Computer methods and programs in biomedicine最新文献

{"title":"Human-computer interaction on virtual reality-based training system for vascular interventional surgery","authors":"Pan Li ,&nbsp;Xinxin Zhang ,&nbsp;Xiaowei Hu ,&nbsp;Fangting Ding ,&nbsp;Cunman Liang","doi":"10.1016/j.cmpb.2025.108731","DOIUrl":"10.1016/j.cmpb.2025.108731","url":null,"abstract":"<div><h3>Background and objective</h3><div>Currently, precision control and interaction between virtual hand models and ultrafine, ultra-long flexible guidewires in virtual vascular interventional surgery training systems still remain challenging.</div></div><div><h3>Methods</h3><div>To tackle this issue, this study utilized a hybrid approach combining Cosserat rod theory with quaternions to develop a model for ultra-long flexible guidewires. Through the implementation of a spatial hash-based continuous collision detection (CCD) algorithm, the system achieved precise collision detection between the guidewire and blood vessels. Additionally, adhesive collision particles were integrated into the fingers of the virtual hand model involved in interactions, facilitating the simulation of intervention tasks such as grasping and delivering. CCD technology, in conjunction with extended bounding volume, was employed in the blood vessel model to prevent tunneling effects resulting from rapid hand manipulations.</div></div><div><h3>Results</h3><div>Experiments were conducted to assess the picking, delivery, and consistency of delivery distance, showcasing the alignment of manipulation between the virtual hand models and real hands when handling the guidewire. The virtual hand model successfully navigated the flexible guidewire model into vessels curved at angles of 30°, 60°, 90°, and 120°, achieving an average response time of 12.64 ms. Moreover, across vessel models curved at various angles, the average disparity between the delivery distance along the <em>x</em>-axis by the hand in a real environment and the guidewire's delivery distance within the virtual vessel model was approximately 3.71 mm, showcasing a high level of smoothness and stability in the interaction between the hand model and the guidewire model.</div></div><div><h3>Conclusions</h3><div>Finally, within the virtual system, the successful navigation of the hand delivering the guidewire through the femoral artery and radial artery towards the heart further demonstrates the excellent interaction performance between the virtual hand model and the ultrafine, ultra-long flexible guidewires. This success provides both theoretical and experimental support for the interactive training of virtual hand models and guidewires within virtual surgical training systems.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108731"},"PeriodicalIF":4.9,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739981","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":"Combating Medical Label Noise through more precise partition-correction and progressive hard-enhanced learning","authors":"Sanyan Zhang ,&nbsp;Surong Chu ,&nbsp;Yan Qiang ,&nbsp;Juanjuan Zhao ,&nbsp;Yan Wang ,&nbsp;Xiao Wei","doi":"10.1016/j.cmpb.2025.108734","DOIUrl":"10.1016/j.cmpb.2025.108734","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Computer-aided diagnosis systems based on deep neural networks heavily rely on datasets with high-quality labels. However, manual annotation for lesion diagnosis relies on image features, often requiring professional experience and complex image analysis process. This inevitably introduces noisy labels, which can misguide the training of classification models. Our goal is to design an effective method to address the challenges posed by label noise in medical images.</div></div><div><h3>Methods:</h3><div>we propose a novel noise-tolerant medical image classification framework consisting of two phases: fore-training correction and progressive hard-sample enhanced learning. In the first phase, we design a dual-branch sample partition detection scheme that effectively classifies each instance into one of three subsets: clean, hard, or noisy. Simultaneously, we propose a hard-sample label refinement strategy based on class prototypes with confidence-perception weighting and an effective joint correction method for noisy samples, enabling the acquisition of higher-quality training data. In the second phase, we design a progressive hard-sample reinforcement learning method to enhance the model’s ability to learn discriminative feature representations. This approach accounts for sample difficulty and mitigates the effects of label noise in medical datasets.