BioMedical Engineering OnLine最新文献

{"title":"Game-based and gamification-enhanced telerehabilitation for physical therapy in people with multiple sclerosis: a scoping review.","authors":"Somayeh Norouzi-Ghazbi, Shaghayegh Mirbaha, Jaeden Michael Mariyanayagam, Zoe Li, Jan Andrysek, Roger Goldstein, Sander L Hitzig","doi":"10.1186/s12938-026-01589-4","DOIUrl":"10.1186/s12938-026-01589-4","url":null,"abstract":"<p><strong>Introduction: </strong>People with multiple sclerosis (MS) commonly experience balance, gait, and upper-limb impairments that require long-term physical therapy (PT). Home-based telerehabilitation can improve access to therapy, and game-enhanced interventions (serious games/exergaming) and gamification elements may enhance engagement and adherence.</p><p><strong>Methods: </strong>This scoping review examined the current evidence and explored the implementation considerations of gamification-based telerehabilitation (GBT) systems designed to deliver home-based PT for people with MS. Following PRISMA-ScR guidance, the databases OVID Medline, OVID EMBASE, CINAHL, and EBSCO were systematically searched between January 2010 and November 2024. Fifteen studies satisfied the inclusion criteria. Study quality was appraised using the Downs and Black checklist, and evidence levels were classified according to a modified Sackett scale.</p><p><strong>Results: </strong>The majority of the 15 studies were of fair-to-good methodological quality, and all used a quantitative design with small sample sizes. The included studies mainly focused on whole-body physical rehabilitation. Eleven studies used commercial games, while others developed customized hardware or software modules. No serious adverse events were reported. High levels of participant satisfaction and adherence in home settings supported feasibility. The effectiveness of GBT for people with MS is still uncertain because the results are mixed. Across controlled trials, balance and postural control outcomes showed the most consistent improvements, whereas fatigue, QoL, and participation outcomes were mixed and often not significant between the groups.</p><p><strong>Conclusion: </strong>GBT solutions may serve as a therapeutic alternative to conventional therapy, particularly when access to traditional services is limited or when individuals with MS experience reduced motivation to maintain their exercise routines. More research is needed to find out which measures respond best, which subgroups benefit most, and to provide stronger evidence through the use of both within-group and between-group comparisons.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13377992/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148004444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nanomedicine strategies for overcoming the blood-brain barrier in central nervous system drug delivery: mechanisms, advances, and challenges.","authors":"Mukul Pratap Singh, Ananda Kumar Chettupalli, Sarad Pawar Naik Bukke, Bharath Kumar Mamilla Mugaiahgari, Pavani Uppu, Priyanshu Pathak, Bayapa Reddy Narapureddy","doi":"10.1186/s12938-026-01582-x","DOIUrl":"https://doi.org/10.1186/s12938-026-01582-x","url":null,"abstract":"<p><p>Central nervous system (CNS) disorders remain one of the most significant challenges in medicine given the restrictive properties of the blood-brain barrier (BBB), which substantially reduces the delivery of most therapeutics to penetrate the brain. Although there has been considerable progress in the generation of support neuroactive substances, approximately 98% of possible CNS medicines never get to effective milligram proofs in the brain, mostly due to exclusion from BBB. This research offers an in-depth and analytical assessment of approaches utilizing nanomedicine aimed at addressing the limitations of the blood-brain barrier (BBB) and improving the delivery of drugs to the brain. It thoroughly explores the structural and functional properties of the BBB, identifies the major obstacles hindering molecular movement, and investigates the cellular and molecular processes that regulate the movement of nanoparticles. Significant focus is given to various nanocarrier platforms, encompassing lipid-based systems (such as liposomes, solid lipid nanoparticles, and nanostructured lipid carriers), polymeric nanoparticles, micelles, dendrimers, nanogels, nanoemulsions, exosomes, carbon nanotubes, and metallic nanoparticles. These platforms are particularly noted for their important functions in improving drug stability, bioavailability, controlled release, and precision targeting within the central nervous system. Furthermore, recent developments in innovative technologies, including nanofiber scaffolds and multidimensional (3D-6D) printing methods for neurological uses, are also discussed. The paper also analyses translational hurdles, safety issues, and toxicity factors that persistently obstruct the clinical application of nanomedicine-based CNS therapeutics. This paper highlights the revolutionary potential of nanotechnology in brain drug delivery and offers insights into future strategies for the rational design of safe and effective nanocarriers to meet unmet demands in CNS disease therapy.