Physiological measurement最新文献

{"title":"Aggregated postpartum cerebral autoregulatory curves in normotensive individuals, preeclampsia with severe features, and superimposed preeclampsia with severe features.","authors":"Helen Woolcock, Maria Katsidoniotaki, Leonidas Taliadouros Meng, Noora Haghighi, Anne-Sophie van Wingerden, Aymen Alian, Whitney A Booker, Natalie A Bello, Randolph S Marshall, Ioannis A Kougioumtzoglou, Nils H Petersen, Eliza C Miller","doi":"10.1088/1361-6579/adfeb4","DOIUrl":"10.1088/1361-6579/adfeb4","url":null,"abstract":"<p><p><i>Objectives</i>. Impaired cerebral autoregulation could contribute to postpartum stroke risk in individuals with preeclampsia. We modeled aggregated static autoregulatory curves in the postpartum period in individuals with no hypertension, preeclampsia, and chronic hypertension with superimposed preeclampsia.<i>Approach</i>. This is a retrospective analysis of data from a prospective observational study of postpartum participants. We measured continuous mean arterial pressure (MAP) with finger plethysmography and cerebral blood velocity (CBv) with transcranial Doppler within 2 weeks after delivery. Data were aggregated and group curves generated from normalized MAP and CBv data using 3rd order polynomial equations. We compared overall polynomial curve shapes between groups as well as pair-wise comparisons of autoregulatory range.<i>Main results</i>. A total of 73 participants were enrolled: 21 (29%) normotensive, 31 (42%) with preeclampsia and 21 (29%) with superimposed preeclampsia. Polynomial<i>S</i>-curves suggested a flatter plateau in the normotensive group compared with both preeclampsia groups, but the differences were not statistically significant. Autoregulatory range were wider in both preeclampsia groups than in the normotensive group, with a MAP range of 27.5 mmHg in the normotensive group, 43.2 mmHg in the preeclampsia group, and 31.5 mmHg in the superimposed preeclampsia group, but only the difference between the preeclampsia and normotensive groups reached statistical significance (<i>p</i>= 0.02).<i>Significance</i>. Static autoregulation curves generated using third-order polynomials showed distinct characteristics in postpartum participants with normotension, preeclampsia, and superimposed preeclampsia, and suggested a wider cerebral autoregulatory range in those with preeclampsia.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12441783/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144964891","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":"Quantifying movement fluency in amputees in key functional tasks.","authors":"Amy Edwards, Terry Fawden, Iwan Vaughan Roberts, Manohar Bance, Thomas Stone","doi":"10.1088/1361-6579/ae06ee","DOIUrl":"https://doi.org/10.1088/1361-6579/ae06ee","url":null,"abstract":"<p><strong>Objective: </strong>Sit-to-stand (STS) and sit-to-walk (STW) movements are key functional tasks to master following lower limb (LL) amputation. They are core to activities of daily living, enabling patients to regain independence. Physiotherapists assess movement fluency (hesitation and smoothness) by observing STS and STW however, this relies on extensive experience and lacks objectivity. This study aimed to establish objective, accessible and scalable quantitative measurements of movement fluency in amputees using instrumented movement analysis.&#xD;Approach: 12 transfemoral amputees (6 limited community and 6 community ambulators) and 6 typical individuals completed walking, STS and STW tasks. Movement fluency was assessed using published algorithms to obtain hesitation and smoothness in STS and STW.&#xD;Main Results: In STW, hesitation, and smoothness showed statistically significant differences among the three groups. Community ambulators were significantly less hesitant (p = 0.009) and smoother (p = 0.007) than the limited community ambulators, but significantly more hesitant (p < 0.001) and less smooth (p < 0.001) than typical individuals. In STS, the community ambulators were significantly smoother than the limited community ambulators (p < 0.001), but not significantly different from typical individuals (p = 0.68). Community ambulators walked significantly faster than limited community ambulators (p < 0.001) but significantly slower compared to typical individuals (p < 0.001). &#xD;Significance: Assessment of movement after amputation is not just about walking speed. Other important functional tasks can differentiate amputees and therefore should be considered. An amputee must learn to master both the STS and STW tasks before they can independently walk. Quantifying movement fluency in functional tasks is important to understanding the restoration of function following limb loss, tracking rehabilitation, and classifying amputees. While the study's small sample size reflects its feasibility design, findings support future research with larger cohorts. Subsequent studies should incorporate power calculations to improve generalisability. &#xD.