Computer Methods in Biomechanics and Biomedical Engineering最新文献

{"title":"A novel framework for diabetic risk prediction using SCAW-Net integrated with TabNet architecture.","authors":"Usha V, Rajalakshmi N R","doi":"10.1080/10255842.2025.2566962","DOIUrl":"https://doi.org/10.1080/10255842.2025.2566962","url":null,"abstract":"<p><p>Blood glucose levels are essential for metabolism and brain function; insulin regulates sugar to prevent hypo- and hyperglycemia. Proper control prevents diabetic complications from insulin deficiency or resistance. Rapid, precise diabetes identification is critical for effective care. This study proposes SCAW-Net within TabNet to boost prediction accuracy and computational speed, compared with AdaBoost, XGBoost, Bagging, and Random Forest. Trained on diabetes features and tested on multiple datasets, the model achieved 98.9% accuracy, outperforming others. Consistent results on complex, imbalanced data validate SCAW-Net in TabNet as a promising real-world diabetes prediction tool, supporting timely clinical intervention and improved patient management outcomes.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1-19"},"PeriodicalIF":1.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145214100","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{"title":"RETRACTED ARTICLE: Human vulnerability assessment based on bullet motion and cavity expansion model with tissue identification.","authors":"Yining Jia, Yaoke Wen, Fangdong Dong, Bin Qin, Ronghua Liu","doi":"10.1080/10255842.2023.2294263","DOIUrl":"10.1080/10255842.2023.2294263","url":null,"abstract":"<p><p>We, the authors, Editors and Publisher of the journal <i>Computer Methods in Biomechanics and Biomedical Engineering</i>, have retracted the following article:Jia, Y., Wen, Y., Dong, F., Qin, B., & Liu, R. (2024). Human vulnerability assessment based on bullet motion and cavity expansion model with tissue identification. <i>Computer Methods in Biomechanics and Biomedical Engineering</i>, 1-15. https://doi.org/10.1080/10255842.2023.2294263Since publication, the authors noticed an error in the setting of the model parameters during post-publication review of the methods and results.As this directly impacts the validity of the reported results and conclusions, the authors alerted the issue to the Editor and Publisher. All have agreed to retract the article to ensure the integrity of the scholarly record.We have been informed in our decision-making by our editorial policies and the COPE guidelines.The retracted article will remain online to maintain the scholarly record, but it will be digitally watermarked on each page as 'Retracted'.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"i-xv"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139571989","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":"Advanced design and classification of wearable near-infrared spectroscopy device using temporal channel reconfiguration multi-graph convolutional neural networks for motor activity.","authors":"V Akila, A Shirly Edward, J Anita Christaline","doi":"10.1080/10255842.2025.2510370","DOIUrl":"10.1080/10255842.2025.2510370","url":null,"abstract":"<p><p>In this paper, advanced design and classification of wearable near-infrared spectroscopy device using temporal channel reconfiguration multi-graph convolutional neural networks for motor activity (WNISD-TRMCNN) are proposed. Input data is collected from real-time fNIRS data. The input data are pre-processed using event-triggered consensus Kalman filtering (ETCKF) to remove motion artefacts. Then, the pre-processed data is fed to TRMCNN for classifying wearable NIRS as oxygenated hemoglobin (HbO) and deoxygenated hemoglobin (HbR). To enhance classification, Young's double slit experiment optimization algorithm (YDSEOA) is applied. Performance metrics such as accuracy, precision, AUC, and processing time demonstrate the proposed method's superiority over existing techniques.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"2017-2031"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144276523","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":"Optimizing functionally graded tibial components for total knee replacements: a finite element analysis and multi-objective optimization study.","authors":"Mohaddeseh Fatemi, Zohreh Bahrami, Marjan Bahraminasab, Farideh Nabizadeh Chianeh","doi":"10.1080/10255842.2024.2358358","DOIUrl":"10.1080/10255842.2024.2358358","url":null,"abstract":"<p><p>The optimal design of complex engineering systems requires tracing precise mathematical modeling of the system's behavior as a function of a set of design variables to achieve the desired design. Despite the success of current tibial components of knee implants, the limited lifespan remains the main concern of these complex systems. The mismatch between the properties of engineered biomaterials and those of biological materials leads to inadequate bonding with bone and the stress-shielding effect. Exploiting a functionally graded material for the stem of the tibial component of knee implants is attractive because the properties can be designed to vary in a certain pattern, meeting the desired requirements at different regions of the knee joint system. Therefore, in this study, a Ti6Al4V/Hydroxyapatite functionally graded stem with a laminated structure underwent simulation-based multi-objective design optimization for a tibial component of the knee implant. Employing finite element analysis and response surface