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2026-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147986514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel spinal orthosis with embedded shape memory alloy for adolescent idiopathic scoliosis.","authors":"Peikun Zhu, Chunxiao Lu, Xinjing Wu, Jinzhu Bai","doi":"10.1186/s12938-026-01588-5","DOIUrl":"10.1186/s12938-026-01588-5","url":null,"abstract":"<p><p>Bracing is the most effective measure for the treatment of mild-to-moderate adolescent idiopathic scoliosis (AIS). However, the balance between three-dimensional correction of scoliosis and wear comfort is still not ideal. To design a novel bracing with embedded shape memory alloy for the treatment of AIS that can improve patients' comfort and provide sustained and effective three-dimensional correction force, as well as to preliminarily verify its clinical efficacy. A Ni‒Ti shape memory alloy material was constructed with 20 ℃ martensite and 0 ℃ austenite. On the basis of the traditional rigid thoracolumbosacral scoliosis braces, when considering the three-dimensional correction of scoliosis and the wear comfort of the patient, a novel spinal orthosis with embedded shape memory alloy was designed and manufactured, and the performance of the novel brace was tested. Ten patients with mild-to-moderate scoliosis were included to evaluate clinical efficacy. The bending test and minimum surface temperature of the embedded shape memory alloys met the deformation requirements for the novel brace. The thoracic kyphosis and lumbar lordosis angle were larger and the interface pressure was lower in the novel brace group than in the traditional brace group (P < 0.05). The SRS-22 assessment with the novel brace was better than with the traditional brace (P < 0.05). The novel brace provided a better three-dimensional correction effect to adolescent idiopathic scoliosis patients and also increased wearing comfort than traditional orthoses, which can improve compliance of patients.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13366665/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147980387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Applications of bioimpedance measurement in clinical and allied fields: a comprehensive review.","authors":"Dhruba Jyoti Bora, Santhosh Kumar Goud Manikonda","doi":"10.1186/s12938-026-01581-y","DOIUrl":"10.1186/s12938-026-01581-y","url":null,"abstract":"<p><strong>Background: </strong>Accurate and timely disease detection is essential in modern healthcare. Conventional imaging methods such as computed tomography (CT), magnetic resonance imaging (MRI), and dual-energy X-ray absorptiometry (DXA) offer valuable diagnostic information, but face significant limitations, including high cost, radiation exposure, and lengthy scan times. Electrical impedance tomography (EIT) and bioelectrical impedance analysis (BIA) have emerged as promising non-invasive, radiation-free, and cost-effective alternatives for assessing tissue properties by measuring bioimpedance-the electrical response of biological tissues influenced by cellular and molecular characteristics.</p><p><strong>Main body: </strong>Bioimpedance-based technologies measure electrical properties modulated by tissue composition, hydration, and disease-related changes. BIA, in particular, is widely used for body composition analysis, hydration status monitoring, and disease management in contexts such as oncology, diabetes, nephrology, cardiopulmonary function, fitness, and wound healing. Further, EIT can be used to generate tomographic images through surface electrode arrays, facilitating internal tissue visualization. Technological advances such as multi-frequency bioimpedance spectroscopy, wearable and portable devices, and integration with machine learning algorithms can further improve diagnostic accuracy and functional utility. Applications have broadened beyond clinical settings to include non-medical fields like agriculture, robotics, and material science. However, challenges persist, including methodological limitations, biological and environmental variability, electrode design, and limited penetration depth. Standardizing protocols, population-specific calibration equations, and cross-validation with gold-standard imaging techniques like MRI and CT are vital to enhancing measurement reliability and clinical acceptance. Furthermore, advances in sensor technology, data analytics, and multimodal diagnostic approaches incorporating bioimpedance promise to refine disease monitoring and personalized healthcare.</p><p><strong>Conclusion: </strong>Bioimpedance technology is a versatile and promising diagnostic and monitoring tool, combining safety, portability, and affordability. Its ability to provide real-time, non-invasive insights across a broad spectrum of medical and non-medical applications positions it at the forefront of biomedical innovation. Continued technological advancements and rigorous validation will be essential to realize its full potential in personalized healthcare and beyond. This comprehensive review highlights the versatility of bioimpedance technology, its growing role in personalized medicine and therapy, and its potential to enhance diagnostics and patient management across various healthcare domains.