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145070174","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":"Skin temperature adapted physiological strain index (aPSI) predicts exertional heat illness.","authors":"Mark J Buller, Emma Atkinson, Michelle Elizabeth Akana, Peter D Finch, Kyla A Driver, Timothy J Mesite, Roger C DesRochers, Christopher J King, Tim L Bockelman, Michael S Termini","doi":"10.1088/1361-6579/ae05ae","DOIUrl":"https://doi.org/10.1088/1361-6579/ae05ae","url":null,"abstract":"<p><strong>Objective: </strong>&#xD;Exertional heat illness (EHI) remains a challenge for those that exercise in hot and humid environments. Physiological status monitoring is an attractive method for assessing EHI risk and a critical component of recommended layered risk management approaches. While there is consensus that some combination of core body temperature, mean skin temperature, heart rate (HR), and hydration provide an indication of heat strain, a field-feasible metric that correlates to EHI incidence has not been identified.</p><p><strong>Approach: </strong>We present a comparison of five practicable heat strain indices (skin temperature, estimated core temperature, core-skin temperature difference, Physiological Strain Index [PSI], and Adaptive Physiological Strain Index [aPSI]) for 5,080 U.S. Marine Corps recruits during an intense multi-day physical assessment. We considered the ability of the calculated indices in predicting the 30 EHI cases that occurred during our study.&#xD;Results:&#xD;aPSI and single-point skin temperature identified 86.7% and 83.3% of EHI cases, respectively (~35 minute alert time and ~15% false positive rate). PSI and core-skin temperature difference were only able to identify 63.3% and 60% of EHI cases. Estimated core temperature only identified 23.3% of EHIs. Critically, the cases missed by aPSI included two individuals with fevers from viral infections, and two cases of heat exhaustion who had moderate field rectal temperatures (< 39°C); the rectal temperatures of false negatives for Tsk ranged from 38.3-40.3°C (mean 39.1 ± 0.7°C).</p><p><strong>Significance: </strong>aPSI is demonstrated as the first field-practical exertional heat strain index that accurately identifies EHI risk in real time.&#xD.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145034010","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":"Analysis of time delay between non-invasively measured pulse oscillations in cerebral macro- and microcirculation.","authors":"Marta Hendler, Arkadiusz Ziółkowski, Tomasz Sozański, Marek Czosnyka, Magdalena Kasprowicz","doi":"10.1088/1361-6579/ae008d","DOIUrl":"10.1088/1361-6579/ae008d","url":null,"abstract":"<p><p><i>Objective.</i>Integration of cerebral blood macrocirculation and microcirculation form a crucial aspect of global cerebral blood flow. Our study aimed to investigate time delay between pulse oscillations of cerebral blood flow velocity (FV) and total hemoglobin concentration (tHb) acquired via transcranial Doppler ultrasonography and functional near-infrared spectroscopy, respectively. Additionally, we compared time-related characteristics with cerebral arterial time constant (τ).<i>Approach.</i>The study involved monitoring of FV, tHb, arterial blood pressure and end-tidal CO₂(EtCO₂) during 5 min of rest (normocapnia) and 5 min of controlled hypercapnia in 36 healthy subjects (age: 24 years,<i>Q</i>1-<i>Q</i>3: 21-27 years, 15 females). Onset time delay (onset TD) was defined as the time offset between onsets of FV and tHb pulses, and time to tHb max (TTM) as a time difference between the FV pulse onset and tHb pulse maximum.τwas calculated as a product of cerebrovascular compliance and resistance. Onset TD and TTM were compared between normocapnia and hypercapnia, and their associations withτwere assessed.<i>Main results.</i>Onset TD was consistently positive (0.075 s,<i>Q</i>1-<i>Q</i>3: 0.065-0.108 s). Onset TD andτwere significantly shorter in hypercapnia (0.075 s vs 0.071 s,<i>p</i>< 0.001; 0.107 s vs 0.099 s,<i>p</i>< 0.001). Changes in onset TD andτbetween normo- and hypercapnia were significantly correlated (<i>R</i>_S= 0.452,<i>p</i>< 0.01). TTM was correlated withτin normocapnia (<i>R</i>_S= 0.364,<i>p</i>= 0.03), hypercapnia (<i>R</i>_S= 0.407,<i>p</i>= 0.01) and in terms of relative changes (<i>R</i>_S= 0.421,<i>p</i>= 0.01).<i>Significance.</i>There is a time delay between cerebral macro- and microcirculation, which becomes shorter as the cerebral vasculature dilates in hypercapnia.