject-level burden estimation from reduced-channel EEG/EOG. Limitations include retrospective evaluation on PSG cohorts, dataset-dependent channel availability, no prospective validation against respiratory PSG, and no embedded portable-hardware testing; therefore, the findings do not establish diagnostic or deployment readiness.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148471990","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":"Attention-Enhanced static-dynamic fusion network for major depressive disorder diagnosis.","authors":"Qian Fu, Ling He, Mingyao Gao, Yajing Meng, Changjian Qiu, Qing Li, Jing Zhang","doi":"10.1088/1361-6579/ae8a0f","DOIUrl":"10.1088/1361-6579/ae8a0f","url":null,"abstract":"<p><p><i>Objective</i>. Accurate depression classification using fNIRS signals is critical for objective auxiliary diagnosis, yet many existing methods separately model static characteristics or temporal dynamics, limiting their ability to capture coordinated brain activity.<i>Approach</i>. This study proposes a static-dynamic fusion network for fNIRS-based depression classification that jointly models stable hemodynamic and network properties together with time-varying functional connectivity. A static feature encoder captures global and channel-wise traits, while a dynamic feature encoder employs sequential modeling with attention mechanisms to identify temporally salient neural variations. A channel-aware fusion module is further introduced to adaptively integrate static and dynamic features based on their diagnostic relevance.<i>Main results</i>. Validated on 352 subjects undergoing verbal fluency tasks, static and dynamic feature-fusion network achieved 91.2% accuracy on 90 s signal segments and 81.5% on 160 s segments.<i>Significance</i>. The proposed framework demonstrates improved classification performance over existing methods by explicitly modeling complementary static and dynamic neural features within an interpretable architecture for depression analysis.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148437465","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":"Predicting human metabolic rate based on multiple physiological parameters: a pilot study.","authors":"Huifang Fan, Yujia Wei, Zhongman Ge, Shen Wang","doi":"10.1088/1361-6579/ae9118","DOIUrl":"10.1088/1361-6579/ae9118","url":null,"abstract":"<p><p><i>Objective.</i>Accurate prediction of human metabolic rate (MR) is essential for thermal comfort evaluation. However, traditional static lookup table methods lack adaptability in dynamic scenarios. As a preliminary study, this study aimed to reveal the correlation mechanism between four physiological parameters (heart rate, mean arterial pressure, skin conductance level, and ear temperature) and MR, comparatively analyze the performance of different input parameter combinations constructed by linear regression, support vector regression, and two-layer neural network (TLNN), and ultimately evaluate the effectiveness of the pure physiological parameter-driven model.<i>Approach.</i>We recruited 36 healthy young participants and obtained four physiological parameters under nine different levels of exercise through experiments. After that, we used the analytical method in ISO 8996:2021 to calculate MR as the predicted ground truth, then conducted correlation comparisons based on the training set and verified the effectiveness of multi-parameter combination pathways. The generalization performance of the full-parameter combination models of the three algorithms was evaluated based on the testing set.<i>Main results.</i>Physiological parameters exhibit complementary sex-specific differences and interval-dependent characteristics in reflecting MR, with nonlinear relationships to the observed variable; full-parameter combinations effectively enhance model accuracy. The TLNN model demonstrates superior predictive and generalization performance on the testing set; however, larger-sample studies are warranted to substantiate these findings. Current models, likely constrained by limited sample sizes, yield disproportionately large relative absolute errors under low MR conditions, indicating substantial room for improvement before practical deployment.<i>Significance.</i>This study preliminarily confirmed the effectiveness of a combination of multiple physiological parameters in predicting MR.