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13352812/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147970099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Operational mechanisms and application advances in artificial olfactory systems.","authors":"Chongyang Wang, Zhikai Wang, Shengqi Gan, Bin He, Yejingwen Tong, Yaojie Zhu, Dong Ye","doi":"10.1186/s12938-026-01580-z","DOIUrl":"10.1186/s12938-026-01580-z","url":null,"abstract":"<p><p>Artificial olfactory systems represent biomimetic platforms that emulate biological olfaction for volatile compound detection and discrimination. Biological olfaction achieves efficient perception through the specific binding of volatile molecules to olfactory receptors (OR), odorant-binding proteins (OBPs), and associated chemosensory proteins, followed by neural encoding, providing a theoretical foundation for artificial olfactory system design. This review synthesizes the current literature sourced from Web of Science, PubMed, and Scopus databases, with selection criteria emphasizing sensing mechanisms, device architectures, and translational applications. Bioelectronic nose platforms utilizing ORs, OBPs, and synthetic peptides are critically evaluated alongside nonbioreceptor-based sensing approaches, specifically colorimetric arrays employing chemo-responsive dyes and metal oxide semiconductor (MOS) sensors, which rely on synthetic rather than biological recognition elements. Four principal application domains constitute the thematic framework: medical diagnosis through breath volatile biomarker detection, food safety assessment via freshness monitoring, environmental surveillance of air and water quality, and public safety applications in hazardous substance detection. Signal processing methodologies encompassing feature extraction and machine learning-based pattern recognition are examined. Critical translational challenges including limited long-term stability of biological recognition elements, sensor drift, and environmental interference are addressed. The comparative analysis indicates that bioreceptor-based platforms achieve superior sensitivity suitable for trace biomarker detection, whereas nonbioreceptor-based sensors offer enhanced operational stability for continuous monitoring, and hybrid architectures integrating biological selectivity with robust synthetic transduction mechanisms represent a promising direction for next-generation devices.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13344000/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147947695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of multiple motor point stimulation on knee joint torque compared with conventional functional electrical stimulation.","authors":"Benjamin Kozlowski, Derrick Lim, Meredith Gladish, Arash Arami, Kei Masani","doi":"10.1186/s12938-026-01578-7","DOIUrl":"10.1186/s12938-026-01578-7","url":null,"abstract":"<p><strong>Background: </strong>Functional electrical stimulation (FES) delivers transcutaneous electrical current to motor nerves to artificially evoke muscle contractions and produce joint torque. In neurorehabilitation, FES is commonly applied via a large surface electrode pair placed over a muscle group-an approach that we here refer to as single-electrode stimulation (SES). However, the torque-generating capacity of SES is limited, possibly due to spatial-fixation of recruited motor units. Targeting specific regions of high electrical excitability, or motor points, may enhance neuromuscular activation and increase joint torque output.</p><p><strong>Methods: </strong>Twelve neurologically-intact participants underwent both continuous multiple motor point stimulation (mMPS) and SES of the quadriceps and hamstring muscle groups. Isometric tetanic knee torque was evaluated and compared relative to maximal voluntary contraction (MVC). As secondary aims, we quantified the discrepancy between observed and predicted torque response and the relative contribution of MPS conditions to knee extension torque.</p><p><strong>Results: </strong>Stimulating all quadriceps motor points produced approximately 51% greater knee extension torque than SES (33.3% MVC vs. 22.1% MVC). In contrast, stimulating all hamstring motor points (18.4% MVC) did not significantly increase knee flexion torque compared to SES (21.0% MVC). Discrepancies between observed and predicted MPS torques were primarily associated with rectus femoris stimulation, while vastus medialis contributed the least.</p><p><strong>Conclusions: </strong>Stimulation of all quadriceps motor points generated greater knee extension torque compared with conventional SES, highlighting the potential of mMPS to improve the effectiveness of FES interventions. In contrast, hamstring stimulation did not yield additional knee flexion torque underscoring muscle-specific limitations. These findings provide practical guidance for quadriceps electrode placement and channel allocation, indicating that more refined FES strategies can be achieved by prioritizing a targeted subset of motor points.