BioMedical Engineering OnLine最新文献

{"title":"Transcriptomic and metabolomic insights into neutrophil activity in COPD complicated by metabolic syndrome.","authors":"Juan Li, Xue Wu, Yufen Fu, Jiliu Liu, Yao Liu, Jiahuan Li, Bomiao Qing, Yi Zhang, Jie Gao, Xiang He, Junyi Wang, Guoping Li","doi":"10.1186/s12938-025-01378-5","DOIUrl":"https://doi.org/10.1186/s12938-025-01378-5","url":null,"abstract":"<p><strong>Objectives: </strong>Chronic obstructive pulmonary disease (COPD) frequently coexists with metabolic syndrome (MS), compounding its impact on patients' health and quality of life. This study aimed to elucidate the immune and metabolic response characteristics in COPD patients with and without MS.</p><p><strong>Methods: </strong>A total of 11,315 COPD patients admitted to the Department of Respiratory and Critical Care Medicine at the Third People's Hospital of Chengdu between January 1, 2013, and May 1, 2023, were selected. Multivariate logistic regression was conducted to identify the risk factors for acute exacerbation of chronic obstructive pulmonary disease. Moreover, from this cohort, 30 patients (18 with COPD and 12 with COPD-MS) were recruited for a further study to investigate the underlying mechanisms of COPD and COPD-MS. Blood samples were collected from these participants to perform transcriptomic and metabolomic analyses, aiming to explore the differences in immune responses and metabolic alterations between the two groups.</p><p><strong>Results: </strong>Our findings indicate a significant enhancement of neutrophil-mediated immune responses in COPD-MS patients. Transcriptomic analysis revealed 327 differentially expressed genes (DEGs) significantly involved in neutrophil-mediated immunity. Key metabolic pathways were disrupted, with 39 differential metabolites identified. Notably, metabolites, such as L-homoarginine and diethanolamine, which were elevated in COPD-MS patients, showed strong correlations with DEGs involved in neutrophil pathways and immune checkpoint regulation. The study also found decreased levels of IL4 and IL5RA in COPD-MS patients, suggesting a shift from Th2 to Th1 inflammatory responses, potentially contributing to glucocorticoid resistance.</p><p><strong>Conclusions: </strong>COPD patients with metabolic syndrome exhibit a heightened neutrophil-mediated inflammatory response and significant metabolic disturbances, which underscores the need for precise therapeutic strategies targeting both metabolic and inflammatory pathways to improve patient outcomes and manage COPD-MS complexities effectively.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"43"},"PeriodicalIF":2.9,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11998468/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143961797","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":"Exploration of the effect of morphology and location on hemodynamics of small aneurysms: a variable-controlled study based on two cases with tandem aneurysms.","authors":"Jun Wan, Yeqing Jiang, Ligang Xu, Qimin Zhang, Guanghu Xu, Long Yu, Xinzhuo Li, Xiaolong Zhang, Shengzhang Wang","doi":"10.1186/s12938-025-01379-4","DOIUrl":"10.1186/s12938-025-01379-4","url":null,"abstract":"<p><strong>Introduction: </strong>Small aneurysms are usually treated with a flow diverter alone, without coils. However, some continue to exhibit incomplete occlusion after treatment, even after an extended period. This study aimed to investigate the effects of aneurysm morphology and location on the hemodynamic parameters related to poor outcomes.</p><p><strong>Methods: </strong>Two patients with tandem aneurysms were enrolled. Flow diverter deployment was simulated, and preoperative and postoperative hemodynamics were analyzed using computational fluid dynamics. The preoperative and postoperative hemodynamics of the actual surgical plan were simulated using finite element analysis and computational fluid dynamics. The correlation between morphology, hemodynamics, and incomplete occlusion was evaluated by calculating the hemodynamics of aneurysm models with different heights and neck widths, adjusted according to the original geometry.</p><p><strong>Results: </strong>Simulation of the actual surgical plan showed that the incompletely occluded aneurysm had a larger postoperative velocity at the sac and neck region (v_a and v_neck) and residual flow volume than the occluded aneurysm in both cases. The inflow rate (Q_inflow), inflow concentration index (ICI), v_a, and residual flow volume increased when the aneurysm neck width was expanded; with the increase in height, Q_inflow and ICI increased up to a certain point, while v_a and residual flow volume showed a decreasing trend. Aneurysms located on the superior wall of the internal carotid artery ophthalmic segment had a larger v_neck than those on the inferior wall.</p><p><strong>Conclusion: </strong>Aneurysms located on the superior wall of the internal carotid artery ophthalmic segment or with a larger neck or height present a more severe hemodynamic environment, requiring careful consideration when planning surgery. This study provides hemodynamic evidence demonstrating how morphology affects aneurysm progression.