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144964906","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":"Association between phase angle and body composition components in adolescent athletes: a cross-sectional study.","authors":"Jean Carlos Parmigiani De Marco, Tiago Rodrigues de Lima, Pedro Biehl Tanimoto, Clair Costa Miranda, Mateus Augusto Bim, Andreia Pelegrini","doi":"10.1088/1361-6579/adfffb","DOIUrl":"10.1088/1361-6579/adfffb","url":null,"abstract":"<p><p><i>Objective.</i>To investigate the association of phase angle (PhA) with body fat percentage, lean soft tissue, and bone mineral density (BMD) in adolescent athletes overall and stratified by sex and sexual maturity stage.<i>Approach.</i>A cross-sectional study was conducted with 112 adolescent athletes (67 boys, 14.25 ± 2.08 years) who practiced indoor volleyball, beach volleyball, swimming, Track and Field, or basketball. BMD, lean soft tissue, and body fat percentage were estimated using dual-energy x-ray absorptiometry. PhA was determined using bioelectrical impedance analysis (50 kHz). Associations between PhA and body composition were tested using multiple linear regression in three models: (1) total sample, (2) stratified by sex, and (3) stratified by maturation. Covariates generally included skin color/race, sport modality, time in the sport, and weekly training volume.<i>Main results.</i>In the overall sample, PhA showed a negative association with body fat percentage and a positive association with lean soft tissue and BMD. When the results were stratified by sex, there was a negative association with fat percentage in girls and positive associations with lean soft tissue and BMD in boys. Analysis by sexual maturity stage revealed that PhA was negatively associated with body fat percentage in pubertal athletes and positively associated with lean soft tissue and BMD in both pubertal and post-pubertal athletes.<i>Significance.</i>PhA was positively associated with lean soft tissue and BMD and negatively associated with fat percentage. However, associations varied by sex and sexual maturity, underscoring the importance of accounting for these biological variables when assessing relationships between body composition and PhA in athletes.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144964919","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":"Reconstructing the aortic pressure waveform using a hybrid model of variational mode decomposition improved by particle swarm optimization and gated recurrent units.","authors":"Shuo Du, Guozhe Sun, Hongming Sun, Lisheng Xu, Guanglei Wang, Jordi Alastruey, Jinzhong Yang","doi":"10.1088/1361-6579/adfc25","DOIUrl":"https://doi.org/10.1088/1361-6579/adfc25","url":null,"abstract":"<p><p><i>Objective.</i>The aortic pressure waveform (APW) is relevant to diagnosing and treating cardiovascular diseases. While various non-invasive methods for APW estimation exist, more accurate and practical monitoring methods are required. This study introduces a hybrid model combining variational mode decomposition improved by particle swarm optimization (PSO-VMD) and gated recurrent unit (GRU) networks (PSO-VMD-GRU) to reconstruct the APW from the brachial pressure waveform (BPW).<i>Approach.</i>The model was verified using invasive APWs and BPWs. Data synthesis generated additional samples. The synthetic BPWs were decomposed into multiple intrinsic mode functions (IMFs) using PSO-VMD. A GRU was trained to map the relationship between the IMFs and synthetic APWs. The proposed model was evaluated by comparing the mean absolute errors and Spearman's correlation coefficients (SCCs) of reconstructed total waveform (TW) and key hemodynamic indices including systolic, diastolic and pulse pressures (SP, DP and PP, respectively) against those from generalized transfer function (GTF) and other neural network-based methods, including temporal convolutional network (TCN), and bi-directional long short-term memory and self-attention mechanism (CBi-SAN).<i>Main results.</i>Among the four methods, PSO-VMD-GRU achieved the highest SCCs for TW (0.9912) and DP (0.9676), while TCN performed the best for SP (0.9850) and PP (0.9875). In MAE comparisons, PSO-VMD-GRU matched CBi-SAN across TW, SP, DP, and PP, while surpassing GTF in TW (2.44 versus 2.66 mmHg) and DP (1.61 versus 1.94 mmHg), and outperforming TCN in DP (1.61 versus 1.93 mmHg).<i>Significance.</i>Experiment results have shown that integrating PSO-VMD with GRU improves the accuracy of APW reconstruction effectively.