BioMedical Engineering OnLine最新文献

{"title":"Machine learning vs. radiomics for discriminating atypical cartilaginous tumors from benign enchondromas on MRI.","authors":"Simon Johannes Joham, Johannes Nikolaus Woltsche, Dieter Szolar, Andreas Leithner, Martin Urschler, Maria Anna Smolle","doi":"10.1186/s12938-026-01547-0","DOIUrl":"10.1186/s12938-026-01547-0","url":null,"abstract":"<p><strong>Background: </strong>Enchondromas (EC) present cartilaginous tumors that are difficult to differentiate from their intermediate counterpart, atypical cartilaginous tumors (ACT). Histologically, tumor distinction of these entities is limited by sampling bias, while radiologically, similar lesion features render classification challenging. Therefore, the aim of this study is to investigate whether machine learning- or radiomics-based image analysis tools can reliably differentiate between EC and ACT using MRI data and corresponding expert annotations.</p><p><strong>Methods: </strong>Based on an MRI dataset of 206 unique patients (79 controls, 104 EC, 23 ACT), we develop a machine learning-based AI image analysis tool that uses the state-of-the-art nnU-Net framework for medical image segmentation and extends it for tumor classification. Two nnU-Net models (Scout and Specialist) are applied sequentially. Scout first detects images without tumor tissue and removes them from further analysis, whereas Specialist performs the final tumor classification on the remaining images. Alternatively, our tool supports radiomics-based classification using hand-crafted tumor characteristics.</p><p><strong>Results: </strong>In our cross-validation experiments, when using the two models approach, where Specialist follows Scout, we achieved 87% Sensitivity (95% CI [0.67, 0.96]) for the ACT class and 93% Sensitivity (95% CI [0.87, 0.97]) for the EC class. Furthermore, no image containing an ACT was classified as non-tumor.</p><p><strong>Conclusions: </strong>In this pilot study, we demonstrated that MRI information alone can be used to differentiate between ACT and EC with high accuracy. These results seem promising that in future, machine learning and AI can be used for better orthopedic diagnosis of cartilaginous tumors in clinical practice.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13134191/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147509434","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":"Mechanics-based estimation of metabolic cost of locomotion in rehabilitation: A narrative review.","authors":"Dezhi Jiang, Lauri Stenroth, Rosa Pàmies-Vilà, Parvat Katwal, Suraj Jaiswal, Antti Löppönen, Aki Mikkola, Arend L Schwab","doi":"10.1186/s12938-026-01553-2","DOIUrl":"10.1186/s12938-026-01553-2","url":null,"abstract":"<p><p>The objective of this paper is to explore methodologies used to estimate the mechanical cost of locomotion and evaluate their validity as indicators of metabolic cost within rehabilitation contexts. Aging societies face rising healthcare costs and fewer workers. Remote monitoring of rehabilitation progress may help address these challenges. Because locomotion mechanics are easier to measure than metabolic cost, understanding whether mechanical cost of transport can serve as a surrogate is of interest. We conducted a systematic search for studies on mechanical work or power and metabolic energy consumption in adults under physical rehabilitation contexts. Abstract, full text screening, and data extraction were performed. Ten articles were included. We found no direct relationship between mechanical cost and metabolic cost in the included studies. However, consistent trends were observed: interventions that provided net positive work generally reduced both mechanical and metabolic costs. Similar trends were found in wheelchair propulsion, where mechanical advantage and power assistance reduced both mechanical cost and metabolic demand for wheelchair users. Rehabilitation progress can be monitored using metabolic cost, and given the observed parallel trends, mechanical cost may also serve as a practical indicator, although further research is needed to establish its validity as a surrogate.