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"42"},"PeriodicalIF":2.9,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11992751/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143969709","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":"Antioxidant scaffolds for enhanced bone regeneration: recent advances and challenges.","authors":"Hui Li, Zhenhe Zhang, Jing Liu, Huiwen Wang","doi":"10.1186/s12938-025-01370-z","DOIUrl":"10.1186/s12938-025-01370-z","url":null,"abstract":"<p><p>Bone regeneration is integral to maintaining bone function and integrity in the body, as well as treating bone diseases, such as osteoporosis and defects. However, oxidative stress often poses a significant obstacle during bone regeneration, leading to cell damage, inflammatory responses, and subsequent impediment of normal bone tissue formation. Therefore, to maintain bone regeneration, antioxidant therapy is essential. Bone scaffolds, serving as a temporary support for bone tissue, can provide an ideal microenvironment for cell proliferation and differentiation, effectively promoting bone tissue formation. In recent years, with in-depth research on antioxidants and their mechanisms of action, the development and application of antioxidant bone scaffolds have shown tremendous potential. These antioxidant bone scaffolds not only promote osteogenic differentiation and angiogenesis, but also effectively inhibit the inflammatory response and osteoclast formation, significantly improving the efficiency of bone regeneration. Notably, with the rapid development of nanotechnology, nanozymes with multi-enzyme-like activities have been successfully constructed and encapsulated within bone scaffolds, leading to the proposal of multifunctional antioxidant strategies. Therefore, this review summarizes recent research progress, categorically introducing types of bone scaffolds and antioxidants, elucidating therapeutic strategies of antioxidant bone scaffolds, and identifying current challenges, aiming to provide valuable guidance for subsequent research.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"41"},"PeriodicalIF":2.9,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11980302/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143810246","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 review of osteoporotic vertebral fracture animal models.","authors":"Zhichao Qi, Guozhu Ye, Zhiyi Liu, Jie Zhang, Weidong Xie, Yu Li, Wenbin Yang","doi":"10.1186/s12938-025-01372-x","DOIUrl":"10.1186/s12938-025-01372-x","url":null,"abstract":"<p><strong>Introduction: </strong>Osteoporotic vertebral fractures are a common outcome of osteoporosis, imposing a substantial economic burden. The development of reliable animal models is essential for advancing research. This review examines osteoporotic vertebral fracture models across various animal species.</p><p><strong>Methods: </strong>The review compares and analyzes the different approaches used to model osteoporotic vertebral fractures in experimental animals, synthesizing the existing design protocols.</p><p><strong>Results: </strong>Rats and sheep are the primary experimental animals utilized in vertebral fracture research. The predominant approach in model design remains the creation of bone defects to simulate vertebral fractures. The spontaneous fracture model is primarily applicable to small species, such as transgenic mice. Rabbits and zebrafish are not suitable for modeling vertebral fractures due to the low cancellous bone content in their lumbar. The bone loss in the lumbar cancellous bone of the dog osteoporosis model is minimal, making it unsuitable for fracture modeling.</p><p><strong>Conclusions: </strong>The bone defect model remains the most widely used approach for osteoporotic vertebral fractures. However, the stress compression model shows promise as a potential focal point for future investigations.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"40"},"PeriodicalIF":2.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11977875/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143802274","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":"Forecasting motion trajectories of elbow and knee joints during infant crawling based on long-short-term memory (LSTM) networks.","authors":"Jieyi Mo, Qiliang Xiong, Ying Chen, Yuan Liu, Xiaoying Wu, Nong Xiao, Wensheng Hou","doi":"10.1186/s12938-025-01360-1","DOIUrl":"10.1186/s12938-025-01360-1","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Hands-and-knees crawling is a promising rehabilitation intervention for infants with motor impairments, while research on assistive crawling devices for rehabilitation training was still in its early stages. In particular, precisely generating motion trajectories is a prerequisite to controlling exoskeleton assistive devices, and deep learning-based prediction algorithms, such as Long-Short-Term Memory (LSTM) networks, have proven effective in forecasting joint trajectories of gait. Despite this, no previous studies have focused on forecasting the more variable and complex trajectories of infant crawling. Therefore, this paper aims to explore the feasibility of using LSTM networks to predict crawling trajectories, thereby advancing our understanding of how to actively control crawling rehabilitation training robots.