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":"46 9","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144993313","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 systematic review of contactless respiratory rate measurement using RGB cameras.","authors":"Sreya Deb Srestha, Sungho Kim","doi":"10.1088/1361-6579/adfc24","DOIUrl":"10.1088/1361-6579/adfc24","url":null,"abstract":"<p><p><i>Objective</i>. The advancement of contactless methods of measuring the respiratory rate (RR) using RGB cameras demonstrates a significant potential for improving patient care in various environments. As these methods offer reliable and discreet monitoring, they can prevent severe health complications and improve outcomes for patients facing challenges accessing traditional healthcare facilities.<i>Approach</i>. This systematic review explores recent advancements in RR estimation using RGB cameras, focusing on assessing publicly available datasets and effective signal preprocessing methods. We also conducted a comprehensive analysis by comparing RGB camera-based approaches with other sensor modalities and discussed potential future research directions and indicated the necessity of developing new approaches that would mitigate existing challenges and would enhance the accuracy and reliability of non-contact RR measurement methods.<i>Main results</i>. We analyzed existing public datasets, assessing their diversity in lighting, skin tone, and motion, alongside the camera hardware configurations, including frame rate and resolution, utilizing different filter and feature-based techniques. While deep learning and hybrid models achieved lower errors under ideal indoor lighting and minimal motion, performance significantly declined in low light, high motion, or complex uncontrolled environments. In contrast, other sensor modalities, such as thermal and infrared sensors, achieved high accuracy across a wide range of conditions, but at greater hardware cost and system complexity, while RGB cameras remained the most cost-effective option, trading off precision for accessibility.<i>Significance</i>. RGB camera-based RR monitoring systems have the potential for robust applicability in clinical and nonclinical settings such as telemedicine platforms for monitoring patients breathing rates (BRs) in real time. This review highlights existing research gaps, such as insufficient real-world datasets and sensitivity to environmental variance, and emphasizes on the importance of acquiring datasets based on complex real-world scenarios, standardized benchmarks, multi-sensor fusion for addressing current limitations, and deep neural network architecture implementation for reliable non-contact RR estimation for real-world applications.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144859538","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":"Accuracy of energy expenditure estimation by the Apple Watch in EMS-supported exercise.","authors":"V Heinz, N Pilz, T Lindner, H F Brandt, Oliver Opatz, L Fesseler, A Patzak, T L Bothe","doi":"10.1088/1361-6579/adfcaf","DOIUrl":"10.1088/1361-6579/adfcaf","url":null,"abstract":"<p><p><i>Objective.</i>Wearable devices are becoming increasingly prevalent, offering the capability to estimate energy expenditure. Among these devices, the Apple Watch has demonstrated notable results in estimating energy expenditure during physical activity, especially compared to other wearable devices. Its accuracy in determining energy expenditure during electromyostimulation (EMS) training remains unexplored and is investigated in this work.<i>Methods.</i>35 young, healthy adults completed two stepwise increasing bike ergometer protocols (50/30/3 protocol) until the maximum physical load was reached with and without EMS support. Energy expenditure estimates from the Apple Watch Series 7 (Apple Inc., Cupertino, California, USA) were compared against gold-standard spirometric calorimetry measurements.<i>Results.</i>The Apple Watch Series 7 underestimated energy expenditure compared to spirometric calorimetry for all data (mean difference: -27.4 kcal, LoA: 62.2 kcal), for ergometer exercise without EMS (mean difference: -28.8 kcal, LoA: 62.8 kcal), and for ergometer exercise with EMS (mean difference: -26.0 kcal, LoA: 62.4 kcal) data. We observed strong correlations between the Apple Watch Series 7 and spirometric calorimetry, with<i>r</i>= 0.93 (<i>p</i>< 0.001) for all data,<i>r</i>= 0.93 (<i>p</i>< 0.001) for exercise without EMS, and<i>r</i>= 0.93 (<i>p</i>< 0.001) for exercise with EMS.<i>Conclusion.</i>The Apple Watch Series 7 showed consistent accuracy in estimating energy expenditure during ergometer exercise, both with and without EMS. These findings suggest that the device can reliably monitor energy expenditure during EMS training, exhibiting similar accuracy limitations to conventional exercise settings.