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13137497/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147509393","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":"Compliance-mediated pressure-independent cerebrovascular regulation: a distinct novel mechanism in youth.","authors":"Zijie Wang, Youjun Liu, Hao Sun, Tengfei Li, Liyuan Zhang, Guangfei Li, Binxu Yang, Yanjun Gong, Bao Li","doi":"10.1186/s12938-026-01551-4","DOIUrl":"10.1186/s12938-026-01551-4","url":null,"abstract":"<p><p>Cerebrovascular regulatory capacity is essential for maintaining brain stability. Most previous studies have focused on middle-aged and elderly populations, where regulation depends on vasodilation with reduced resistance and elevated blood pressure-the pressure-dependent mechanism. Whether this paradigm applies to younger individuals remains unclear. Given the rising prevalence of cardiovascular and cerebrovascular risks in young adults, elucidating youth-specific mechanisms is of great importance. In this study, standardized breath-holding was used to induce hypercapnia in 52 young volunteers (23.67 ± 1.77 years). Hemodynamic parameters of both middle cerebral arteries (blood pressure, heart rate, and flow velocity) were measured at rest and during hypercapnia. The breath-holding index (BHI), reflecting cerebrovascular regulatory capacity, was calculated, and a hemodynamic model was applied to derive resistance variation coefficient ( <math><msub><mi>R</mi> <mi>v</mi></msub> </math> ), diameter variation coefficient ( <math><msub><mi>D</mi> <mi>v</mi></msub> </math> ), and compliance ( <math><mi>C</mi></math> ), forming a multiparametric framework. In total, 104 unilateral datasets underwent multilevel statistical analysis. Two regulatory patterns were identified: pressure-dependent (n = 72) and pressure-independent (n = 32). The pressure-independent group showed greater dilation ( <math><msub><mi>D</mi> <mi>v</mi></msub> </math> : 1.4222 vs. 1.2817, p < 0.05) and more stable blood pressure (1.4271 vs. 5.3937 mmHg, p < 0.05), achieving comparable cerebrovascular regulatory capacity ( <math><mtext>BHI</mtext></math> : 1.3327 vs. 1.3907, p > 0.05) via enhanced compliance. Strong correlations were observed between rest and task states for blood pressure, heart rate, and flow velocity (all r > 0.85, p < 0.001). The proposed pressure-independent mechanism challenges the conventional paradigm, highlights individual variability, and offers new insights into cerebrovascular regulatory capacity under hypercapnia.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13130797/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147497719","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":"Synergistic effects of dexamethasone and vitamins D and K on mesenchymal stem cell differentiation.","authors":"Jana Dvorakova, Jana Kolaja Dobra, Lucie Hauer, Petra Kocanek Chocholata, Miroslava Cedikova, Anna Nekleionova, Vaclav Babuska","doi":"10.1186/s12938-026-01556-z","DOIUrl":"10.1186/s12938-026-01556-z","url":null,"abstract":"<p><strong>Background: </strong>The ability to guide stem cells toward the bone-forming lineage is a fundamental aspect of regenerative medicine. Conventional protocols for osteogenic differentiation of mesenchymal stem cells typically rely on continuous exposure to the synthetic steroid dexamethasone, in combination with other supplements such as ascorbate and glycerophosphate. Although dexamethasone effectively induces bone-related gene expression and matrix mineralization, prolonged or excessive exposure can lead to adverse catabolic and cytotoxic effects. Therefore, there is a need to develop improved culture conditions that retain efficacy while enhancing physiological relevance, safety, and reproducibility. This study investigated whether 1-week dexamethasone exposure and supplementing the medium with vitamin D3 and the synthetic vitamin K analogue K3 could enhance osteogenic differentiation of bone marrow-derived mesenchymal stem cells.</p><p><strong>Methods: </strong>Stem cells were cultured for 28 days in four types of osteogenic media differing in the duration of dexamethasone exposure and the presence of vitamins D3 and K3. Osteogenic differentiation was evaluated using histochemical staining for mineralized matrix, quantification of calcium deposition, analysis of alkaline phosphatase activity, fluorescence microscopy of cellular morphology and mitochondrial organization, and gene expression of osteogenic markers including RUNX2, alkaline phosphatase, osteocalcin, and bone morphogenetic protein 2.</p><p><strong>Results: </strong>A short exposure to dexamethasone alone was insufficient to support robust osteogenic progression, confirming the importance of sustained stimulation. In contrast, the combination of vitamins D3 and K3 produced a clear synergistic effect, characterized by stronger mineralization, increased alkaline phosphatase activity, and enhanced expression of key osteogenic genes.