Physiological measurement最新文献

{"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}

{"title":"Assessment of cardiopulmonary physiological modulation using multilayer visibility graph analysis of ECG and respiration signals.","authors":"Raghuwansh Singh, Rohit Sane, Vivek Ranjan, Anindita Ganguly, Suman Halder","doi":"10.1088/1361-6579/ae8efd","DOIUrl":"10.1088/1361-6579/ae8efd","url":null,"abstract":"<p><p><i>Objective.</i>This study aimed to quantify cardiopulmonary physiological modulation in patients with hypertension (HTN) and ischaemic heart disease (IHD) using electrocardiogram (ECG) and respiration signals recorded before and after a 7 d Panchakarma-based integrative residential programme.<i>Approach.</i>Simultaneous 10 min ECG and respiration recordings were acquired before and after the programme. A predefined signal-quality pipeline was applied before graph construction. ECG-derived cardiac dynamics were based on normal-to-normal (NN) intervals after artefact and ectopy screening, while respiration cycles were screened for physiologically plausible breath intervals. From each acceptable recording, a clean 300 s segment was selected. NN-derived heart rate (HR) and respiration-rate series were interpolated to a common 4 Hz time base, detrended and standardised. Natural visibility graphs (VGs), weighted VGs and a two-layer multilayer VG (MLVG) were then constructed using synchronous HR-respiration interlayer coupling. Graph index complexity (GIC), average path length, assortativity and pulse-respiration quotient PRQ-derived features were analysed using paired Wilcoxon signed-rank tests with Hodges-Lehmann paired differences and false discovery rate correction.<i>Main results.</i>After quality control, alignment and graph-eligibility screening, paired graph-feature analysis included 20 HTN and 26 IHD subjects. The alignment procedure produced complete HR-respiration time series with negligible missing fractions. Post-program recordings showed measurable cardiopulmonary modulation. In HTN, PRQ decreased with false-discovery-rate-supported significance, while weighted GIC features showed descriptive post-program increases. In IHD, unweighted respiration-VG and MLVG GIC increased descriptively, whereas weighted and path-based metrics showed heterogeneous changes. Interlayer surrogate validation further quantified whether identity-coupled MLVG complexity exceeded shifted-coupling null networks.<i>Significance.</i>The proposed framework provides a reproducible ECG-respiration network-physiology workflow combining NN-based quality control, respiration-cycle screening, common-time-base alignment, unimodal and multilayer VG modelling, PRQ analysis and surrogate validation. The findings support objective quantification of post-program cardiopulmonary modulation while avoiding causal attribution to Panchakarma alone.</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":"148562483","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":"Continuous fast tracking of auditory threshold during middle ear surgery using the auditory steady state response (ASSR).","authors":"Robert B Patuzzi, Alison M Cook, Michael J Bergin, Philip A Bird","doi":"10.1088/1361-6579/ae9032","DOIUrl":"10.1088/1361-6579/ae9032","url":null,"abstract":"<p><p><i>Objective</i>To continuously track auditory threshold during middle ear surgery, using the auditory brainstem response (ABR) as an indirect measure of cochlear sensitivity, thereby providing surgeons with timely feedback to help avoid iatrogenic hearing loss.<i>Approach</i>We improved the signal-to-noise ratio of the electrophysiological measurement of ABRs to repetitive bone-conducted chirps (logarithmic up-chirps from 2 kHz to 16 kHz, with 5 ms duration at 80 s^-1). This was achieved using optimised electrode type and placement, improved bone conductor and bio-amplifier design, and a streamlined placement and retention of the electrodes and bone conductor with an over-the-head elastic strap. We masked the contralateral ear's response with wideband noise to ensure responses were from the operated ear only. Using custom-written software, we automatically adjusted chirp intensity to maintain the brainstem's auditory steady state response (ASSR) near a fixed amplitude ('the ASSR target'), set to an amplitude just above our system's measurement noise floor. The chirp intensity required to maintain this target amplitude was defined as the patient's 'ASSR threshold'.