</div></div><div><h3>Results:</h3><div>Our framework achieves an accuracy of 82.39% on the pneumoconiosis dataset collected by our laboratory. On a five-class skin disease dataset with six different levels of label noise (0, 0.05, 0.1, 0.2, 0.3, and 0.4), the average accuracy over the last ten epochs reaches 88.51%, 86.64%, 85.02%, 83.01%, 81.95%, 77.89%, respectively; For binary polyp classification under noise rates of 0.2, 0.3, and 0.4, the average accuracy over the last ten epochs is 97.90%, 93.77%, 89.33%, respectively.</div></div><div><h3>Conclusions:</h3><div>The effectiveness of our proposed framework is demonstrated through its performance on three challenging datasets with both real and synthetic noise. Experimental results further demonstrate the robustness of our method across varying noise rates.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108734"},"PeriodicalIF":4.9,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740117","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":"Breaking through scattering: The H-Net CNN model for image retrieval","authors":"Roger Chiu-Coutino ,&nbsp;Miguel S. Soriano-Garcia ,&nbsp;Carlos Israel Medel-Ruiz ,&nbsp;S.M. Afanador-Delgado ,&nbsp;Edgar Villafaña-Rauda ,&nbsp;Roger Chiu","doi":"10.1016/j.cmpb.2025.108723","DOIUrl":"10.1016/j.cmpb.2025.108723","url":null,"abstract":"<div><h3>Background:</h3><div>In scattering media, traditional optical imaging techniques often find it significantly challenging to accurately reconstruct images owing to rapid light scattering. Thus, to address this problem, we propose a convolutional neural network architecture called H-Net, which is specifically designed to recover structural information from images distorted by scattering media.</div></div><div><h3>Method:</h3><div>Our approach involves the use of dilated convolutions to capture local and global features of the distorted images, allowing for the effective reconstruction of the underlying structures. First, we developed a diffuse image dataset by projecting handwritten numbers through diffusers with different thicknesses, capturing the resulting distorted images. Second, we generated a synthetic speckle images dataset, composed of simulated speckle patterns. These datasets were designed to train the model to recover structures within scattering media. To evaluate the model’s performance, we calculated the Structural Similarity Measure Index between the model’s predictions and the original images on unseen data.</div></div><div><h3>Result:</h3><div>This proposed architecture achieves reconstructions with an average structural similarity index measure of 0.8 while maintaining low computational costs.</div></div><div><h3>Conclusion:</h3><div>The results of this study indicate that H-Net offers an alternative to more complex and computationally expensive models, providing efficient and reliable image reconstruction in scattering media.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108723"},"PeriodicalIF":4.9,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714963","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 Physics-Integrated Deep Learning Approach for Patient-Specific Non-Newtonian Blood Viscosity Assessment using PPG","authors":"Hyeong Jun Lee ,&nbsp;Young Woo Kim ,&nbsp;Seung Yong Shin ,&nbsp;San Lee Lee ,&nbsp;Chae Hyeon Kim ,&nbsp;Kyung Soo Chung ,&nbsp;Joon Sang Lee","doi":"10.1016/j.cmpb.2025.108740","DOIUrl":"10.1016/j.cmpb.2025.108740","url":null,"abstract":"<div><h3>Background and Objective</h3><div>The aim of this study is to extract a patient-specific viscosity equation from photoplethysmography (PPG) data. An aging society has increased the need for remote, non-invasive health monitoring systems. However, the circulatory system remains beyond the scope of wearable devices. The solution might be found in the possibility of measuring blood viscosity from wearable devices. Blood viscosity information can be used to monitor and diagnose various circulatory system diseases. Therefore, if blood viscosity can be calculated from wearable photoplethysmography, the versatility of a non-invasive health monitoring system can be broadened.</div></div><div><h3>Methods</h3><div>A hybrid 1D CNN-LSTM architecture incorporating physics-informed constraints was developed to integrate rheological principles into data-driven PPG analysis. The shear-viscosity equation derived from the viscometer was used as ground-truth data. The signal obtained from the wearable devices was processed with noise filtering and wandering elimination to gain stable blood pressure waves. The neural network was trained using k-fold cross-validation and weight factor optimization, with the loss function incorporating rheological constraints from the Carreau–Yasuda model.