</p><p><strong>Conclusions: </strong>This study demonstrates that the combined use of vitamins D3 and K3, together with optimized dexamethasone exposure, provides a simple and biologically compatible strategy to improve the osteogenic differentiation of mesenchymal stem cells. This approach offers a physiologically relevant, safe, and cost-effective modification of standard osteogenic protocols and may contribute to the development of more efficient cell-based systems for bone tissue engineering and regenerative medicine.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13123151/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147479629","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":"Salvigenin alleviates ferroptosis and pyroptosis in myocardial ischemia/reperfusion models by inhibiting the NLRP3 pathway.","authors":"Wenrong Su, Shiqing Zhang, Jinghai Chen, Junchang Sun","doi":"10.1186/s12938-026-01554-1","DOIUrl":"10.1186/s12938-026-01554-1","url":null,"abstract":"<p><p>Myocardial ischemia/reperfusion injury (MI/RI) is a life-threatening vascular disease. Salvigenin (SGN) has been reported to play anti-oxidative stress and anti-inflammatory roles in various diseases. Our purpose was to investigate the effect of SGN on MI/RI and its potential mechanism. The viability of hypoxia/reoxygenation (H/R)-induced H9C2 cells was explored by CCK-8 assay. Fe²⁺ and MDA levels were detected via corresponding commercial kits. The protein expression level was evaluated through western blot. The intracellular ROS level was detected by immunofluorescent staining. IL-1β and IL-18 levels were explored through ELISA assay. C57BL/6 mice were used to construct in vivo model by left anterior descending coronary artery occlusion. The effect of SGN on mice models were evaluated by enzyme activity kits, echocardiography, HE staining and TUNEL. SGN increased the viability of H/R-induced H9C2 cells. SGN reduced the levels of Fe²⁺ and MDA both in vitro and in vivo. SGN up-regulated SLC7A11, GPX4 and FTH1protein levels and decreased ROS level in H/R-induced H9C2 cells compared with the control cells. SGN down-regulated NLRP3, cleaved caspase-1 and GSDMD-N, and reduced the concentration of IL-1β and IL-18 both in cells and in mice models. Moreover, SGN repaired the left ventricular systolic function, decreased infarct size, serum CK-MB, CTnT, and LDH levels and cardiomyocyte area in mice models. SGN treatment decreased the apoptosis level of myocardial tissue cells. However, co-transfection with the NLRP3 overexpression vector reversed the inhibition of SGN on ferroptosis and pyroptosis. In conclusion, our results indicated that SGN could moderate MI/RI and alleviate ferroptosis and pyroptosis in vitro and in vivo, and its mechanism of action was associated with the inhibition of NLRP3 pathway. SGN may be considered for MI/RI treatment.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13097952/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147455406","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":"Prognostic value of BMI, prognostic nutritional index, and CRP in patients with lymphoma after autologous hematopoietic stem cell transplantation.","authors":"Jin Zhao, Xiaolian Wen, Li Ma, Meijing Zheng, Tao Guan, Liping Su","doi":"10.1186/s12938-026-01545-2","DOIUrl":"10.1186/s12938-026-01545-2","url":null,"abstract":"<p><strong>Objective: </strong>Analyze the predictive value of body mass index (BMI), prognostic nutritional index (PNI), C-reactive protein (CRP), and CD3+CD8+T for the prognosis of lymphoma patients undergoing autologous hematopoietic stem cell transplantation.</p><p><strong>Method: </strong>We retrospectively included 160 patients with malignant lymphoma who underwent first-line or salvage chemotherapy and successfully underwent autologous hematopoietic stem cell transplantation in our hospital between May 2010 and January 2019. The clinical data of the patients before transplantation (baseline period) were collected and analyzed. The cutoff values were obtained based on the ROC curve. The clinical characteristics of patients were compared, including age, gender, physical condition (ECOG PS) score, Ann Arbor staging, International Prognostic Index (IPI) score, extranodal involvement, bone marrow involvement, and B symptoms. Followed up for 5 years, Kaplan-Meier method and Cox proportional hazards regression model were used to analyze the effects of various indicators and clinical characteristics on overall survival (OS) and progression-free survival (PFS).