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13344018/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147947692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Value of a radiomics model based on high-resolution large matrix target reconstruction images in predicting the invasiveness of lung adenocarcinoma with pure ground-glass nodules.","authors":"Jun Lv, Yufan Gao, Min Ren, Li Zhou, Jianhui Li, Hong Zhang, Xin Li, Ximing Li, Minghui Hua, Keyi Cui, Wenjiao Wang, Zhenchun Song","doi":"10.1186/s12938-026-01548-z","DOIUrl":"10.1186/s12938-026-01548-z","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the potential of computed tomography (CT) radiomics, based on high-resolution large matrix target reconstruction images, in predicting the invasiveness of lung adenocarcinoma in pure ground-glass nodules (pGGNs) with a diameter ≤ 1.5 cm.</p><p><strong>Methods: </strong>The clinical and imaging data of 297 patients with pGGNs, confirmed by pathology, were collected between March 2021 and June 2024. Pathological diagnoses included atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC). The patients were divided into non-invasive (AAH and AIS) and invasive (MIA and IAC) groups based on pathology. Radiomics features were extracted using ITK-SNAP software, and a predictive model was built using Python 3.9.7, with feature selection based on least absolute shrinkage and selection operator regression. Receiver operating characteristic analysis, area under the curve (AUC), sensitivity, specificity and clinical decision curve analysis were used to assess model performance.</p><p><strong>Results: </strong>Multivariate logistic regression revealed that the maximum lesion diameter, median CT value and solid component ratio were significant predictors of invasiveness (P < 0.05). The CT radiomics model achieved AUC values of 0.861 (95% confidence interval [CI] 0.811-0.912) in the training set and 0.790 (95% CI 0.687-0.892) in the validation set. A combined model integrating clinical and radiomics features showed improved predictive performance, with an AUC of 0.861 (95% CI 0.809-0.913) in the training set and 0.810 (95% CI 0.709-0.912) in the validation set.</p><p><strong>Conclusions: </strong>The combined model based on CT radiomics and clinical imaging showed good performance in predicting the invasiveness of small pGGNs and may assist in clinical decision-making regarding follow-up management, surgery timing and treatment strategies. Further validation in prospective, multicentre studies is needed to verify these findings and assess generalisability to broader populations.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13340364/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147926063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Convolutional neural network analysis of cervical CT images: classification of Kikuchi disease, lymphoma, lymphadenitis, and tuberculosis.","authors":"Gun Ho Kim, Eui-Suk Sung, Kyoung Won Nam","doi":"10.1186/s12938-026-01586-7","DOIUrl":"10.1186/s12938-026-01586-7","url":null,"abstract":"<p><strong>Background: </strong>Kikuchi disease, lymphoma, lymphadenitis, and tuberculosis are common diseases affecting the head and neck. The causes and treatment methods differ; however, the initial symptoms of these diseases (fever, pain, and neck swelling) are generally similar; therefore, it is important to accurately determine the type of disease at its initial stage.</p><p><strong>Results: </strong>During the performance evaluation, the values of precision-recall area under the curve (PR AUC) were 0.785, 0.731, 0.920, and 0.821 for the four single-disease detection models for Kikuchi disease, lymphoma, lymphadenitis, and tuberculosis, respectively; 0.819 for a model for classifying the type of treatment; and 0.807 for a model for classifying all diseases with a single inspection. In the model performance tests, all six implemented models showed relatively high performance for the test dataset (accuracy: 0.6864-0.9278, precision: 0.7532-0.9583, recall: 0.3896-0.8804, and F1-score: 0.5310-0.8710).</p><p><strong>Conclusion: </strong>Based on these experimental results, we conclude that the proposed CNN-based diagnosis support technique has the potential to be an efficient pre-screening tool for first-time patients with Kikuchi disease, lymphoma, lymphadenitis, and tuberculosis by reducing the dependency on high-risk invasive diagnosis; however, additional model enhancement is required to improve its clinical applicability.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13339412/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147926016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A standardized and efficient intensity-based image registration framework for quantitative cranial base superimposition.","authors":"Fengcong Wang, Yang Lyu","doi":"10.1186/s12938-026-01583-w","DOIUrl":"10.1186/s12938-026-01583-w","url":null,"abstract":"<p><strong>Background: </strong>Structural cranial base superimposition is widely regarded as a biologically reliable reference for evaluating orthodontic treatment outcomes. However, its clinical implementation remains limited due to labor-intensive manual procedures and operator-dependent variability. Recent artificial intelligence approaches have primarily focused on automated landmark detection (e.g., Sella-Nasion), which may propagate geometric instability and do not explicitly address physical inconsistencies such as inter-device magnification discrepancies. To overcome these limitations, this study proposes a standardized, intensity-based image registration framework aim to improve reproducibility, geometric validity, and computational efficiency in cranial base superimposition.