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148606391","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":"Validity, tolerability, and feasibility of automated arterial occlusion pressure across body positions.","authors":"Jinghui Yang, Taylor Gubler, Elizabeth Kenneally, Caden Cloutier, Erin Duffy, Zach Hamilton, Grace Harty, Nicholas Rolnick, Ben Senra, Drew Martin","doi":"10.1088/1361-6579/ae9034","DOIUrl":"10.1088/1361-6579/ae9034","url":null,"abstract":"<p><p><i>Objective</i>. Accurate arterial occlusion pressure (AOP) measurement is essential for individualized blood flow restriction (BFR) prescription, but no automated BFR device has been validated across the range of body positions commonly used in practice. This study evaluated the validity, tolerability, and feasibility of automated algorithm-based AOP measurement compared to pulsed-wave Doppler ultrasound across supine, seated, and standing positions.<i>Approach</i>. Forty-six healthy adults completed AOP measurements on the dominant lower limb using both automated and Doppler ultrasound methods at three body positions in randomized order. Validity was assessed using intraclass correlation coefficients (ICC), Bland-Altman analysis, and proportional bias testing. Tolerability was evaluated through measurement duration, pain perception (0-10), and adverse event surveillance. Feasibility was assessed by the first-attempt success rate.<i>Main results</i>. The automated method demonstrated good agreement with Doppler ultrasound in supine (ICC = 0.76), seated (ICC = 0.87), and standing (ICC = 0.83) positions. However, 95% limits of agreement ranged from -38 to +48 mmHg across positions, and a significant negative proportional bias was observed in supine (<i>p</i>= 0.031). Automated measurements required significantly longer duration than Doppler across all positions (<i>p</i>< 0.001), while pain perception was comparable between methods. A single participant withdrew during standing automated measurement due to intolerable pain. The first-attempt success rate was significantly lower for automated measurement in standing compared to Doppler (87% vs 100%,<i>p</i>= 0.041) but comparable in supine and seated.<i>Significance</i>. The automated device demonstrates good validity and acceptable tolerability for AOP assessment in healthy young adults during seated and standing positions. Clinicians should consider manual ultrasound verification for supine measurements or when prescribing high-percentage AOP protocols, and provide postural support during standing measurements to improve first-attempt success.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148584851","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 diabetes mellitus classification based on HbA1c using the Mel-frequency cepstral coefficients from the photoplethysmographic signal.","authors":"Surendra Kumar Saini, Sakshi Tiwari, Anil Sharma, Amit Mahesh Joshi, Ravi Kumar Maddila","doi":"10.1088/1361-6579/ae9037","DOIUrl":"10.1088/1361-6579/ae9037","url":null,"abstract":"<p><p>Diabetes mellitus (DM) is a metabolic condition with improper regulation of blood sugar levels and is one of the leading global causes of death. Glycated hemoglobin (HbA1c) serves as a crucial indicator for managing diabetes. This study proposes a noninvasive approach to classify glycemic status based on HbA1c levels. This work uses novel Mel-frequency cepstral coefficient features of finger photoplethysmographic (PPG) signals and physiological parameters, enabling straightforward detection of DM. A finger PPG dataset (in reflective mode) comprising 180 subjects with diabetes, prediabetes, and normal HbA1c levels is curated and used to validate the proposed method. The dataset comprises 93 normal (HbA1c5.7%), 57 prediabetic (HbA1c 5.7%-6.4%), and 30 diabetic (HbA1c6.5%) individuals. Furthermore, a hybrid feature (HyF) selection method is employed for feature reduction. The HyF Selection-based gradient boosting model achieved effective accuracies of 93.89% for binary classification and 91.67% for multiclass classification. The results are compared with the gold standard HbA1c test. Both the binary and multiclass classifications show improved overall performance. These findings indicate that PPG signals are a feasible substitute for noninvasive HbA1c detection and have potential for wearable HbA1c monitoring.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148584896","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":"Assessing cerebral autoregulation impairment via short-time correlation-based markers derived from transcranial Doppler and near-infrared spectroscopy signals during general anesthesia in cardiac surgery.","authors":"Vlasta Bari, Beatrice Cairo, Ilaria Burzo, Miriam Angolani, Martina Anguissola, Marco Ranucci, Giacomo Bortolussi, Alberto Porta","doi":"10.1088/1361-6579/ae8efb","DOIUrl":"10.1088/1361-6579/ae8efb","url":null,"abstract":"<p><p><i>Background</i>. Cerebral autoregulation (CA) is estimated by assessing the association between variations of mean cerebral blood velocity (MCBv) and mean arterial pressure (MAP). Recently, regional oxygen saturation (rSO₂) has been tested as an alternative to MCBv for CA estimation.