</div></div><div><h3>Results</h3><div>The final estimation model achieved an accuracy of 81.1 %. The accuracy in the physiological shear range (50–300 s^-1) was 84.0 %, outperforming other low and high shear regions. Mean absolute errors of 0.67 cP in the physiological range align with clinical viscometry tolerances (&lt; 1 cP), demonstrating diagnostic feasibility. Statistical analysis revealed strong linear relationships between predicted and ground truth values across all shear rates (correlation coefficients: 0.619–0.742, <em>p</em> &lt; 0.0001), with mean absolute errors decreasing from 7.84 cP at low shear rates to 0.67 cP in the physiological range. The accuracy and contribution of each parameter to the Carreau–Yasuda model were also analyzed. The results show that the contribution of each parameter varies based on the shear range, providing insight into weight factor optimization.</div></div><div><h3>Conclusion</h3><div>By non-invasively estimating blood viscosity from PPG, the diagnostic capabilities of wearable healthcare systems can be expanded to target various diseases related to the circulatory system. The demonstrated accuracy in physiologically relevant shear ranges supports the potential clinical application of this methodology.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108740"},"PeriodicalIF":4.9,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725676","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":"Fluid-structure interaction simulations in patient-specific coronary arteries with aneurysms: Viscoelastic or shear-thinning property of blood","authors":"C. Paz ,&nbsp;E. Suárez ,&nbsp;C. Gil ,&nbsp;S.I.S. Pinto","doi":"10.1016/j.cmpb.2025.108736","DOIUrl":"10.1016/j.cmpb.2025.108736","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Coronary artery aneurysm is a progressive and often asymptomatic condition with a prevalence ranging from 0.3 % to 5 %. This condition can lead to severe and potentially fatal complications. Given the challenges of conducting experiments on real patients, numerical simulations have emerged as a valuable alternative. This study aims to enhance the accuracy of hemodynamic analysis and fluid-structure interaction assessments by incorporating the viscoelastic properties of blood, which are often overlooked, in simulations of the right coronary artery with various aneurysm morphologies.</div></div><div><h3>Methods</h3><div>This research employs numerical simulations to analyse the hemodynamics and assess the one-way coupled fluid-structure interaction within the right coronary artery. The study utilised the simplified Phan-Thien/Tanner model to represent the viscoelastic properties of blood. Different aneurysm morphologies were simulated, and the results were compared with those obtained using the widely recognised Carreau model. The analysis focused on the time-average wall-shear stress, as well as the stress and deformation experienced by the aneurysm wall.</div></div><div><h3>Results</h3><div>The hemodynamic analysis demonstrated that the simplified Phan-Thien/Tanner model produced similar flow patterns to the Carreau model but resulted in a significant reduction of approximately 50 % in the time-average wall-shear stress. This reduction aligns with previous findings. Additionally, the study revealed substantial differences in the stress and deformation of the aneurysm wall, with the simplified Phan-Thien/Tanner model proving more accuracy. The largest deformations were observed in aneurysms with incipient and fusiform shapes, particularly in the divergent section of the proximal region. In the case of saccular aneurysms, the most compromised area was identified not within the aneurysm sac itself, but in the region of the artery just upstream.</div></div><div><h3>Conclusions</h3><div>Incorporating the viscoelastic properties of blood into fluid-structure interaction simulations significantly improves the accuracy of hemodynamic and structural assessments of coronary artery aneurysms. This study underscores the importance of considering these properties when evaluating aneurysm behaviour, which could have important implications for understanding the progression and potential rupture of aneurysms, thereby guiding more effective clinical interventions.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108736"},"PeriodicalIF":4.9,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725677","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":"Evaluation of the impacts of neuromuscular electrical stimulation based on cortico-muscular-cortical functional network","authors":"Jianpeng Tang ,&nbsp;Xugang Xi ,&nbsp;Ting Wang ,&nbsp;Lihua Li ,&nbsp;Jian Yang","doi":"10.1016/j.cmpb.2025.108735","DOIUrl":"10.1016/j.cmpb.2025.108735","url":null,"abstract":"<div><h3>Background and objective</h3><div>Neuromuscular electrical stimulation (NMES) has been extensively applied for recovery of motor functions. However, its impact on the cortical network changes related to muscle activity remains unclear, which is crucial for understanding the changes in the collaborative working patterns within the sensory-motor control system post-stroke.