</p><p><strong>Methods: </strong>We propose a semi-automated image registration workflow employing the SVD-constrained Enhanced Correlation Coefficient (ECC) algorithm. The framework integrates three key innovations: (1) pre-registration calibration to standardize spatial resolution and correct magnification errors; (2) a \"Human-in-the-Loop\" initialization strategy to incorporate expert judgement and prevent algorithmic drift; and (3) a mathematically traceable optimization process that aligns images based on pixel intensity rather than isolated landmarks. The method was validated on serial lateral cephalograms of representative adult premolar extraction cases. Registration accuracy was assessed using pixel-wise difference heatmaps and vector displacement analysis.</p><p><strong>Results: </strong>The framework achieved high-precision alignment of stable cranial base structures, evidenced by a low Mean Absolute Difference (MAD) in pixel intensity (< 15 a.u.) within the reference region. Difference heatmaps confirmed the algorithm's specificity, exhibiting a \"locking\" effect on the cranial base while accurately highlighting significant discrepancies in the dentoalveolar regions corresponding to treatment changes. The workflow significantly reduced processing time to seconds, with robust performance across diverse imaging systems.</p><p><strong>Conclusions: </strong>The proposed framework enables quantitative and reproducible cranial base superimposition within a unified coordinate system, while reducing operator dependence and maintaining clinically interpretable outputs. This pipeline provides a practical and reproducible approach for longitudinal cephalometric analysis.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13335231/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147873074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A TyG-UHR-based machine learning model for screening lean MAFLD: development and external validation.","authors":"Yansong Ji, Hui Zhang, Jingjing Xia, Guilian Chen, Hong Li","doi":"10.1186/s12938-026-01585-8","DOIUrl":"10.1186/s12938-026-01585-8","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Lean metabolic dysfunction-associated fatty liver disease (MAFLD) is increasingly recognized but often goes unnoticed during health checkups and primary care due to low perceived risk and limitations of imaging. Cost-effective, automated screening methods using routine data could enhance triage and referrals for confirmatory imaging.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We used routinely collected data from a hospital health checkup cohort (N = 3346; Huai'an First People's Hospital, China) to develop a machine learning model for lean MAFLD incorporating prespecified predictors--triglyceride-glucose (TyG) and uric acid-to-high-density lipoprotein cholesterol ratio (UHR). The cohort was randomly split 70:30 into training and test sets. In the training set, additional clinical predictors were selected via elastic-net regression, followed by the tuning of eight algorithms with strict leakage control, utilizing average precision as the primary optimization metric. Extreme gradient boosting (XGBoost) was chosen based on test set discrimination, calibration, and clinical utility. External validation utilized data from the National Health and Nutrition Examination Survey 2017-2020 (N = 2216), split 50:50 into calibration and hold-out validation subsets. Post hoc recalibration was performed on the calibration subset. Performance in the hold-out validation subset was summarized using the receiver operating characteristic curve, calibration plots, decision curve analysis, and Shapley Additive Explanations (SHAP) for model interpretability.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Restricted cubic spline analysis revealed a nonlinear association for TyG, whereas UHR showed an almost linear association. Elastic-net regularization identified additional clinical predictors, including systolic blood pressure (SBP), diastolic blood pressure (DBP), age, the alanine aminotransferase/aspartate aminotransferase (ALT/AST) ratio, and serum creatinine (Scr). In the test set, XGBoost achieved an area under the curve (AUC) of 0.995, a Brier score of 0.008, a log loss of 0.035, and an expected calibration error of approximately 0.007, offering the highest net benefit across threshold probabilities of 0.05 to 0.60. In the hold-out validation subset, discrimination remained robust both before and after recalibration (AUC 0.826 vs. 0.810), while probability accuracy improved significantly (Brier score decreased from 0.286 to 0.109; log loss from 1.253 to 0.388). Recalibrated probabilities demonstrated acceptable calibration (intercept 0.103; slope 0.684), with consistent positive net benefit observed across thresholds of approximately 0.02 to 0.30. Regarding interpretability, SHAP values ranked TyG (2.538) as the most influential factor, followed by SBP (1.727) and UHR (0.999), with modest but consistent contributions from age (0.810), Scr (0.713), and the ALT/AST ratio (0.657), whereas DBP (0.266) had the smallest effect.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13330354/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147873136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}