<i>Main results</i>Our improvements allowed us to rapidly track hearing threshold continuously for the entire duration of middle ear surgery in fully anaesthetised patients, with the ASSR threshold initially within 10 dB of psychoacoustic threshold just before surgery. The system can track threshold changes rapidly, but can be limited by background acoustic masking noise in the operating room.<i>Significance</i>Our system could provide surgeons with a rapid and sensitive display of cochlear sensitivity during middle ear procedures, and help identify and possibly avoid traumatic manipulations that cause iatrogenic hearing loss.</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":"148584551","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":"Real-time personalized hemodynamic responses to enhanced external counterpulsation therapy in post-PCI patients using a multidimensional 0/1D-3D model.","authors":"Zhibo Wang, Xuanhao Xu, Qi Zhang, Xue Jia, Ling Lin, Liling Hao, Lin Qi, Guifu Wu, Shuai Tian","doi":"10.1088/1361-6579/ae87f0","DOIUrl":"10.1088/1361-6579/ae87f0","url":null,"abstract":"<p><p><i>Background and objective.</i>Enhanced external counterpulsation (EECP) has shown promise in facilitating postoperative recovery in patients after percutaneous coronary intervention by improving the hemodynamic environment within the stents. However, understanding of the hemodynamic environment across patient profiles, encompassing geometric features of the stent (e.g., length, diameter, and curvature) and patient demographics (e.g., height, age, and weight), has yet to be fully elucidated.<i>Methods.</i>A multidimensional 0/1D-3D coupled model was developed using clinical data from 18 subjects. This model integrated a 0/1D model for assessing the blood perfusion and pressure in coronary arteries with a 3D model to predict the intricate in-stent hemodynamic environment.<i>Results.</i>The simulation results showed increases in time-averaged wall shear stress (TAWSS), transverse wall shear stress, and oscillatory shear index and a decrease in relative residual time under the effect of EECP. Moreover, TAWSS consistently decreased with increasing length and stent diameter while decreasing with increasing stent curvature.<i>Conclusions.</i>A surrogate model based on polynomial chaos expansion, which provides valuable tools for expedited clinical decision-making, was developed from the numerical results for TAWSS enhancement ratio. This model incorporated both the physiological characteristics of the subjects and the geometric features of the stent.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148412544","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":"Simplified grading scale for IR breast thermography using as a first-line component of a multi-imaging breast cancer detection strategy.","authors":"G Chernov, E Martín-Del-Campo-Mena, M Barboza-Flores, A Angulo-Molina, V Chernov","doi":"10.1088/1361-6579/ae8b6f","DOIUrl":"10.1088/1361-6579/ae8b6f","url":null,"abstract":"<p><p><i>Objective.</i>In this study, we propose a simplified, objective grading scale (mild, moderate, or severe) for infrared breast thermography, intended as a first-line component of a multi-imaging breast cancer detection strategy. The goal was to provide a repeatable, automated alternative to traditional scales, such as the Ville Marie scale, which rely on subjective vascular assessments.<i>Approach.</i>Thermal images of the anterior view of the breasts from 246 asymptomatic volunteers and 54 women with biopsy-confirmed breast cancer were analyzed. Five distinct areas of interest were identified and segmented: the nipples and areolas, the breast tissue, the axillary tails, the axillas, and the submammary region. Breast hyperthermia, which is the difference between the maximal temperature of one breast (without the nipple and areola) and the mean temperature of the contralateral breast, was calculated. To minimize physiological and environmental variability, temperature differences relative to the body surface temperature were calculated. Abnormality and asymmetry levels were quantified using empirical<i>z</i>-scores. To evaluate the global abnormality and asymmetry grading levels of the thermal images, Mahalanobis distances were calculated to assess the joint probability of six thermal variables against an empirical 6-dimensional normal distribution.<i>Main results.</i>Utilizing relative temperatures reduced variability from 1.0 °C - 1.5 °C to 0.4 °C - 0.9 °C compared to absolute measurements for images of asymptomatic women. While the axillary and submammary regions showed no correlation with the presence of cancer, the nipple with areola, breast regions, and breast hyperthermia exhibited significant differences in cases with confirmed cancer. Based on the maximum severity rule, 64.8% of women with cancer presented moderate or severe abnormality grades, whereas 94.7% of asymptomatic women fell within the mild-to-moderate range.