Bioengineering最新文献

{"title":"e-Health Strategy for Surgical Prioritization: A Methodology Based on Digital Twins and Reinforcement Learning.","authors":"Fabián Silva-Aravena, Jenny Morales, Manoj Jayabalan","doi":"10.3390/bioengineering12060605","DOIUrl":"10.3390/bioengineering12060605","url":null,"abstract":"<p><p>This article presents a methodological framework for elective surgery scheduling based on the integration of patient-specific Digital Twins (DTs) and reinforcement learning (RL). The proposed approach aims to support the future development of an intelligent e-health platform for dynamic, data-driven prioritization of surgical patients. We generate prioritization scores by modeling clinical, economic, behavioral, and social variables in real time and optimize access through a reinforcement learning engine designed to maximize long-term system performance. The methodology is designed as a modular, transparent, and interoperable digital decision-support architecture aligned with the goals of organizational transformation and equitable healthcare delivery. To validate its potential, we simulate realistic surgical scheduling scenarios using synthetic patient data. Results demonstrate substantial improvements compared withto traditional strategies, including a 55.1% reduction in average wait time, a 41.9% decrease in clinical risk at surgery, a 16.1% increase in OR utilization, and a significant increase in the prioritization of socially vulnerable patients. These findings highlight the value of the proposed framework as a foundation for future smart healthcare platforms that support transparent, adaptive, and ethically aligned decision-making in surgical scheduling.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189496/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep-Learning-Based Computer-Aided Grading of Cervical Spinal Stenosis from MR Images: Accuracy and Clinical Alignment.","authors":"Zhiling Wang, Xinquan Chen, Bin Liu, Jinjin Hai, Kai Qiao, Zhen Yuan, Lianjun Yang, Bin Yan, Zhihai Su, Hai Lu","doi":"10.3390/bioengineering12060604","DOIUrl":"10.3390/bioengineering12060604","url":null,"abstract":"<p><p><b>Objective:</b> This study aims to apply different deep learning convolutional neural network algorithms to assess the grading of cervical spinal stenosis and to evaluate their consistency with clinician grading results as well as clinical manifestations of patients. <b>Methods:</b> We retrospectively enrolled 954 patients with cervical spine magnetic resonance imaging (MRI) data and medical records from the Fifth Affiliated Hospital of Sun-Yat Sen University. The Kang grading method for sagittal MR images of the cervical spine and the spinal cord compression ratio for horizontal MR images of the cervical spine were adopted for cervical spinal canal stenosis grading. The collected data were randomly divided into training/validation and test sets. The training/validation sets were processed by various image preprocessing and annotation methods, in which deep learning convolutional networks, including classification, target detection, and key point localization models, were applied. The predictive grading of the test set by the model was finally contrasted with the grading results of the clinicians, and correlation analysis was performed with the clinical manifestations of the patients. <b>Result:</b> The EfficientNet_B5 model achieved a five-fold cross-validated accuracy of 79.45% and near-perfect agreement with clinician grading on the test set (<i>κ</i>= 0.848, 0.822), surpassing resident-clinician consistency (<i>κ</i> = 0.732, 0.702). The model-derived compression ratio (0.45 ± 0.07) did not differ significantly from manual measurements (0.46 ± 0.07). Correlation analysis showed moderate associations between model outputs and clinical symptoms: EfficientNet_B5 grades (<i>r</i> = 0.526) were comparable to clinician assessments (<i>r</i> = 0.517, 0.503) and higher than those of residents (<i>r</i> = 0.457, 0.448). <b>Conclusion:</b> CNN models demonstrate strong performance in the objective, consistent, and efficient grading of cervical spinal stenosis severity, offering potential clinical value in automated diagnostic support.