Biocybernetics and Biomedical Engineering最新文献

{"title":"A multidomain 0D model for continuous positive airway pressure ventilation circuit design: Validation and applications","authors":"Andrea Formaggio ,&nbsp;Margherita De Luca ,&nbsp;Simone Borrelli ,&nbsp;Giovanni Putame ,&nbsp;Nello De Vita ,&nbsp;Fabio Minelli ,&nbsp;Francesco Della Corte ,&nbsp;Rosanna Vaschetto ,&nbsp;Alberto L. Audenino ,&nbsp;Carlo Olivieri ,&nbsp;Mara Terzini","doi":"10.1016/j.bbe.2025.02.004","DOIUrl":"10.1016/j.bbe.2025.02.004","url":null,"abstract":"<div><div>This study focuses on optimizing a non-invasive ventilation (NIV) circuit for the treatment of hypoxemic respiratory failure using continuous positive airway pressure (CPAP). A multidomain 0D <em>in silico</em> approach was employed, creating a lumped circuit model of an innovative NIV-CPAP system in Mathworks® Simulink. The model relies on <em>in vitro</em> tests on commercial components characterizing pneumatic resistive behavior, and it exploits an extended resistance-inductance-capacitance model for the patient’s respiratory system, recurring to sigmoidal pressure–volume behavior characteristic of pathological conditions. The NIV-CPAP system was assembled <em>in vitro</em> and connected to a lung simulator to validate the model under healthy and pathological conditions (acute respiratory distress syndrome and chronic obstructive pulmonary disease). The study explored the impact of key features on the ventilation circuit, such as interface leakage, air volume within the circuit, and resistance induced by circuit components.</div><div>Validation of the 0D model through <em>in vitro</em> tests showed correlation coefficients between 0.9 and 1. Interface leakage caused reductions of up to 6% in delivered static pressure. Changes in air volume (mask or helmet interface, reservoirs adding) resulted in a maximum 8% decrease in pressure oscillations. Increased resistances from the starting ventilation circuit produced a tidal volume reduction of less than 1%. An optimized configuration that balanced resistances between limbs improved intrinsic positive end-expiratory pressure generation.</div><div>The proposed 0D model proved to be effective in guiding the design of the innovative device, providing computational efficiency and flexibility; it demonstrated its reliability as a tool to support the optimization of non-invasive ventilation circuits.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 170-180"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A sepsis diagnosis method based on Chain-of-Thought reasoning using Large Language Models","authors":"Weimin Zhang ,&nbsp;Mengfei Wu ,&nbsp;Luyao Zhou ,&nbsp;Min Shao ,&nbsp;Cui Wang ,&nbsp;Yu Wang","doi":"10.1016/j.bbe.2025.04.002","DOIUrl":"10.1016/j.bbe.2025.04.002","url":null,"abstract":"<div><div>Sepsis is a severe infectious disease with high incidence and mortality rates globally. Early diagnosis of sepsis is crucial for improving patient outcomes. Previous diagnostic methods heavily relied on subjective clinical experience, while the machine learning-based methods can only learn knowledge from a specific dataset. Recently, the rapid development of Large Language Models (LLMs) has significantly enhanced various downstream dialogue tasks by leveraging prior semantic knowledge. Therefore, it is of great interest to explore the potential of LLMs in sepsis diagnosis. This study proposed an early sepsis diagnosis method based on the Chain of Thought (CoT) reasoning using LLMs. First, the clinical data of a patients were transformed into a textual representation to form the prompt. Subsequently, a CoT was created to simulate the reasoning process of human medical experts and utilized the prior semantic knowledge in LLMs to achieve sepsis diagnosis. The proposed method was validated using real clinical data, demonstrating high classification performance with an accuracy of 0.87, recall of 0.98, and F1 score of 0.88. These metrics showed an improvement in F1 score by 7 to 8 percentage points compared to commonly used machine learning classifiers. The experimental results indicated that the proposed method can enhance the performance of early sepsis diagnosis, and the introduction of CoT enhanced the interpretability of diagnostic results, contributing to the application of LLMs in clinical diagnosis.