<i>Significance.</i>The proposed model is fully objective and suitable for automated processing, thereby reducing the dependence on technician experience. It establishes a clear clinical triage protocol: mild cases indicate no thermographic abnormalities, moderate cases require follow-up within several months, and severe cases should be immediately referred for medical evaluation.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148456443","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":"Enhancing the golden hour: classification of traumatic brain injury, severity, and concomitant clinical phenotypes using prehospital continuous physiological data during air transport.","authors":"Matthew R Woodward, Shiming Yang, Mayur Somalinga, Kenneth Dalton, Ryan B Felix, Jamie Podell, Lujie Chen, Gary Schwartzbauer, William Teeter, Doug Floccare, Peter Hu, Neeraj Badjatia","doi":"10.1088/1361-6579/ae8ca7","DOIUrl":"10.1088/1361-6579/ae8ca7","url":null,"abstract":"<p><p><i>Background.</i>During emergency transport, clinical assessment and vital signs (VS) may lack the sensitivity to identify traumatic brain injury (TBI) and identify specific TBI subtypes which may have implications for triaging and timely delivery of life-saving interventions.<i>Objective.</i>To evaluate the ability of machine learning (ML) algorithms to identify the presence of TBI with or without specific important concomitant clinical phenotypes including shock, coagulopathy and polytrauma during air transport to a trauma center.<i>Methods.</i>We identified a cohort of consecutive trauma patients aged 18-65 transported from the scene of injury via helicopter to an urban academic trauma center and collected prehospital clinical data and continuous VSs. We used ElasticNet (regularized regression) and XGBoost (gradient boosting), comparing three variable sets: clinical variables only, continuous physiologic monitoring data only, and combined clinical and physiological data, to develop four predictive models: (1) presence/absence of TBI, (2) mild vs moderate-severe TBI, (3) presence/absence of polytrauma in moderate-severe TBI, (4) presence/absence of coagulopathy in TBI, and (5) presence/absence of shock in TBI.<i>Results.</i>1025 patients (median age 38, interquartile range (IQR): 27-53; 70% male; median Glasgow coma scale 15 (IQR: 13-15) were identified. Across all predictive models, ML algorithms exhibited good predictive discrimination, with area under the receiver operator curve of 0.79 (0.75-0.84), 0.79 (0.74-0.83), 0.89 (0.85-0.92), 0.77 (0.67-0.86), and 0.78 (0.72-0.84) for TBI, TBI severity, polytrauma, coagulopathy, and shock, respectively. Clinical data best predicted TBI severity and polytrauma, while physiologic data improved prediction of shock and coagulopathy.<i>Conclusions.</i>ML algorithms integrating clinical and continuous physiological monitoring can improve identification of TBI and concomitant clinical phenotypes during prehospital transport.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148471960","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":"Multitask learning-based phonocardiogram denoising model for preserving valvular heart disease characteristics.","authors":"Geon Lee, Hangsik Shin","doi":"10.1088/1361-6579/ae8caa","DOIUrl":"10.1088/1361-6579/ae8caa","url":null,"abstract":"<p><p><i>Objective.</i>This study developed a multitask learning (MTL)-based denoising model to reconstruct phonocardiogram (PCG) signals while preserving heart murmur characteristics under both synthetic and diverse real-world clinical noise.<i>Approach.</i>The model was trained to jointly denoise PCG data and classify valvular heart disease (VHD). The original PCG dataset comprised recordings lasting up to 3 s, including normal heart sounds and four VHD classes, with 200 samples per class. To construct inputs, we synthesized contaminated PCGs by mixing synthetic and real-world clinical noise sources and converted them into spectrogram images. The model was evaluated at signal-to-noise ratios (SNRs) of -5, 0, 5, and 10 dB using 5 × 5 nested cross-validation. Denoising performance was measured by the scale-invariant signal-to-distortion ratio (SI-SDR), and VHD classification by accuracy.<i>Main results.