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We collected joint trajectory data from 20 healthy infants (11 males and 9 females, aged 8-15 months) as they crawled on hands and knees. This study implemented LSTM networks to forecast bilateral elbow and knee trajectories based on corresponding joint angles. The data set comprised 58, 782 time steps, each containing 4 joint angles. We partitioned the data set into 70% for training and 30% for testing to evaluate predictive performance. We investigated a total of 24 combinations of input and output time-frames, with window sizes for input vectors ranging from 10, 15, 20, 30, 40, 50, 70, and 100 time steps, and output vectors from 5, 10, and 15 steps. Evaluation metrics included Mean Absolute Error (MAE), Mean Squared Error (MSE), and Correlation Coefficient (CC) to assess prediction accuracy.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The results indicate that across various input-output windows, the MAE for elbow joints ranged from 0.280 to 4.976°, MSE ranged from 0.203° to 59.186°, and CC ranged from 89.977% to 99.959%. For knee joints, MAE ranged from 0.277 to 4.262°, MSE from 0.229 to 53.272°, and CC from 89.454% to 99.944%. Results also show that smaller output window sizes lead to lower prediction errors. As expected, the LSTM predicting 5 output time steps has the lowest average error, while the LSTM predicting 15 time steps has the highest average error. In addition, variations in input window size had a minimal impact on average error when the output window size was fixed. Overall, the optimal performance for both elbow and knee joints was observed with input-output window sizes of 30 and 5 time steps, respectively, yielding an MAE of 0.295°, MSE of 0.260°, and CC of 99.938%.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study demonstrates the feasibility of forecasting infant crawling trajectories using LSTM networks, which could potentially integrate with exoskeleton control systems. It experimentally explores how different input and output time-frames affect prediction accuracy and sets the stage for future research focused on optimizing models and developing effective cont","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"39"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11967147/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143771295","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":"Ex vivo myo-mechanical assessment of isolated rectus abdominis muscle in pregnancy-specific urinary incontinence: a cross-sectional study nested within the Diamater cohort.","authors":"Carolina N F Carvalho, David R A Reyes, Juliana F Floriano, Sofia B C V Quiroz, Rafael G Oliveira, Fernanda C B Alves, Gabriela A Garcia, Luana F Iamundo, Adriely B M Magyori, Caroline B Prudencio, Patricia S Rossignoli, Cristiane R Pedroni, Raghavendra L S Hallur, Iracema M P Calderon, Angélica M P Barbosa, Marilza V C Rudge","doi":"10.1186/s12938-025-01366-9","DOIUrl":"10.1186/s12938-025-01366-9","url":null,"abstract":"<p><strong>Background: </strong>Rectus abdominis muscle (RAM) myopathy is the underlying mechanism of pregnancy-specific urinary incontinence (PSUI), which has been shown to be a predictor of long-term urinary incontinence (UI). However, there is limited knowledge about selective ex vivo myo-mechanical assessment (MMA) of the RAM in healthy pregnant women, particularly those with PSUI.</p><p><strong>Results: </strong>Our analysis revealed no specific quantitative parameters from the window analysis or contractile response of the RAM in ex vivo MMA. A gradual and consistent decline was predominantly observed in the peak and strength parameters for both groups. The qualitative contractile response analysis of the RAM using peak and strength parameters revealed three distinct behaviors under electrical stimulation: a progressive decrease in strength, sudden muscular arrest, and asynchrony with erratic fluctuations. In-depth quantitative analysis of the RAM ex vivo did not yield substantial differences between the two groups. However, qualitative analysis proved valuable in distinguishing the groups, revealing a tendency toward the loss of the progressive peak declines observed in the control group.</p><p><strong>Conclusion: </strong>This study highlights the complexity of RAM myopathy in the context of PSUI and its potential impact on UI outcomes.