methodology, three material design variables (stem's central diameter, gradient factor, and number of layers) were optimized for seven objective functions related to stress-shielding and micro-motion (including Maximum stress on the cancellous bone, maximum and mean stresses on predefined paths, the standard deviation of mean stress on paths, maximum and mean micro-motions at the bone-implant interface and the standard deviation of mean micro-motion). Then, the optimized functionally graded stem with 6 layers, a central diameter of 5.59 mm, and a gradient factor of 1.31, was compared with a Ti6Al4V stem for various responses. In stress analysis, the optimal stem demonstrated a 1.92% improvement in cancellous bone stress while it had no considerable influence on the maximum, mean, and standard deviation of stresses on paths. In micro-motion analysis, the maximum, mean, and standard deviation of mean micro-motion at the interface were enhanced by 24.31%, 39.53%, and 19.77%, respectively.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"2064-2082"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141159185","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":"Identification of potential biomarkers for pancreatic ductal adenocarcinoma: a bioinformatics analysis.","authors":"JagadeeswaraRao G, SivaPrasad A","doi":"10.1080/10255842.2024.2356648","DOIUrl":"10.1080/10255842.2024.2356648","url":null,"abstract":"<p><p>PDA is an aggressive cancer with a 5-year survival rate, which is very low. There is no effective prognosis or therapy for PDA because of the lack of target biomarkers. The objective of this article is to identify the target biomarkers for PDA using a bioinformatics approach. In this work, we have analysed the three microarray datasets from the NCBI GEO database. We used the Geo2R tool to analyse the microarray data with the Benjamini and Hochberg false discovery rate method, and the significance level cut-off was set to 0.05. We have identified 659 DEGs from the datasets. There are a total of 15 hub genes that were selected from the PPI network constructed using the STRING application. Furthermore, these 15 genes were evaluated on PDA patients using TCGA and GTEx databases in (GEPIA). The online tool DAVID was used to analyse the functional annotation information for the DEGs. The functional pathway enrichment was performed on the GO and KEGG. The hub genes were mainly enriched for cell division, chromosome segregation, protein binding and microtubule binding. Further, the gene alteration study was performed using the cBioportal tool and screened out six hub genes (ASPM, CENPF, BIRC5, TTK, DLGAP5, and TOP2A) with a high alteration rate in PDA samples. Furthermore, Kaplan-Meier survival analysis was performed on the six hub genes and identified poor-survival outcomes that may be involved in tumorigenesis and PDA development. So, this study concludes that, these six hub genes may be potential prognostic biomarkers for PDA.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"2049-2063"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141077314","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":"Band power feature part-based convolutional neural network with African vulture optimization fostered channel selection for EEG classification.","authors":"Vairaprakash Selvaraj, Manjunathan Alagarsamy, Kavitha Datchanamoorthy, Geethalakshmi Manickam","doi":"10.1080/10255842.2024.2356633","DOIUrl":"10.1080/10255842.2024.2356633","url":null,"abstract":"<p><p>The electroencephalogram-based motor imagery (MI-EEG) classification task is significant for brain-computer interface (BCI). EEG signals need a lot of channels to be acquired, which makes it difficult to use in real-world applications. Choosing the optimal channel subset without severely impacting the classification performance is a problem in the field of BCI. To overwhelm this problem, a band power feature part-based convolutional neural network with African vulture optimization fostered channel selection for EEG classification (PCNNC-AVOACS-EEG) is proposed in this article. Initially, the input EEG signals are taken from BCI competition IV, dataset 1. Then the input EEG signals are pre-processed by contrast-limited adaptive histogram equalization filtering. These pre-processed EEG signals are extracted by hexadecimal local adaptive binary pattern (HLABP) method. This HLABP method extracts the features of alpha and beta bands from the EEG segments. Each EEG channel's band power data are utilized as features for a PCNNC to exactly classify the EEG into 3 classes: two MI states and idle state. The AVOA is applied within the band power feature PCNNC for channel selection, wherein channel selection aids to enhance the categorization accuracy on test set that is a vital indicator for real-time BCI applications. The proposed method is activated in python. From the experiment, the proposed technique attains 17.91%, 20.46% and 18.146% higher accuracy; 14.105%, 15.295% and 5.291% higher area under the curve and 70%, 60% and 65.714% lower computation time compared with the existing approaches.