</i>Our model outperformed a single-task U-Net denoising baseline; even at a highly contaminated SNR of -5 dB, it achieved an absolute mean SI-SDR of 14.05 dB. For real-world noise, including hospital ambient noise and lung sounds, our model improved SI-SDR by up to 9.69 dB over previous work. For VHD classification, the model exceeded 98.5% accuracy across most conditions at SNRs of 5 and 10 dB, suggesting that heart murmur-specific features were preserved during denoising.<i>Significance.</i>Overall, this MTL-based model demonstrated consistent and robust PCG reconstruction across diverse noise conditions, improving VHD classification on contaminated PCG signals.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148472023","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":"Mean power and surface mechanomyographic responses following fatiguing isotonic muscle actions are unaffected by ischemic preconditioning.","authors":"Sean M Lubiak, Mason A Howard, Jeffrey T Schmidt, Niriham M Shah, Nihar N Patel, Anuj J Prajapati, Emma K Herring, Ethan C Hill","doi":"10.1088/1361-6579/ae8b6e","DOIUrl":"10.1088/1361-6579/ae8b6e","url":null,"abstract":"<p><p><i>Objective.</i>The use of ischemic preconditioning (IPC) may delay the onset of fatigue, however, its impact on mean power (MP) and neuromuscular function remains unclear. The purpose of this investigation was to examine the impact of IPC prior to an acute bout of fatiguing resistance exercise on MP, surface mechanomyography amplitude (sMMG_AMP), and sMMG MP frequency (sMMG_MPF).<i>Approach.</i>Nineteen males randomly completed IPC on separate visits at a low (20 mmHg), moderate individualized (80% of total arterial occlusion pressure), and a supra-systolic absolute (220 mmHg) pressure. Following IPC, participants performed one-set to failure of unilateral (i.e. one leg), isotonic (i.e. constant load), concentric-only leg extensions with a submaximal load (i.e. 30% of one-repetition maximum). MP, sMMG_AMP, and sMMG_MPFwere assessed from concentric peak torque muscle actions performed at an angular velocity of 90°·s^-1prior to and immediately following the bout of exercise. Each dependent variable was analyzed with Bayesian multilevel models (i.e. random intercepts and slopes) and the fixed effects are reported as the mean difference (Mean_diff) and the 95% high-density interval (95% HDI).<i>Main Results.</i>There were no significant interactions or main effects of Condition for any of the dependent variables. Following the one-set to failure, however, MP (Mean_diff= 68.60 ± 1.67 W; 95% HDI: 53.80-83.60), sMMG_AMP(Mean_diff= 0.58 ± 0.04 m·s^-2; 95% HDI: 0.26-0.91), and sMMG_MPF(Mean_diff= 1.35 ± 0.13 Hz; 95% HDI: 0.32-2.39) decreased.<i>Significance.</i>The use of IPC prior to an acute bout of fatiguing resistance exercise did not attenuate the fatigue-induced decreases in MP, sMMG_AMP, or sMMG_MPF. These responses may be attributed to the accumulation of metabolic byproducts, decreases in muscular compliance, and/or alterations in the global firing rate of the unfused activated motor units.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148456498","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":"ECG-image-database: large-scale paired ECG images and time-series with real-world artifacts; a foundation for computerized ECG digitization and analysis.","authors":"Matthew A Reyna, Deepanshi, Audrey T Weigle, Zuzana Koscova, Kiersten Campbell, Kshama Kodthalu Shivashankara, Soheil Saghafi, Sepideh Nikookar, Mohsen Motie-Shirazi, Yashar Kiarashi, Salman Seyedi, Mohammadsina Hassannia, Agnar M Bjørnstad, Elias Stenhede, Arian Ranjbar, Gari D Clifford, Reza Sameni","doi":"10.1088/1361-6579/ae85b2","DOIUrl":"10.1088/1361-6579/ae85b2","url":null,"abstract":"<p><p><i>Objective.</i>We present electrocardiogram (ECG)-Image-Database, comprising ECG image datasets paired with the underlying time-series signals. The database is designed to reflect real-world digitization challenges by incorporating diverse scanning, imaging, and physical artifacts commonly encountered in clinical and archival ECG records. It currently includes ECG images of records from Emory Healthcare (Atlanta, USA), the PTB-XL dataset from Physikalisch-Technische Bundesanstalt (Berlin, Germany), and Akershus University Hospital (Lørenskog, Norway).<i>Approach.