</div></div><div><h3>Methods</h3><div>In this research, we have integrated cortico-muscular interactions, intercortical interactions, and intramuscular interactions to propose a novel closed-loop network structure, namely the cortico-muscular-cortical functional network (CMCFN). The framework is endowed with the capability to distinguish the directionality of causal interactions and local frequency band characteristics through transfer spectral entropy (TSE). Subsequently, the CMCFN is applied to stroke patients to elucidate the potential influence of NMES on cortical physiological function changes during motor induction.</div></div><div><h3>Results</h3><div>The results indicate that short-term modulation by NMES significantly enhanced the cortico-muscular interactions of the contralateral cerebral hemisphere and the affected upper limb (p &lt; 0.001), while coexistence of facilitatory and inhibitory effects is observed in the intermuscular coupling across different electromyography (EMG) signals. Furthermore, following NMES treatment, the connectivity of the brain functional network is significantly strengthened, particularly in the γ frequency band (30–45 Hz), with marked improvements in the clustering coefficient and shortest path length (p &lt; 0.001).</div></div><div><h3>Conclusions</h3><div>As a new framework, CMCFN offers a novel perspective for studying motor cortical networks related to muscle activity.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108735"},"PeriodicalIF":4.9,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143705882","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":"Performance analysis of 2D and 3D image features for computer-assisted speech diagnosis of dental sibilants in Polish children","authors":"Agata Sage","doi":"10.1016/j.cmpb.2025.108716","DOIUrl":"10.1016/j.cmpb.2025.108716","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Sigmatism is a speech disorder concerning sibilants, and its diagnosis affects many Polish children of preschool age. The success of therapy often depends on early and accurate diagnosis. This paper presents research findings on using 2D and 3D (time-related) visual features to analyze the place of articulation, sibilance (the character of a gap between teeth that allows the articulation of sibilant sounds), and tongue positioning in four of twelve Polish sibilants:/s/,/z/,/ʦ/, and/dz/.</div></div><div><h3>Methods:</h3><div>A dedicated data acquisition system captured the stereovision stream during the speech therapy examination (201 speakers aged 4-8). The material contains 23 words and four logatomes. This study introduces 3D texture and shape features extracted for the mouth, lips, and tongue. The third dimension is the time of articulation, and the volumes reflect the movements of speech organs. The research compares the usability of 3D mode to a 2D approach (mouth texture features; mouth, lips, and tongue shape parameters) described in previous works. The statistical analysis includes Mann-Whitney U test to indicate the significant differences between selected articulation patterns for each sibilant and pronunciation aspect (considering p<span><math><mo>&lt;</mo></math></span>0.05).</div></div><div><h3>Results:</h3><div>Overall outcomes suggest the dominance of 3D time-related statistically significant features, especially describing the shape of a tongue. Analysis considering features with at least medium effect size showed that 3D features differentiate dental and interdental articulation in case of/s/,/z/, and/ʦ/, while in case of/dz/ significant parameters were 2D. The 3D mode prevails also in terms of sibilance: analysis of sounds/z/ and/ʦ/ results in 3D features only, but for/s/ and/dz/ outcomes include both 3D and 2D parameters. Analysis of the tongue positioning during articulation in terms of at least moderate effect size suggests a presence of features only in the case of affricates:/ʦ/ (3D features) and/dz/ (2D features). All parameters with at least medium effect size describe the shape of the tongue.</div></div><div><h3>Conclusions:</h3><div>This research proves the potential of visual data in building computer-aided speech diagnosis systems using non-contact recording tools. It highlights the usability of a 3D approach introduced in this paper. Results also emphasize the importance of tongue movement analysis.