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189467/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Half Squat Mechanical Analysis Based on PBT Framework.","authors":"Miguel Rodal, Emilio Manuel Arrayales-Millán, Mirvana Elizabeth Gonzalez-Macías, Jorge Pérez-Gómez, Kostas Gianikellis","doi":"10.3390/bioengineering12060603","DOIUrl":"10.3390/bioengineering12060603","url":null,"abstract":"<p><p>Muscular strength is an essential factor in sports performance and general health, especially for optimizing mechanical power, as well as for injury prevention. The present study biomechanically characterized the half squat (HS) using a systemic structural approach based on mechanical power, called Power-Based Training (PBT), through which four phases of the movement were determined (acceleration and deceleration of lowering and lifting). Five weightlifters from the Mexican national team (categories U17, U20, and U23) participated, who performed five repetitions per set of HS with progressive loads (20%, 35%, 50%, 65%, and 80% of the one repetition maximum). The behavior of the center of mass of the subject-bar system was recorded by photogrammetry, calculating position, velocity, acceleration, mechanical power, and mechanical work. The results showed a significant reduction in velocity, acceleration, and mechanical power as the load increases, as well as variations in the duration and range of displacement per phase. These findings highlight the importance of a detailed analysis to understand the neuromuscular demands of HS and to optimize its application. The PBT approach and global center of mass analysis provide a more accurate view of the mechanics of this exercise, facilitating its application in future research, as well as in performance planning and monitoring.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189782/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Multi-Label Chest X-Ray Classification Using an Improved Ranking Loss.","authors":"Muhammad Shehzad Hanif, Muhammad Bilal, Abdullah H Alsaggaf, Ubaid M Al-Saggaf","doi":"10.3390/bioengineering12060593","DOIUrl":"10.3390/bioengineering12060593","url":null,"abstract":"<p><p>This article addresses the non-trivial problem of classifying thoracic diseases in chest X-ray (CXR) images. A single CXR image may exhibit multiple diseases, making this a multi-label classification problem. Additionally, the inherent class imbalance makes the task even more challenging as some diseases occur more frequently than others. Our methodology is based on transfer learning aiming to fine-tune a pretrained DenseNet121 model using CXR images from the NIH Chest X-ray14 dataset. Training from scratch would require a large-scale dataset containing millions of images, which is not available in the public domain for this multi-label classification task. To address class imbalance problem, we propose a rank-based loss derived from the Zero-bounded Log-sum-exp and Pairwise Rank-based (ZLPR) loss, which we refer to as focal ZLPR (FZLPR). In designing FZLPR, we draw inspiration from the focal loss where the objective is to emphasize hard-to-classify examples (instances of rare diseases) during training compared to well-classified ones. We achieve this by incorporating a \"temperature\" parameter to scale the label scores predicted by the model during training in the original ZLPR loss function. Experimental results on the NIH Chest X-ray14 dataset demonstrate that FZLPR loss outperforms other loss functions including binary cross entropy (BCE) and focal loss. Moreover, by using test-time augmentations, our model trained using FZLPR loss achieves an average AUC of 80.96% which is competitive with existing approaches.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189069/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Graph Representation Learning for the Prediction of Medication Usage in the UK Biobank Based on Pharmacogenetic Variants.","authors":"Bill Qi, Yannis J Trakadis","doi":"10.3390/bioengineering12060595","DOIUrl":"10.3390/bioengineering12060595","url":null,"abstract":"<p><p>Ineffective treatment and side effects are associated with high burdens for the patient and society. We investigated the application of graph representation learning (GRL) for predicting medication usage based on individual genetic data in the United Kingdom Biobank (UKBB). A graph convolutional network (GCN) was used to integrate interconnected biomedical entities in the form of a knowledge graph as part of a machine learning (ML) prediction model. Data from The Pharmacogenomics Knowledgebase (PharmGKB) was used to construct a biomedical knowledge graph. Individual genetic data (<i>n</i> = 485,754) from the UKBB was obtained and preprocessed to match with pharmacogenetic variants in the PharmGKB. Self-reported medication usage labels were obtained from UKBB data field 20003. We hypothesize that pharmacogenetic variants can predict the impact of medications on individuals. We assume that an individual using a medication on a regular basis experiences a net benefit (vs. side-effects) from the medication. ML models were trained to predict medication usage for 264 medications. The GCN model significantly outperformed both a baseline logistic regression model (<i>p</i>-value: 1.53 × 10^-9) and