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"2003-2016"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141441029","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":"Retraction.","authors":"","doi":"10.1080/10255842.2024.2359878","DOIUrl":"10.1080/10255842.2024.2359878","url":null,"abstract":"","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"xvi"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141307296","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":"Performance parametric formulation of carbon fiber-reinforced composite locking bone implant plates based on finite-element analysis.","authors":"Wares Chancharoen, Jirapong Pansai, Teeravut Boonchuay, Somchart Saeya, Raj Das, Thanapon Chobpenthai, Sontipee Aimmanee","doi":"10.1080/10255842.2024.2358362","DOIUrl":"10.1080/10255842.2024.2358362","url":null,"abstract":"<p><p>The treatment of Giant Cell Tumor <b>(</b>GCT<b>)</b> in the distal radius poses challenges due to the intricate anatomical features of the bone. It often necessitates the use of long implant plates or the interconnection of multiple short plates after tumor excision. However, the deployment of metal plates may increase the risk of screw loosening and various complications. To address these challenges, this study proposes the adoption of carbon fiber-reinforced PEEK (CFRP) as the base material. As a unique strategy, performance parameters (PP) were developed to compare CFRP implant plates with a Ti-6Al-4V plate using the Finite-element Method. The focus was on four elements: the screw axial force, bone growth, callus formation, and bone resorption. The investigation into the screw axial force involved analyzing the internal force of the screw. The remaining parameters were evaluated using the stress, strain, or elastic energy induced in the bones. The findings showed that the second screw endured the largest screw axial force, measuring 10.16 N under a 90-degree 10-N loading at the translocated bone. The model without a callus exerted a significantly greater force on the screw than the model with a callus, leading to screw loosening in the early stage of treatment. The maximum PP, reached 1.62, was achieved with an angle-ply <b>[</b>45₆<b>/-</b>45₆<b>]</b> laminate, featuring a weighting fraction of 0.7 for bone growth and 0.1 for the other parameters. This study provides a generalized methodology for assessing the performances of CFRP implants and offers guidelines for future development in composite implant plate technology.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"2083-2099"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141160682","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":"Authentication with a one-dimensional CNN model using EEG-based brain-computer interface.","authors":"Ahmed Yassine Ferdi, Abdelkader Ghazli","doi":"10.1080/10255842.2024.2355490","DOIUrl":"10.1080/10255842.2024.2355490","url":null,"abstract":"<p><p>Brain-computer interface (BCI) technology uses electroencephalogram (EEG) signals to create a direct interaction between the human body and its surroundings. Motor imagery (MI) classification using EEG signals is an important application that can help a rehabilitated or motor-impaired stroke patient perform certain tasks. Robust classification of these signals is an important step toward making the use of EEG more practical in many applications and less dependent on trained professionals. Deep learning methods have produced impressive results in BCI in recent years, especially with the availability of large electroencephalography (EEG) data sets. Dealing with EEG-MI signals is difficult because noise and other signal sources can interfere with the electrical amplitude of the brain, and its generalization ability is limited, so it is difficult to improve EEG classifiers. To address these issues, this paper presents a methodology based on one-dimensional convolutional neural networks (1-D CNN) for motor imagery (MI) recognition for the right hand, left hand, feet, and sedentary task. The proposed model is a lightweight model with fewer parameters and has an accuracy of 91.75%. Then, in an innovative exploitation of the four output classes, there is an idea that allows people with disabilities who are deprived of security measures, such as entering a secret code, to use the output classification, such as password codes. It is also an idea for a unique authentication system that is more secure and less vulnerable to theft or the like for a healthy person at the same time.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1969-1980"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141065646","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":"Finite element analysis of proximal femur bionic nail for treating intertrochanteric fractures in osteoporotic bone.","authors":"Xiang Shen, Hao Guo, Guangxin Chen, Hongyu Lian, Wei Guo, Zhen Wang, Zihao Xu, Zitao Li","doi":"10.1080/10255842.2024.2355492","DOIUrl":"10.1080/10255842.2024.2355492","url":null,"abstract":"<p><p>This study compared the biomechanical characteristics of proximal femur bionic nail (PFBN) and proximal femoral nail antirotation (PFNA) in treating osteoporotic femoral intertrochanteric fractures using finite element analysis. Under similar bone density, the PFBN outperforms the PFNA in maximum femoral displacement, internal fixation displacement, stress distribution in the femoral head and internal fixation components, and femoral neck varus angle. As the bone density decreases, the PFBN's biomechanical advantages over PFNA become more pronounced. This finding suggests that the PFBN is superior for treating osteoporotic intertrochanteric femoral fractures.</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1991-2002"},"PeriodicalIF":1.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141065648","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}