</i>ECG images from Emory Healthcare and PTB-XL were generated using ECG-Image-Kit, an open-source toolkit that converts 12-lead ECG time series into realistic printout-style images. The toolkit introduces controlled digital distortions, including noise, wrinkles, stains, and perspective changes. A total of 1977 ECG records (977 PTB-XL and 1000 Emory Healthcare) were processed to create high-fidelity ECG printouts. These images were further subjected to physical degradation-such as soaking, staining, and mold exposure-before being scanned or photographed under varying lighting and capture conditions. In addition, we captured mobile photographs of the original ECG images displayed on computer monitors. This process resulted in 35 595 images. Independently, ECG images from Akershus University Hospital were captured from thermal-paper ECG printouts from 266 patients acquired during routine clinical care. Each printout underwent natural handling degradation and was repeatedly scanned and photographed, yielding 1596 images.<i>Main results.</i>ECG-Image-Database contains 37 191 images derived from 2243 ECG records across three countries. The dataset spans clean scans, noisy photographs, and severe physical deterioration, and includes heterogeneous ECG layouts and acquisition conditions. Each record is linked to its corresponding digital ECG time series, enabling supervised training and benchmarking of digitization and classification methods. Subsets of this resource were used in the PhysioNet Challenge 2024 and a subsequent 2025-2026 Kaggle challenge on ECG image digitization and classification. The database is structured for scalability and future expansion.<i>Significance.</i>By providing paired ECG images and signals across diverse real-world artifact conditions, ECG-Image-Database supports robust development of methods for recovering ECG time series from images and for direct image-based interpretation, helping preserve diagnostic value from non-digital ECG archives.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":"47 7","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13402943/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148593073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-enabled robust regional lung function assessment in mechanically ventilated AECOPD patients using EIT parameters.","authors":"Shuyang Jiang, Liuqing Jiang, Yiyao Chen, Ling Sang, Luping Fang, Zhanqi Zhao, Huiqing Ge, Qing Pan","doi":"10.1088/1361-6579/ae88b5","DOIUrl":"10.1088/1361-6579/ae88b5","url":null,"abstract":"<p><p><i>Objective</i>. Reliable quantification of regional lung function via electrical impedance tomography (EIT) in mechanically ventilated AECOPD patients requires identifying breaths suitable for steady-state regional parameter estimation and excluding breaths deviating from local steady state. However, automated screening remains difficult because existing methods primarily rely on inaccessible raw voltage data or fail to distinguish complex asynchrony patterns in reconstructed images.<i>Approach</i>. We developed an EIT robustness evaluator (EITRE), a spatio-temporal deep learning framework to identify breaths suitable for steady-state regional parameter estimation directly from reconstructed EIT image sequences. The architecture integrates an EfficientNet-b0 spatial encoder with an attention-augmented gated recurrent unit and an XGBoost classifier to capture complex regional impedance dynamics. The framework's performance was evaluated in a multicenter validation protocol using operational reference labels derived from synchronized ventilator waveforms and a statistical deviation rule. The practical utility of EITRE was further demonstrated in a clinical positive end-expiratory pressure (PEEP) titration experiment to evaluate its effect on parameter-derived PEEP recommendations.<i>Main results</i>. Validated on a multi-center dataset comprising 58 AECOPD patients and 140 310 respiratory cycles, EITRE achieved robust cross-domain performance and generalizability (F1-score 0.933 on unseen data following single-subject fine-tuning). Quantitative analysis revealed diverse impacts of patient-ventilator asynchrony (PVA) on EIT parameters: parameters assessing temporal ventilation heterogeneity exhibited higher sensitivity and substantial deviations during PVA, whereas parameters assessing spatial ventilation heterogeneity remained relatively robust. In a PEEP titration experiment, EITRE-based screening produced indicator-and patient-dependent shifts in EIT-derived PEEP recommendations relative to a baseline statistical screening rule, supporting improved measurement consistency for steady-state parameter estimation rather than a uniform population-level correction.<i>Significance</i>. EITRE provides a specialized tool for supporting breath-by-breath measurement consistency for steady-state EIT parameter estimation, enabling more reliable regional lung-function assessment in mechanically ventilated AECOPD patients.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148423156","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}