</p><p><strong>Result: </strong>According to the ROC curve cutoff value, 160 patients were divided into low BMI group (83 cases) and high BMI group (77 cases), low PNI group (78 cases) and high PNI group (82 cases), low CRP group (90 cases) and high CRP group (70 cases), low CD3+CD8+T group (86 cases) and high CD3+CD8+T group (74 cases). There were significant differences in ECOG PS score, Ann Arbor staging, IPI score, and B symptoms among patients with different BMI levels (P < 0.05). There were differences in ECOG PS score, Ann Arbor staging, and IPI score among patients with different PNI levels (P < 0.05). Patients with different CRP levels also have differences in ECOG PS score, Ann Arbor staging, IPI score, spinal cord involvement, and B symptoms (P < 0.05). A total of 160 lymphoma patients were followed up for 5 years, with a survival rate of 65.00% (104/160). Kaplan-Meier analysis showed that low BMI, low PNI, high CRP, and high CD3+CD8+T were all associated with poorer overall survival and progression-free survival (P < 0.05). Multivariate Cox regression analysis showed that low PNI and high CRP were independent risk factors for both OS and PFS. In addition, Ann Arbor staging (stages III-IV) was an independent risk factor for OS and PFS, but high CD3+CD8+T was an independent risk factor for PFS.</p><p><strong>Conclusion: </strong>Low levels of PNI and CRP before transplantation are independent risk factors affecting overall survival and progression-free survival in lymphoma patients undergoing autologous hematopoietic stem cell transplantation. In addition, high levels of CD3+CD8+T cells are an independent risk factor for progression-free survival. These indicators provide new and valuable reference for clinical doctors to more accurately evaluate patient prognosis.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13020211/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147442488","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":"Data-independent fluorescence molecular imaging analysis: a two-stage clustering framework for intraoperative tumor imaging.","authors":"Yixiang Zhou, Jiaqi Tang, Jie Liu, Yiyin Zhang, Hanfu Shi, Huaping Wu, Wei Wu, Zeyu Zhang","doi":"10.1186/s12938-026-01549-y","DOIUrl":"10.1186/s12938-026-01549-y","url":null,"abstract":"<p><strong>Background: </strong>Intraoperative fluorescence molecular imaging (FMI) is increasingly used to distinguish benign from malignant tumors; however, existing quantitative methods are predominantly data-driven, requiring large datasets and exhibiting limited adaptability in rare diseases or low-incidence tumor surgeries. Furthermore, high false-positive rates and substantial inter-operator variability remain significant challenges, hindering further application of FMI-guided surgery. This study introduces a novel, self-referenced clustering framework that overcomes these limitations by leveraging internal tissue controls and rapid, data-independent analysis.</p><p><strong>Methods: </strong>We developed a two-stage clustering framework (K-means followed by Fuzzy C-Means, K-FCM) to process and analyze the tumor FMI results in NIR-II spectrum (wavelength 900-1880 nm). Unlike conventional models, our method utilizes each patient's adipose tissue as an internal reference, enabling individualized thresholding without reliance on large external datasets. This strategy was validated on 16 patients undergoing orbital tumor resection (with injecting indocyanine green, ICG). The diagnostic performance of the proposed framework was compared with the traditional tumor-to-normal ratio (TNR) thresholding strategy.</p><p><strong>Results: </strong>The self-referenced K-FCM clustering framework demonstrated substantial improvements over the TNR method, achieving higher sensitivity (0.909 vs 0.818), specificity (0.800 vs 0.600). The use of internal tissue controls effectively normalized fluorescence variability, minimized ICG-related false positives, and enabled accurate intraoperative differentiation of malignant tumors. Furthermore, the proposed framework does not require a large amount of clinical data for training, so it has greater clinical practicality and can be used even for rare tumors.</p><p><strong>Conclusions: </strong>Our self-referenced, data-independent clustering framework provides fast and reliable intraoperative analysis for fluorescence-guided tumor navigation. By lowering false-positive rates and the dependency on operator experience, the method enhances the accuracy and promotes the clinical application of FMI-guided tumor surgery.</p><p><strong>Trial registration: </strong>On 14th November 2020, the study was registered in the Chinese Clinical Trial Registry (ChiCTR2000039908) and the data shown herein are part of this study.