</p><p><strong>Method: </strong>In this cross-sectional study nested within a cohort, we examined ex vivo myography assessments in 87 mothers, comprising 48 with PSUI and 39 without PSUI, all of whom exhibited normal glucose tolerance. General data were extracted from our database, whereas RAM samples were collected during C-section for qualitative and quantitative ex vivo myography analysis, with a focus on initial and final baseline measurements, peak responses, strength, and duration times.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"38"},"PeriodicalIF":2.9,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11938764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143708314","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":"New considerations in selecting donors for dental pulp stem cells: a pilot study.","authors":"Mingchang Hu, Qianqian Zhang, Jidong Xu, Linlin Xu, Xuecheng Xu, Jiajia Wang, Yu Song","doi":"10.1186/s12938-025-01367-8","DOIUrl":"10.1186/s12938-025-01367-8","url":null,"abstract":"<p><strong>Background/purpose: </strong>Tissue engineering based on stem cell therapy necessitates a substantial quantity of high-quality stem cells. However, current sources face limitations, including narrow donor pools, compromised biological properties due to cryopreservation, and cellular senescence resulting from in vitro passaging and expansion. This study examines the impact of mild periodontitis on the biological performance of dental pulp stem cells (DPSCs) to explore the potential of broadening the donor pool for these cells.</p><p><strong>Materials and methods: </strong>The experiment included two variables: age and the presence of periodontitis. DPSCs were isolated from six healthy subjects and six patients with mild periodontitis. Healthy subjects were categorized into Groups A (28-32 years) and B (52-54 years), and patients with mild periodontitis were categorized into Groups C (31-33 years) and D (50-53 years). The analyses included cell morphology, proliferation rate, multilineage differentiation capacity, apoptosis, and surface marker expression.</p><p><strong>Result: </strong>No significant differences in cell morphology, pluripotency, or senescence were observed between healthy controls and periodontitis patients across age groups. Additionally, data on proliferation, pluripotency, and senescence were not significantly different. In healthy subjects, increased age was correlated with more elongated, flattened, and broader cells, alongside greater heterogeneity and intercellular granules. The proliferation and differentiation capacities decreased, whereas the degree of apoptosis increased. Similar trends were noted in patients with periodontitis.</p><p><strong>Conclusion: </strong>The biological properties of DPSCs remain unchanged in teeth with mild periodontitis, providing valuable insights for addressing the shortage of DPSCs in tissue engineering. Teeth with mild periodontitis have the potential to be pulp stem cell donors.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"37"},"PeriodicalIF":2.9,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929365/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676758","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 finger on the pulse of cardiovascular health: estimating blood pressure with smartphone photoplethysmography-based pulse waveform analysis.","authors":"Ivan Shih-Chun Liu, Fangyuan Liu, Qi Zhong, Shiguang Ni","doi":"10.1186/s12938-025-01365-w","DOIUrl":"10.1186/s12938-025-01365-w","url":null,"abstract":"<p><p>Smartphone photoplethysmography (PPG) offers a cost-effective and accessible method for continuous blood pressure (BP) monitoring, but faces persistent challenges with accuracy and interpretability. This study addresses these limitations through a series of strategies. Data quality was enhanced to improve the performance of traditional statistical models, while SHapley Additive exPlanations (SHAP) analysis ensured transparency in machine learning models. Waveform features were analyzed to establish theoretical connections with BP measures, and feature engineering techniques were applied to enhance prediction accuracy and model interpretability. Bland-Altman analysis was conducted, and the results were compared against reference devices using multiple international standards to evaluate the method's feasibility. Data collected from 127 participants demonstrated strong correlations between smartphone-derived digital waveform features and those from reference BP devices. The mean absolute errors (MAE) for systolic BP (SBP), diastolic BP (DBP), and pulse pressure (PP) using multiple linear regression models were 7.75, 6.35, and 4.49 mmHg, respectively. Random forest models further improved these values to 7.34, 5.79, and 4.45 mmHg. Feature importance analysis identified key contributions from time-domain, frequency-domain, curvature-domain, and demographic features. However, Bland-Altman analysis revealed systematic biases, and the models barely meet established accuracy standards. These findings suggest that while smartphone PPG technology shows promise, significant advancements are required before it can replace traditional BP measurement devices.