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 269-277"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classifying developmental delays with EEG: A comparative study of machine learning and deep learning approaches","authors":"Muhammad Usman ,&nbsp;Wen-Yi Lin ,&nbsp;Yi-Yin Lin ,&nbsp;Sheng-Ta Hsieh ,&nbsp;Yao-Tien Chen ,&nbsp;Yu-Chun Lo ,&nbsp;Chun-Ling Lin","doi":"10.1016/j.bbe.2025.04.001","DOIUrl":"10.1016/j.bbe.2025.04.001","url":null,"abstract":"<div><div>Early detection of developmental delays is crucial for improving children’s cognitive, social, and emotional outcomes through timely interventions. This study explores the potential of machine learning (ML) and deep learning (DL) to classify Electroencephalography (EEG) data from an oddball task, distinguishing between children with and without developmental delays. Participants underwent language assessments and EEG recordings, with subsequent analysis using Event-Related Potentials (ERPs), Event-Related Spectral Perturbations (ERSPs), and functional connectivity to characterize group differences. Three methodologies were employed in this research to classify EEG data. Firstly, statistical features are extracted from the EEG data and various ML algorithms are applied for classification, with feature selection techniques utilized to identify the most relevant features and enhance classification accuracy. Secondly, brain dynamics is utilized to incorporate ERP, ERSP, and functional connectivity measures as features for developmental delay detection. Similar to the first approach, feature selection techniques are again employed to enhance classification accuracy. Lastly, DL approaches are explored by implementing multiple convolutional neural networks (CNNs), including a 2D CNN (EEGNet), various hybrid CNN architectures integrating LSTM, GRU, and attention mechanisms, and a novel 1D CNN with a standardized convolutional layer (SCL) for improved stability and training performance. The effectiveness of each approach in accurately classifying EEG data for developmental delay detection is independently analyzed. The results demonstrate that the proposed 1D convolutional neural network outperforms both EEGNet and the employed ML classifiers. This model achieves an impressive accuracy of 96.4% and an F1 score of 96.6%, underscoring its potential as a valuable tool for early and accurate developmental delay detection using EEG data.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 229-246"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143799347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hemodynamic factors in coronary artery lesions: An in-vitro tomographic particle image velocimetry study","authors":"Ke-Wei Xu ,&nbsp;Hang Zhao ,&nbsp;Min Wan ,&nbsp;Ke Zhang ,&nbsp;Xiuhua Hu ,&nbsp;Qi Gao","doi":"10.1016/j.bbe.2025.05.001","DOIUrl":"10.1016/j.bbe.2025.05.001","url":null,"abstract":"<div><div>This study addresses the gap in in-vitro research by providing three-dimensional flow field measurements of a complete coronary artery model to explore coronary artery hemodynamics. An in-depth analysis of the left coronary artery (LCA) was conducted using tomographic particle image velocimetry (TPIV) in a patient-specific model with a mock circulatory loop (MCL) that simulates physiological conditions. The study maps wall shear stress (WSS) and flow rates across arterial branches, highlighting the predisposition to atherosclerosis in the left anterior descending (LAD) artery due to its unique hemodynamic properties. Intermittent low WSS is identified and considered to be strongly associated with diffuse coronary artery disease (CAD). Additionally, statistical analysis of fluid topology reveals a significant correlation between the kinematic vorticity number and CAD, suggesting its potential as a CAD risk indicator in clinical practice. This research enhances the understanding of coronary hemodynamics and contributes to establishing a theoretical framework for flow-induced atherosclerosis.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 296-304"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Observer-based linear state-dependent control for blood glucose regulation in type 1 diabetic patients with unknown delays","authors":"J. Castro-Gómez ,&nbsp;B. Targui ,&nbsp;O. Hernández-González ,&nbsp;G. Valencia-Palomo ,&nbsp;M.E. Guerrero-Sánchez","doi":"10.1016/j.bbe.2025.02.003","DOIUrl":"10.1016/j.bbe.2025.02.003","url":null,"abstract":"<div><div>This paper presents a control strategy for blood glucose regulation in the presence of a time-varying delayed input, where the delay is unknown. The proposed control scheme is based on an observer-based linear state-dependent (LSD) (a subclass of the general linear parameter varying (LPV) framework) control with <span><math><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></math></span> criterion. This proposed control regulates glucose levels in response to meal intake. A novel LSD system representation is used to relax the inherent conservativeness of the nonlinear system. First, the observer achieves an estimate of the current state vector despite the delayed input, where the time-varying unknown delay can be relatively long. Thus, the control law will perform well in the presence of a long unknown delay. The observer-based control scheme is validated by considering different meal disturbances and unknown delay scenarios.