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13094019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147430601","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":"Experimental quantification of balance using whole-body stability regions from postural sway exercises.","authors":"Kübra Akbaş, Neethan Ratnakumar, Rachel Jones, Marianne Doss, Carlotta Mummolo, Jean-François Daneault, Xianlian Zhou","doi":"10.1186/s12938-026-01546-1","DOIUrl":"10.1186/s12938-026-01546-1","url":null,"abstract":"<p><strong>Background: </strong>Comprehensive balance assessment is essential for evaluating balance deficiencies, particularly in individuals with limited mobility and increased fall risk. However, clinical balance assessments often rely on subjective scoring and simplified models that may not capture the full dynamics of human postural control. Additionally, center of pressure (COP)-based metrics and inverted pendulum models offer limited insight into whole-body balance ability. Balance regions (BRs) offer a more holistic approach by quantifying balanced center of mass (COM) states. Previously, BRs were used to assess the balancing capabilities of bipedal systems and humans in simulation; however, there is a lack of real-world implementations of whole-body BR analyses in human balance.</p><p><strong>Methods: </strong>This study presents a novel experimental framework to quantify human balance using COM-based BRs derived from large postural sway tasks. The participants comprised 22 healthy young adults who performed voluntary, supported, and perturbed anterior-posterior (AP) sway exercises while standing on force plates, with a full-body motion capture setup. COM trajectories were obtained from individualized musculoskeletal models in OpenSim to construct BRs, which were compared with linear inverted pendulum (LIP) limits. Key COM-based metrics included maximum AP margin of stability (MoS), maximum AP velocity, extrapolated COM (XcoM) range, and BR areas. COP measures (root mean square (RMS), range, 95% confidence ellipse area, mean AP velocity) and joint kinematics were also analyzed.</p><p><strong>Results: </strong>COM trajectories largely stayed within the LIP-based analytical boundaries, with BRs capturing individualized balance envelopes. Significant sex differences were observed in the maximum posterior MoS (p = 0.01974), XcoM range metrics (p < 0.03924), and BR areas (p < 0.045). COP metrics varied significantly across tasks in the RMS, 95% confidence ellipse area, and mean velocity (p < 0.02046), and inverse kinematics revealed distinct joint coordination patterns during sway; there was a significant sex difference in the COP range during perturbed backward sway (p = 0.03053).</p><p><strong>Conclusions: </strong>This study presents a novel, COM-based experimental framework for balance assessment that captures whole-body stability regions from dynamic postural tasks. BRs provide a quantitative and individualized measure of balance capacity beyond traditional metrics. This framework has potential for fall risk evaluation, balance training, and integration with wearable or markerless motion capture in clinical and neurorehabilitation settings.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13081498/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147371943","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":"Machine learning algorithms for predicting quality of life improvements after digital orthodontic treatment: a retrospective analysis.","authors":"Yuzhe Huang, Rasheed Abdulsalam","doi":"10.1186/s12938-026-01543-4","DOIUrl":"10.1186/s12938-026-01543-4","url":null,"abstract":"<p><strong>Background: </strong>Digital orthodontic treatment has revolutionized clinical practice, yet predicting individual patient outcomes remains challenging. This retrospective study developed and validated machine learning algorithms to predict quality of life improvements following digital orthodontic treatment.</p><p><strong>Methods: </strong>Clinical data from 386 patients who underwent clear aligner therapy between January 2020 and December 2023 were analyzed. The dataset included demographic information, clinical parameters, imaging data, and standardized quality of life assessments using OHIP-14, IOTN, and VAS scales. Three machine learning algorithms-random forest, support vector machine, and neural network-were trained and evaluated using 70% training, 15% validation, and 15% test sets.