<i>Objective</i>. We propose a correlation-based method iterating the computation of the Pearson correlation coefficient<i>r</i>over short windows of MAP, MCBv and rSO₂and testing on an individual basis the significance of the positive MCBv-MAP and rSO₂-MAP association.<i>Analysis</i>. The rejection of the null hypothesis of zero or negative correlation was performed using a fast approach based on the classical t-test applied to the Pearson correlation coefficient and via a time-consuming approach based on surrogate series generation. The median of<i>r</i>computed over segments rejecting the null hypothesis and their percentage was computed in 53 patients (age: 62 ± 11 years, 39 males, 14 females) scheduled for cardiac surgery acquired before (BASAL) and after induction of propofol-based general anesthesia (ANESTH). The method was compared to more traditional time-domain techniques.<i>Main results.</i>The percentage of positively correlated sequences and their<i>r</i>decreased during ANESTH and this result was valid regardless of the method utilized to reject the null hypothesis and the use of MCBv or rSO₂. Since markers computed using MCBv and rSO₂were uncorrelated, two approaches might unveil different CA aspects. Only results based on MCBv were significantly correlated with traditional time-domain indexes.<i>Significance.</i>The method should be considered for applications of CA monitoring in practical settings.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148562504","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":"Estimation of deflation parameters as a surrogate for transpulmonary pressure from regional pressure-flow-curves derived from electrical impedance tomography in a porcine model of the acute respiratory distress syndrome.","authors":"Maike Henkel, Paul Frenkel, Fabian Mueller-Graf, Jonas Merz, Chiara Felicitas Schlögel, Susanne Reuter, Brigitte Vollmar, Amelie Zitzmann, Daniel A Reuter, Sven Pulletz, Stephan H Böhm","doi":"10.1088/1361-6579/ae8d7b","DOIUrl":"10.1088/1361-6579/ae8d7b","url":null,"abstract":"<p><p><i>Objective.</i>Adjustment of positive end-expiratory pressure (PEEP) is part of lung-protective ventilation in patients with acute respiratory distress syndrome (ARDS) and can be performed invasively using an esophageal catheter (Talmor<i>et al</i>2008<i>New Engl. J. Med.</i><b>359</b>2095-104). The objective of this proof-of-concept study was to investigate whether the transpulmonary pressure (TPP) of 0 mbar, at which alveolar collapse occurs, can be estimated non-invasively using electrical impedance tomography (EIT).<i>Approach.</i>ARDS was induced in 14 pigs by repeated lung lavage and a 2 h period of ventilator-induced lung injury ventilation. The TPP was calculated as the difference between end-expiratory airway pressure and the corresponding esophageal pressure. During a descending pressure-controlled ramp maneuver from 50 to 0 mbar, pressure-flow curves at the pixel levels of the candidate dependent lung region were generated and regional deflation parameters calculated.<i>Main results.</i>During the descending pressure ramp the beginning of alveolar collapse could be determined at approximately 25 mbar in the dependent region of the EIT images based on regional characteristic points in both lung conditions. A strong correlation was found (<i>r</i>= 0.929,<i>B</i>= 1.005,<i>R</i>²= 0.862,<i>p</i>= 0.007) in healthy lungs and an intermediate correlation (<i>r</i>= 0.817,<i>B</i>= 0.894,<i>R</i>²= 0.668,<i>p</i>= 0.025) in ARDS between the second characteristic point and the PEEP according to Talmor, corresponding to a TPP of 0.<i>Significance.</i>The findings of the study have demonstrated that EIT can identify regional characteristic points that correlate with regional TPP changes in the dependent lung region. This knowledge can be used to optimize a lung protective ventilation strategy by titrating TPP guided PEEP non-invasively.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148536550","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 prognostic value of skin temperature variability analysis in clinical settings: a systematic review of current evidence.","authors":"Eubi Chan, Angelica Blotto, Ali R Mani","doi":"10.1088/1361-6579/ae8efc","DOIUrl":"10.1088/1361-6579/ae8efc","url":null,"abstract":"<p><p><i>Objective.