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108716"},"PeriodicalIF":4.9,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143679704","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 first explainable-AI-based workflow integrating forward-forward and backpropagation-trained networks of label-free multiphoton microscopy images to assess human biopsies of rare neuromuscular disease","authors":"Riccardo Scodellaro ,&nbsp;Jana Zschüntzsch ,&nbsp;Anna-Kathrin Hell ,&nbsp;Frauke Alves","doi":"10.1016/j.cmpb.2025.108733","DOIUrl":"10.1016/j.cmpb.2025.108733","url":null,"abstract":"<div><h3>Background and objective</h3><div>Diagnosis of rare neuromuscular diseases often relies on muscle biopsy analysis, which varies based on the evaluator's experience. Advances in deep learning show promise in improving diagnostic accuracy by identifying standardized features and phenotypic expressions in biopsy images. Explainable artificial intelligence extracts these features from the neural network's “black box,” ensuring compliance with European ethical standards for the use of clinical data in real-world applications. This study proposes a clinic-friendly workflow, based on explainable artificial intelligence. It combines forward-forward and backpropagation-trained convolutional networks to identify complementary features of Duchenne Muscular Dystrophy. Our proposal sets the forward-forward training, applied here for the first time on biomedical images, as a potential new standard for interpretable deep learning applications in clinics.</div></div><div><h3>Methods</h3><div>We analyzed a multiphoton microscopy dataset of 1600 images from 16 human muscle biopsies obtained during elective spinal surgery, combining autofluorescence, second and third harmonic generation signals. Class Activation Maps unveiled the dual decision-making process of the convolutional network, independently trained with both standard backpropagation and forward-forward algorithms. We evaluated the significance of the discovered features by using the Mann Whitney method. Entire biopsies were analyzed by providing an attention metric, computed as the weighted mean of all significant parameters.</div></div><div><h3>Results</h3><div>Backpropagation, gold standard for 35 years, and forward-forward achieved over 90 % accuracy in distinguishing healthy and diseased patients tissue. Class activation maps revealed that, when trained independently with both algorithms, the same network identifies Duchenne Muscular Dystrophy tissue by focusing on different features. Both methods identified intramuscular collagen as a key feature. Backpropagation also highlighted collagen waviness and fatty tissue. Forward-forward emphasized collagen density. We integrated these complementary insights, validated by significance analysis, into a standardized attention metric, allowing a multi-structural, quantitative assessment of tissue changes and highlighting areas for further clinical analysis.</div></div><div><h3>Conclusions</h3><div>Our workflow, using clinically routine biopsies and transparent diagnostic features, demonstrates the unique potential of forward-forward in providing novel, reliable, interpretable results from biomedical images. This paves the way for its dual use with backpropagation, shifting benchmarks by enabling the discovery of features potentially overlooked by backpropagation across biomedical datasets.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108733"},"PeriodicalIF":4.9,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143705883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing stability of heart disease prediction across imbalanced learning with interpretable Grow Network","authors":"Simon Bin Akter ,&nbsp;Sumya Akter ,&nbsp;Rakibul Hasan ,&nbsp;Md Mahadi Hasan ,&nbsp;David Eisenberg ,&nbsp;Riasat Azim ,&nbsp;Jorge Fresneda Fernandez ,&nbsp;Tanmoy Sarkar Pias","doi":"10.1016/j.cmpb.2025.108702","DOIUrl":"10.1016/j.cmpb.2025.108702","url":null,"abstract":"<div><h3>Background and objectives:</h3><div>Heart disease prediction models often face stability challenges when applied to public datasets due to significant class imbalances, unlike the more balanced benchmark datasets. These imbalances can adversely affect various stages of prediction, including feature selection, sampling, and modeling, leading to skewed performance, with one class often being favored over another.</div></div><div><h3>Methods:</h3><div>To enhance stability, this study proposes a Grow Network (GrowNet) architecture, which dynamically configures itself based on the data’s characteristics. To enhance GrowNet’s stability, this study proposes the use of TriDyn Dependence feature selection and Adaptive Refinement sampling, which ensure the selection of relevant features across imbalanced data and effectively manage class imbalance during training.