</p><p><strong>Results: </strong>Digital orthodontic treatment demonstrated 92.3 ± 5.8% tooth movement accuracy and reduced average treatment duration to 18.5 ± 4.2 months. Quality of life assessments revealed significant improvements, with OHIP-14 scores decreasing from 24.6 ± 8.2 to 8.2 ± 4.3 (66.7% reduction, P < 0.001), and VAS aesthetic satisfaction increasing from 28.4 ± 12.3 to 85.6 ± 8.7 (P < 0.001). The random forest algorithm achieved superior predictive performance with 87.9% accuracy, 89.5% sensitivity, 85.7% specificity, and 0.93 AUC. Feature importance analysis identified baseline OHIP-14 scores (0.142), crowding severity (0.131), treatment duration (0.121), and patient compliance (0.111) as primary predictive factors. Clinical implementation of the prediction system improved treatment understanding (92.3% vs. 78.6%, P < 0.01) and patient satisfaction (94.8% vs. 83.2%, P < 0.01) compared to conventional consultations.</p><p><strong>Conclusion: </strong>This study demonstrates that machine learning can accurately predict orthodontic treatment outcomes and enhance clinical decision-making. The developed predictive system provides a valuable tool for outcome prediction and identification of factors associated with treatment success, potentially transforming orthodontic practice by enabling data-driven, patient-specific care strategies that optimize treatment outcomes and patient satisfaction.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13069775/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147353563","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":"OxyJet CPAP: an electricity-free low-cost emergency respiratory support device.","authors":"Md Kawsar Ahmed, Kaisar Ahmed Alman, Meemnur Rashid, Farhan Muhib, Saeedur Rahman, Nawsabah Noor, Md Khairul Islam, Forhad Uddin Hasan Chowdhury, Md Mohiuddin Sharif, Rifat Hossain Ratul, Sohana Jahan, Mushfiq Newaz Ahmed, Naveed Rahman, Kazi Nazmul Islam, Mohammad Shahjahan Siddike Shakil, Md Safiul Islam, Salahuddin Ahmed, Md Khairul Anam, Md Titu Miah, Robed Amin, Alain Bernard Labrique, Yasser Khan, Taufiq Hasan","doi":"10.1186/s12938-026-01524-7","DOIUrl":"10.1186/s12938-026-01524-7","url":null,"abstract":"<p><strong>Background: </strong>Respiratory support devices in resource-limited settings should be inexpensive, portable, effective, and easy to use. Non-invasive respiratory support devices can reduce expensive ICU admissions, but these facilities are severely lacking in low-resource settings. Here, we describe the design and validation of a low-cost, portable, electricity-free, and 3D-printed continuous positive airway pressure (CPAP) device named 'OxyJet' that can provide non-invasive respiratory support outside the ICU. The OxyJet is uniquely built using off-the-shelf components and 3D printing technology, making it both inexpensive and easy to produce. OxyJet costs less than 10% of the price of a similar CPAP system. Inspired by the fundamental mechanics of gas ejectors and harnessing the potential energy of a high-pressure oxygen jet, the device can deliver a high flow of oxygenated air up to 65 L/min (approx.), a positive end-expiratory pressure (PEEP) within 5-15 cmH₂O, and a fraction of inspired oxygen (FiO₂) of up to 100%.</p><p><strong>Results: </strong>The device was bench-tested following UK-MHRA RMCPAP guidelines and tested on healthy volunteers (n = 5) and hypoxemic patients (n = 5). A comparative pilot study involving 23 hypoxemic adult patients conducted in Dhaka, Bangladesh, showed a significant improvement (p < 0.05) in the peripheral oxygen saturation (SpO₂) of patients following the administration of OxyJet CPAP. The mean SpO₂ increase was 12.0% (95% CI 10.8-13.2) with OxyJet versus 11.5% (95% CI 9.3-13.8) for standard CPAP (p = 0.695). The findings indicate the device's feasibility and short-term physiological effects comparable to those of standard CPAP systems. Further studies are required to confirm its clinical efficacy and broader utility in resource-limited settings.</p><p><strong>Conclusion: </strong>Our findings suggest that OxyJet CPAP has the potential to serve as an emergency respiratory support device outside the ICU, strengthening health systems in resource-limited settings.</p><p><strong>Methods: </strong>OxyJet's performance was first assessed through benchtop testing following the UK-MHRA RMCPAP protocol. This was followed by preliminary human testing in healthy volunteers and hypoxemic patients to evaluate safety and usability. A pilot feasibility study involving hypoxemic adult patients in Dhaka, Bangladesh, was then conducted to compare the device's physiological effects with those of standard CPAP therapy.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13069705/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147353560","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}