</i>While core body temperature in humans remains relatively stable within a narrow range, peripheral skin temperature fluctuates dynamically. This variability reflects complex interactions between heat loss (e.g. via vasodilation) and heat gain (e.g. through metabolic activity), all modulated by an integrated thermoregulatory network. Emerging evidence suggests that skin temperature variability (STV) may offer insight into the integrity of thermoregulatory, vascular, and autonomic control systems. This systematic review evaluates the prognostic utility of STV as a dynamic physiological marker across diverse clinical settings.<i>Method.</i>The review followed PRISMA guidelines, with comprehensive searches conducted in Ovid MEDLINE, EMBASE, and AMED up to June 2026. Studies examining STV in relation to prognosis were eligible, and methodological quality was assessed using the QualSyst and QUIPS tools. This study used a narrative evidence synthesis guided by a logic model.<i>Results.</i>Of 41 papers screened, 10 met the inclusion criteria. The included studies identified a range of analytic methods used to quantify STV. Overall, the prognostic value of STV appeared to depend on both the timescale of temperature fluctuations and the underlying disease context. In life-threatening conditions such as sepsis, multiple organ failure and decompensated cirrhosis, reduced short-term variability or loss of complexity predicted higher mortality, potentially reflecting severe autonomic or microvascular regulation. At longer timescales, attenuated 24-hour circadian amplitude of temperature time-series in healthy individuals predicted future cardiometabolic diseases, indicating circadian dysregulation associated with increased all-cause mortality risk.<i>Discussion.</i>STV shows promise as a non-invasive physiological marker of prognosis, but current evidence is limited by methodological heterogeneity, small clinical cohorts, and inconsistent confounder control. Standardised measurement protocols, agreed analytical metrics, multicentre validation, and large-scale comparison with established risk scores are needed to enable clinical implementation.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148562488","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 hierarchical multifunctional cross fusion network for emotion recognition from facial expressions and peripheral physiological signals.","authors":"Xiang Zuo, Geng-Xin Xu, Ye Li","doi":"10.1088/1361-6579/ae8b70","DOIUrl":"10.1088/1361-6579/ae8b70","url":null,"abstract":"<p><p><i>Objective.</i>Accurate emotion recognition is essential for enabling adaptive and empathetic human-computer interaction. However, emotion recognition based on a single modality may be affected by modality-specific noise, weak emotional cues, and individual differences. This study aimed to develop a practical non-invasive emotion recognition framework by integrating facial expressions and peripheral physiological signals (PPSs).<i>Approach.</i>We investigated multimodal emotion recognition using facial images and wearable PPSs. To effectively integrate heterogeneous modalities, we proposed a hierarchical multifunctional cross-fusion network (HMCFNet). The framework first performs modality-specific feature refinement to extract emotionally relevant representations from each modality. A joint cross-attention module is then employed to enhance complementary cross-modal information while suppressing redundant or less informative features. Finally, a pyramid-structured deep cross-attention fusion module captures latent emotional representations at multiple feature scales to improve cross-modal feature interaction.<i>Main results.</i>Experimental results on benchmark emotion recognition datasets demonstrated that the proposed HMCFNet achieved superior classification performance compared with several representative methods. The ablation experiments further showed the effectiveness of modality-specific feature refinement, joint cross-attention, and pyramid-structured deep fusion in improving emotion recognition performance.<i>Significance.</i>The proposed framework provides an effective solution for non-invasive multimodal emotion recognition by exploiting complementary information between facial expressions and PPSs. This study may facilitate the development of practical and scalable affective computing systems.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148456415","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}