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"36"},"PeriodicalIF":2.9,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924600/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143661929","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":"Analysis of preoperative ocular optical parameters in patients with cataract.","authors":"Wenqun Xi, Xinhua Liu, Zhiqiang Ren, Xiaosheng Huang, Liangnan Sun, Ye Ye, Yanhua Zhao, Zhe Zhang, Kun Zeng","doi":"10.1186/s12938-025-01364-x","DOIUrl":"10.1186/s12938-025-01364-x","url":null,"abstract":"<p><p>This study aims to evaluate the distribution of preoperative corneal parameters obtained using the Pentacam anterior segment analyzer in Chinese male and female patients with cataracts and to investigate the correlation between these parameters and related factors. Preoperative examination data of the eyes of 1,255 patients who underwent cataract surgery were retrospectively analyzed. The Pentacam AXL was used to extract preoperative corneal measurements, and the total corneal measurement data were analyzed. The average age of the patients was 52.9 ± 21.3 years. The mean simulated keratometry values and corneal curvature of total corneal refractive power were positively correlated with age (both P < 0.01). Spearman's correlation analysis revealed a positive association between age and anterior corneal spherical aberration, posterior corneal spherical aberration, and total corneal spherical aberration changes. A negative correlation was found between age and with-the-rule astigmatism, and it was positively correlated with the ratios of against-the-rule and oblique astigmatism. A significant between-eye correlation was observed regarding spherical aberration (Z40), horizontal coma (Z31), vertical coma (Z3-1), and horizontal trefoil (Z33). The corneal curvature in females was significantly steeper than that in males (P < 0.01). Corneal curvature, corneal spherical aberration, and corneal astigmatism were found to change with age. Additionally, we found physiological differences between the sexes. Individual measurements could be taken preoperatively to facilitate the development of personalized surgical plans. By identifying age- and gender-related corneal variations, this study enables more personalized cataract surgery planning, potentially improving refractive outcomes and reducing postoperative complications through tailored surgical techniques and intraocular lens selection.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"35"},"PeriodicalIF":2.9,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912591/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647050","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":"Performance and limitation of machine learning algorithms for diabetic retinopathy screening and its application in health management: a meta-analysis.","authors":"Mehrsa Moannaei, Faezeh Jadidian, Tahereh Doustmohammadi, Amir Mohammad Kiapasha, Romina Bayani, Mohammadreza Rahmani, Mohammad Reza Jahanbazy, Fereshteh Sohrabivafa, Mahsa Asadi Anar, Amin Magsudy, Seyyed Kiarash Sadat Rafiei, Yaser Khakpour","doi":"10.1186/s12938-025-01336-1","DOIUrl":"10.1186/s12938-025-01336-1","url":null,"abstract":"<p><strong>Background: </strong>In recent years, artificial intelligence and machine learning algorithms have been used more extensively to diagnose diabetic retinopathy and other diseases. Still, the effectiveness of these methods has not been thoroughly investigated. This study aimed to evaluate the performance and limitations of machine learning and deep learning algorithms in detecting diabetic retinopathy.</p><p><strong>Methods: </strong>This study was conducted based on the PRISMA checklist. We searched online databases, including PubMed, Scopus, and Google Scholar, for relevant articles up to September 30, 2023. After the title, abstract, and full-text screening, data extraction and quality assessment were done for the included studies. Finally, a meta-analysis was performed.</p><p><strong>Results: </strong>We included 76 studies with a total of 1,371,517 retinal images, of which 51 were used for meta-analysis. Our meta-analysis showed a significant sensitivity and specificity with a percentage of 90.54 (95%CI [90.42, 90.66], P < 0.001) and 78.33% (95%CI [78.21, 78.45], P < 0.001). However, the AUC (area under curvature) did not statistically differ across studies, but had a significant figure of 0.94 (95% CI [- 46.71, 48.60], P = 1).</p><p><strong>Conclusions: </strong>Although machine learning and deep learning algorithms can properly diagnose diabetic retinopathy, their discriminating capacity is limited. However, they could simplify the diagnosing process. Further studies are required to improve algorithms.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"34"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11909973/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633404","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}