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 189-198"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physically motivated projection of the electrocardiogram—A feasibility study","authors":"Sebastian Wildowicz ,&nbsp;Tomasz Gradowski ,&nbsp;Paulina Figura ,&nbsp;Igor Olczak ,&nbsp;Judyta Sobiech ,&nbsp;Teodor Buchner","doi":"10.1016/j.bbe.2025.03.001","DOIUrl":"10.1016/j.bbe.2025.03.001","url":null,"abstract":"<div><div>We present PhysECG: a physically motivated projection of the 12 lead electrocardiogram, supported by a deep learning model trained on 21,799 recordings from the PTB-XL database and discuss its feasibility. The method allows to evaluate the epicardial activity (inverse problem of ECG imaging) and, in particular, to distinguish left and right ventricular activity, with statistical spread related to localization of the septum. The observed dyssynchrony resembles other experimental results. The foundations of the method are based on the molecular theory of biopotentials. The heart’s activity in view of the method is decomposed into two processes: the passage of the electric activation wavefront and the response of cardiomyocytes. We introduce the idea of the electrode-resolved activity function, which represents the mass of the ventricle in Phase 0 of action potential within the lead field of each electrode. The computations are fast and robust, with excellent convergence. We present the quality metrics for the reconstruction based on the model on the testing set selected from the PTB database. In order to prove feasibility, we present and discuss two healthy controls: male and female, and two pathologies: right bundle branch block, and anterior myocardial infarction. The results obtained using PhysECG seem to be in accordance with the changes evoked by pathology, which has to be confirmed by subsequent clinical studies. The method is based on ECG, and does not require reconstruction of body geometry, which presents an affordable solution for low and middle-income countries where access to imaging is limited.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 199-211"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validation of a markerless motion capture system for centre of mass kinematic analysis","authors":"Ruben Valenzuela ,&nbsp;Javier Corral ,&nbsp;Mikel Diez ,&nbsp;Thomas Provot ,&nbsp;Francisco J. Campa ,&nbsp;Saioa Herrero ,&nbsp;Erik Macho ,&nbsp;Charles Pinto","doi":"10.1016/j.bbe.2025.03.004","DOIUrl":"10.1016/j.bbe.2025.03.004","url":null,"abstract":"<div><div>In recent years, markerless optical systems for biomechanical movement analysis in sports, gait and balance assessments are being used as an alternative to conventional marker based measuring systems. This study compares the performance of the Zed 2i stereoscopic camera against a VICON system in a standing position under three conditions: quiet standing and two movements simulating disturbances in two directions, anteroposterior and mediolateral. This study originates from a collaborative project with a medical team that aims to objectively evaluate balance function in patients recovering from stroke. The displacement and velocities of the centre of mass were calculated and compared in two directions, x and y. A Bland–Altman analysis for non-parametric data, along with the coefficient of determination and mean square error, were used for statistical evaluation. The results demonstrate that the limits of agreement in both sway tasks were greater than those observed in static conditions. However, the coefficient of determination of the sway tasks indicates a significant degree of agreement between the two systems. In contrast, in the static condition, it appears that noise may have a greater influence on the signal than the centre of mass estimate, due to the limitation of the depth algorithm used to estimate the joint positions.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 278-286"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A glimpse ahead: Forecasting 5.5-s human vigilance for enhanced safety in Industry 5.0","authors":"Ettore Cinquetti ,&nbsp;Ilaria Siviero ,&nbsp;Fabio Babiloni ,&nbsp;Gloria Menegaz ,&nbsp;Silvia F. Storti","doi":"10.1016/j.bbe.2025.03.002","DOIUrl":"10.1016/j.bbe.2025.03.002","url":null,"abstract":"<div><div>In the context of Industry 5.0 and human-robot interaction, ensuring the safety of operators by avoiding human errors is crucial. Monitoring vigilance decrement is an essential aspect of this effort, aimed at mitigating safety risks and enhancing productivity. A potentially promising solution to this challenge is using a passive brain-computer interface (BCI) based on electroencephalography (EEG) recordings. However, its application in industrial settings has yet to be explored in-depth. This study uses EEG data to introduce a novel experimental protocol and analysis pipeline to predict vigilance degradation in an industrial research laboratory. The dataset was gathered from ten healthy volunteers who observed a robotic arm for 23 min. The EEG power spectrum over time was computed using the continuous wavelet transform (CWT). After confirming growth in power for the α band using a linear regression model, we forecast its trend using four models. As a conventional approach, we used the vector autoregressive (VAR) model, serving as a reference for comparison with three deep learning architectures: a temporal convolutional network (TCN), a gated recurrent unit (GRU) and an encoder-decoder (ED)-GRU. The proposed ED-GRU model outperformed the others showing accurate forecasts (mean absolute error = 0.048, R² = 0.726) up to 5.5 s. The findings suggest that monitoring vigilance degradation in Industry 5.0 is a feasible strategy to prevent human accidents and reduced performance during repetitive tasks.