a deep neural network model (<i>p</i>-value: 8.68 × 10^-8). The GCN model also significantly outperformed a GCN model trained using a random graph (GCN-random) (<i>p</i>-value: 5.44 × 10^-9). A consistent trend of medications with higher sample sizes having better performance was observed, and for several medications, a high relative rank of the medication (among multiple medications) was associated with greater than 2-fold higher odds of usage of the medication. In conclusion, a graph-based ML approach could be useful in advancing precision medicine by prioritizing medications that a patient may need based on their genetic data. However, further research is needed to improve the quality and quantity of genetic data and to validate our approach using more reliable medication labels.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189576/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lateral Cortical Fixation as the Optimal Strategy for Achieving Stability in Rib Fractures: A Patient-Specific Finite Element Analysis.","authors":"Xiang Zhang, Xuejun Lan, Wang Shen, Qinghua Zhou","doi":"10.3390/bioengineering12060594","DOIUrl":"10.3390/bioengineering12060594","url":null,"abstract":"<p><p>The surgical stabilization of rib fractures helps maintain chest wall stability and reduces respiratory complications. This study aimed to identify the key biomechanical parameters for evaluating the stability of rib fracture fixation using finite element analysis (FEA) and compare four rib fixation configurations-intramedullary rib splint (IRS), locking plate (LP), claw-shape plate, and intrathoracic plate (IP)-using biomechanical analysis. Forty patient-specific FEA models of fourth-rib fractures were constructed using the computed tomography scans of 10 patients. Maximum implant displacement (MID), maximum rib fracture displacement, maximum implant von Mises stress (MIVMS), maximum rib von Mises stress, maximum rib strain, and maximum interfragmentary gap (MIG) were assessed by simulating the anterior and posterior loads on the ribs during postoperative frontal collision. The fixation stabilities were evaluated using entropy scores. MIVMS, MIG, and MID exhibited the highest weighting coefficients. Lateral cortical fixation strategies, particularly LP configuration, demonstrated superior biomechanical performance compared with IRS and IP systems. The composite score of the LP was significantly higher than that of the other modalities. MIVMS, MIG, and MID were identified as critical parameters for evaluating the rib fracture fixation stability, and the lateral cortical fixation strategy (LP) enhanced the structural stability of rib fracture fixation.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189894/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Dai et al. Comparison of Bone Bruise Pattern Epidemiology between Anterior Cruciate Ligament Rupture and Patellar Dislocation Patients-Implications of Injury Mechanism. <i>Bioengineering</i> 2023, <i>10</i>, 1366.","authors":"Ruilan Dai, Yue Wu, Yanfang Jiang, Hongshi Huang, Wenqiang Yan, Huijuan Shi, Qingyang Meng, Shuang Ren, Yingfang Ao","doi":"10.3390/bioengineering12060598","DOIUrl":"10.3390/bioengineering12060598","url":null,"abstract":"<p><p>In the original publication [...].</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189665/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast and Accurate Sperm Detection Algorithm for Micro-TESE in NOA Patients.","authors":"Mahmoud Mohamed, Konosuke Kachi, Kohei Motoya, Masashi Ikeuchi","doi":"10.3390/bioengineering12060601","DOIUrl":"10.3390/bioengineering12060601","url":null,"abstract":"<p><strong>Purpose: </strong>Non-obstructive azoospermia (NOA) presents major challenges in assisted reproductive technology (ART) due to the extremely low number of viable sperm within testicular tissue. In Micro-TESE procedures, embryologists manually search for sperm under DIC microscopy-a slow, labor-intensive process. We aim to streamline this process with an efficient computational detection tool.</p><p><strong>Methods: </strong>We present SD-CLIP (Sperm Detection using Classical Image Processing), a lightweight, real-time algorithm that simulates sperm structure detection from unstained DIC images. The model first identifies convex sperm head candidates based on shape and width using edge gradients, then confirms the presence of a tail via principal component analysis (PCA) of pixel clusters.</p><p><strong>Results: </strong>Compared to the MB-LBP + AKAZE method, SD-CLIP improved processing speed by 4× and achieved a 3.8× higher posterior probability ratio, making detected sperm candidates significantly more reliable. Evaluation was performed on both human Micro-TESE and mouse testis images, demonstrating robustness in low-sperm environments.