</div></div><div><h3>Results:</h3><div>When evaluated on the benchmark UCI heart disease dataset, GrowNet has outperformed other models, achieving a specificity of 92%, sensitivity of 88%, precision of 90%, and F1 score of 90%. Further evaluation on three public datasets from the Behavioral Risk Factor Surveillance System (BRFSS), where heart disease cases constitute only about 6% of the data, has demonstrated GrowNet’s ability to maintain balanced performance, with an average specificity, sensitivity, and AUC-ROC of 77.67%, 81.67%, and 89.67%, respectively, while other models have exhibited instability. This represents a 22.8% improvement in handling class imbalance compared to prior studies. Additional tests on two public datasets from the National Health Interview Survey (NHIS) have confirmed GrowNet’s robustness and generalizability, with an average specificity, sensitivity, and AUC-ROC of 80.5%, 82.5%, and 90%, respectively, while other models have continued to demonstrate instability.</div></div><div><h3>Discussion:</h3><div>To enhance transparency, this study incorporates SHapley Additive exPlanations (SHAP) analysis, enabling healthcare professionals to understand the decision-making process and identify key risk factors for heart disease, such as bronchitis in midlife, renal dysfunction in the elderly, and depressive disorders in individuals aged 35-44.</div></div><div><h3>Conclusion:</h3><div>This study presents a robust, interpretable model to assist healthcare professionals in cost-effective, early heart disease detection by focusing on key risk factors, ultimately improving patient outcomes.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108702"},"PeriodicalIF":4.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698064","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":"Exploring emotional climate recognition in peer conversations through bispectral features and affect dynamics","authors":"Ghada Alhussein ,&nbsp;Mohanad Alkhodari ,&nbsp;Ioannis Ziogas ,&nbsp;Charalampos Lamprou ,&nbsp;Ahsan H. Khandoker ,&nbsp;Leontios J. Hadjileontiadis","doi":"10.1016/j.cmpb.2025.108695","DOIUrl":"10.1016/j.cmpb.2025.108695","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Emotion recognition in conversations using artificial intelligence (AI) has gained significant attention due to its potential to provide insights into human social behavior. This study extends AI-based emotion recognition to the recognition of emotional climate (EC), which reflects the joint emotional atmosphere dynamically created and perceived by peers during conversations. The objective is to propose and evaluate a novel approach, MLBispec, for EC recognition using speech signals.</div></div><div><h3>Methods:</h3><div>The MLBispec approach involves time-windowed bispectral analysis of conversational speech signals to extract features related to nonlinear harmonic interactions. These features are combined with peers’ affect dynamics, derived from emotion labeling for the same time windows, to form an extended feature set. The combined feature set is then fed into machine learning (ML) classifiers. MLBispec was evaluated on the IEMOCAP, K-EmoCon, and SEWA open-access datasets, which provide 2D emotion annotations (arousal and valence) divided into low/high classes. Additionally, cross-lingual experiments were conducted to test the framework’s generalization across languages.</div></div><div><h3>Results:</h3><div>Experimental results demonstrated that MLBispec outperformed previous deep learning-based state-of-the-art approaches in speech emotion recognition, achieving accuracies of 82.6% for arousal and 75.4% for valence. The framework’s incorporation of both qualitative and quantitative EC measurements enhanced its ability to characterize the dynamic speech representations of conversational affective structures. Cross-lingual experiments further validated the robustness of MLBispec.</div></div><div><h3>Conclusions:</h3><div>The findings highlight the effectiveness of MLBispec in objectively recognizing peers’ EC during conversations, setting a new standard for practical emotionally-aware applications. These include point-of-care healthcare, human–computer interfaces (HCI), and large-language models (LLMs). By enabling dynamic and reliable EC recognition, MLBispec paves the way for advancements in emotionally intelligent systems.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"265 ","pages":"Article 108695"},"PeriodicalIF":4.9,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143695950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}