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144874607","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":"Sensor-free physiological guidance for free-breathing cardiac cine MRI using implicit neural representation CineJENSE reconstruction.","authors":"L Quillien, M Beaumont, D Mandry, P-Y Marie, J Felblinger, P-A Vuissoz, J Oster","doi":"10.1088/1361-6579/adfc23","DOIUrl":"10.1088/1361-6579/adfc23","url":null,"abstract":"<p><p><i>Objective</i>. The aim of this study was to explore free-breathing cardiac cine images reconstructed with sensor-free physiological signals estimates. Such signals were estimated using the noise variance of the radio frequency receiver coils. Reconstructions with reference signals acquired during MR scan were compared with the sensor-free reconstructions using an extended CineJENSE algorithm.<i>Approach</i>. Free-breathing untriggered MRI cine data from 27 patients and 22 healthy volunteers in various slice orientations were acquired simultaneously with physiological signals using external sensors (ECG and respiratory belts). Physiological signals were estimated using the noise variance of receiver coils and specific signal processing with source separation. CineJENSE reconstruction, based on implicit neural representations was adapted to free-breathing data. Correlation coefficient between both respiration signals and F1-score of the cardiac peak detections were computed for quantitative results. The reconstructed images were visually inspected to assess their quality and presence of motion artefacts and an automatic segmentation was performed and compared to the manual segmentation with DICE scores computation.<i>Main results</i>. An average correlation coefficient of 0.69 ± 0.22 and F1-score of 0.73 ± 0.23 for all subjects was found. Reconstructed images quality was close to that of the reconstructed images with reference signals, although slightly lower (2.51 ± 0.8 and 2.84 ± 0.7). Dice scores for LV was 0.86 ± 0.13 for reconstructed images with sensor-free estimations compared to 0.85 ± 0.12 with external sensors.<i>Significance</i>. This study demonstrated overall good quality images of free-breathing acquisitions using cardiac and respiration motion estimations based on the RF noise navigator.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144859539","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":"Improved state refinement for LSTM determined 3D CAISR-LSTM model for automatic myocardial infarction detection.","authors":"Muqing Deng, Boyan Li, Mingying Ma, Wei Deng, Xinghui Zeng, Yanjiao Wang, Xiaoyu Huang","doi":"10.1088/1361-6579/adfda9","DOIUrl":"https://doi.org/10.1088/1361-6579/adfda9","url":null,"abstract":"<p><p><i>Objective.</i>Electrocardiograms (ECGs) contain valuable information in the clinical diagnosis of myocardial infarction (MI). However, its interpretation process is dependent on cardiologists with extensive clinical experience and expertise. The issue not only causes a paucity of medical resources, but also restricts patients from receiving timely diagnoses. Thus, a novel approach for MI automatic detection is developed, based on 12-lead ECG and an improved state refinement for long short-term memory (LSTM) determined 3D convolution-attention (3D CAISR-LSTM) model.<i>Approach.</i>The proposed 3D CAISR-LSTM model is trained in an end-to-end fashion. The input 12-lead ECG signals are preprocessed to eliminate power line interference, high-frequency noise and baseline wander. Then, the ECG signals are transformed into time-frequency images using continuous wavelet transform and bilinear interpolation. The obtained images are constructed into three-dimensional spatiotemporal features, serving as input to the 3D CAISR-LSTM model. In the 3D CAISR-LSTM model, there are three main components: a convolutional module, four identical convolutional attention modules, and an improved state refinement for LSTM. Performance of the 3D CAISR-LSTM model in automatic detection of MI versus healthy controls is evaluated through ten-fold cross validation on the publicly available PTB diagnostic ECG database.<i>Main results.</i>Experimental results demonstrate that the 3D CAISR-LSTM model achieves an accuracy of 98.45%, sensitivity of 98.69%, specificity of 97.50%, and<i>F</i>1 score of 99.03%, outperforming various advanced 2D and 3D deep neural network architectures.<i>Significance.</i>The proposed approach is expected to provide an early warning before obvious MI symptoms appear. It also has the potential to be developed into a lightweight embedded MI detection equipment.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":"46 9","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144964884","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}