</p><p><strong>Conclusions: </strong>SD-CLIP simulates a domain-specific image interpretation model that identifies sperm morphology with high specificity. It requires minimal computational resources, supports real-time integration, and could be extended to automated sperm extraction systems. This tool has clinical value for accelerating Micro-TESE and increasing success rates in ART for NOA patients.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189846/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Injectable and Assembled Calcium Sulfate/Magnesium Silicate 3D Scaffold Promotes Bone Repair by In Situ Osteoinduction.","authors":"Wei Zhu, Tianhao Zhao, Han Wang, Guangli Liu, Yixin Bian, Qi Wang, Wei Xia, Siyi Cai, Xisheng Weng","doi":"10.3390/bioengineering12060599","DOIUrl":"10.3390/bioengineering12060599","url":null,"abstract":"<p><p>(1) Background: Osteonecrosis of the femoral head (ONFH), caused by insufficient blood supply, leads to bone tissue death. Current treatments lack effective bone regeneration materials to reverse disease progression. This study introduces an injectable and self-setting 3D porous bioceramic scaffold (Mg@Ca), combining MgO + SiO₂ mixtures with α-hemihydrate calcium sulfate, designed to promote bone repair through in situ pore formation and osteoinduction. (2) Methods: In vitro experiments evaluated human bone marrow mesenchymal stem cell (h-BMSC) proliferation, differentiation, and osteogenic marker expression in Mg@Ca medium. Transcriptome sequencing identified bone development-related pathways. In vivo efficacy was assessed in a rabbit model of ONFH to evaluate bone repair. (3) Results: The Mg@Ca scaffold demonstrated excellent biocompatibility and supported h-BMSC proliferation and differentiation, with significant up-regulation of <i>COL1A1</i> and <i>BGLAP</i>. Transcriptome analysis revealed activation of the PI3K-Akt signaling pathway, critical for osteogenesis. In vivo results confirmed enhanced trabecular density and bone volume compared to controls, indicating effective bone repair and regeneration. (4) Conclusions: The Mg@Ca scaffold offers a promising therapeutic approach for ONFH, providing a minimally invasive solution for bone defect repair while stimulating natural bone regeneration. Its injectable and self-setting properties ensure precise filling of bone defects, making it suitable for clinical applications.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unraveling the Scientific Landscape of Osteoarthritis: Dynamics of Publications over Five Decades.","authors":"Roxana Maria Sanziana Pavel, Andrei-Flavius Radu, Ada Radu, Bogdan Uivaraseanu, Gabriela Bungau, Delia Mirela Tit, Delia Carmen Nistor Cseppento, Paul Andrei Negru","doi":"10.3390/bioengineering12060602","DOIUrl":"10.3390/bioengineering12060602","url":null,"abstract":"<p><p>Osteoarthritis is a disabling condition with highly complex overall management and persistent shortcomings, contributing significantly to the global disease burden. Although research in the field has grown considerably in recent years alongside technological advancements, a cohesive and structured understanding of the evolution of the scientific literature, particularly regarding clinical management and outcome evaluation, remains insufficiently developed. To date, most bibliometric analyses in osteoarthritis have focused narrowly on specific subdomains, leaving a notable gap in comprehensive assessments of the broader clinical framework. This study addresses that gap through an integrated, structured, and visual approach using multiple bibliometric techniques targeting osteoarthritis diagnosis and management, aiming to guide future research and improve strategic development. Scientific publication in osteoarthritis has expanded exponentially, peaking in 2024 with 1234 documents. The United States led in both output and citation impact, while China showed rapid growth. <i>Osteoarthritis and Cartilage</i> emerged as the most influential journal. Australian institutions, especially the University of Sydney, demonstrated a remarkable ascent. Five global research clusters were identified, with the U.S. as the central node and Australia serving as a bridge between Western and Asian collaborations. Research themes evolved toward integrated models connecting biological mechanisms, therapeutic strategies, and patient-centered outcomes. This bibliometric assessment underscores exponential growth in osteoarthritis research and highlights the urgent need for more personalized, multidimensional evaluation strategies to enhance clinical translation.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189298/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}