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 258-268"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An intelligent hemodynamic response analysis method to achieve prognosis and diagnosis of Huntington’s disease","authors":"Niloofar Fathalizade ,&nbsp;Peyvand Ghaderyan","doi":"10.1016/j.bbe.2025.04.003","DOIUrl":"10.1016/j.bbe.2025.04.003","url":null,"abstract":"<div><div>The development of a reliable and cost-effective Huntington’s disease (HD) detection is a challenging task due to non-specific clinical first symptoms. To address the challenge, this is the first study to comprehensively focus on proposing an automated HD detection system based on functional near-infrared spectroscopy (fNIRS) analysis through a standard decomposition technique and dynamic mapping neural networks. fNIRS is a highly cost-effective and more refined neuroimaging modality that noninvasively measures hemodynamic responses and neurovascular coupling mechanisms. Considering the non-stationary nature of the hemoglobin concentration changes, the proposed system has developed a new fNIRS-based biomarker of HD, namely time-varying singular value, to characterize the spatiotemporal characteristics of the oxyhemoglobin and deoxyhemoglobin signals. The classification has been performed using a support vector machine, recurrent neural network, and cascade forward neural network to discriminate healthy controls (HC) from presymptomatic (Pre-HD) or symptomatic HD (SHD) subjects. Moreover, in a comparative study, the effects of trajectory matrix size, clinical categories of HD, type of chromophores, and brain regions have been tested on the detection performance, separately.</div><div>To evaluate the proposed system, the fNIRS dataset of 12 Pre-HD, 15SHD, 29 HC for Pre-HD, and 33 HC for the SHD has been used. The method has achieved remarkable accuracy rates of 95.61% for Pre-HD vs. HC and 95.63% for SHD vs. HC. The comparative analysis leads to the outstanding performance of this system and its high robustness against affecting factors, providing a better trade-off between computational costs and detection performance.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 287-295"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contact Pressure, sliding distance and wear rate analysis at trunnion of hip implant for daily Activities: A finite element approach","authors":"Md Mohiuddin Soliman ,&nbsp;Mohammad Tariqul Islam ,&nbsp;Phumin Kirawanich ,&nbsp;Muhammad E.H. Chowdhury ,&nbsp;Touhidul Alam ,&nbsp;Ayed M. Alrashdi ,&nbsp;Norbahiah Misran ,&nbsp;Mohamed S. Soliman","doi":"10.1016/j.bbe.2025.02.001","DOIUrl":"10.1016/j.bbe.2025.02.001","url":null,"abstract":"<div><div>This research analyses contact pressure, sliding distance, and wear rate at the trunnion interface of hip implants during various activities to understand post-hip replacement outcomes. The study uses a numerical model and ISO-7206–6:2013 constraints with an AML hip implant. Greater F_x, F_y, and F_z forces broaden contact pressure distribution. The highest pressure occurs on the proximal superolateral surface, with the lowest on the anterior and posterior surfaces. The HIGH100 (individuals weighing above 100 kg) weight category demonstrates 2 times higher maximum and average contact pressure compared to AVG75 (individuals weighing 75 kg) for sit-down and knee bend activities. Force components and the duration of a full gait cycle influence sliding distance. Stance activities show the highest sliding distance due to rapid changes in force load during the gait cycle. For sit-down and knee bend activities, the total sliding distance is 2.5 times higher in the HIGH100 weight category compared to AVG75. Sliding distance primarily occurs at the proximal superolateral-inferomedial-anterior-posterior contact surface, decreasing distally. Based on contact pressure, sliding distance, and wear volume rate, jogging and stance activities pose the highest risk for hip replacement patients, while cycling is the safest. The HIGH100 weight group exhibits 5- and 4-times greater wear volume rates than AVG75 in sit-down and knee bend activities, respectively. The research findings align with wear degradation observed in retrieved hip implants, validating the study. These insights can assist patients in making informed decisions about performing activities after surgery while enabling physicians to provide accurate guidelines.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 2","pages":"Pages 137-153"},"PeriodicalIF":5.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}