Frontiers in Medicine最新文献

{"title":"Multiscale attention-over-attention network for retinal disease recognition in OCT radiology images.","authors":"Abdulmajeed M Alenezi, Daniyah A Aloqalaa, Sushil Kumar Singh, Raqinah Alrabiah, Shabana Habib, Muhammad Islam, Yousef Ibrahim Daradkeh","doi":"10.3389/fmed.2024.1499393","DOIUrl":"10.3389/fmed.2024.1499393","url":null,"abstract":"<p><p>Retinal disease recognition using Optical Coherence Tomography (OCT) images plays a pivotal role in the early diagnosis and treatment of conditions. However, the previous attempts relied on extracting single-scale features often refined by stacked layered attentions. This paper presents a novel deep learning-based Multiscale Feature Enhancement via a Dual Attention Network specifically designed for retinal disease recognition in OCT images. Our approach leverages the EfficientNetB7 backbone to extract multiscale features from OCT images, ensuring a comprehensive representation of global and local retinal structures. To further refine feature extraction, we propose a Pyramidal Attention mechanism that integrates Multi-Head Self-Attention (MHSA) with Dense Atrous Spatial Pyramid Pooling (DASPP), effectively capturing long-range dependencies and contextual information at multiple scales. Additionally, Efficient Channel Attention (ECA) and Spatial Refinement modules are introduced to enhance channel-wise and spatial feature representations, enabling precise localization of retinal abnormalities. A comprehensive ablation study confirms the progressive impact of integrated blocks and attention mechanisms that enhance overall performance. Our findings underscore the potential of advanced attention mechanisms and multiscale processing, highlighting the effectiveness of the network. Extensive experiments on two benchmark datasets demonstrate the superiority of the proposed network over existing state-of-the-art methods.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1499393"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11583944/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Employing Xception convolutional neural network through high-precision MRI analysis for brain tumor diagnosis.","authors":"R Sathya, T R Mahesh, Surbhi Bhatia Khan, Areej A Malibari, Fatima Asiri, Attique Ur Rehman, Wajdan Al Malwi","doi":"10.3389/fmed.2024.1487713","DOIUrl":"https://doi.org/10.3389/fmed.2024.1487713","url":null,"abstract":"<p><p>The classification of brain tumors from medical imaging is pivotal for accurate medical diagnosis but remains challenging due to the intricate morphologies of tumors and the precision required. Existing methodologies, including manual MRI evaluations and computer-assisted systems, primarily utilize conventional machine learning and pre-trained deep learning models. These systems often suffer from overfitting due to modest medical imaging datasets and exhibit limited generalizability on unseen data, alongside substantial computational demands that hinder real-time application. To enhance diagnostic accuracy and reliability, this research introduces an advanced model utilizing the Xception architecture, enriched with additional batch normalization and dropout layers to mitigate overfitting. This model is further refined by leveraging large-scale data through transfer learning and employing a customized dense layer setup tailored to effectively distinguish between meningioma, glioma, and pituitary tumor categories. This hybrid method not only capitalizes on the strengths of pre-trained network features but also adapts specific training to a targeted dataset, thereby improving the generalization capacity of the model across different imaging conditions. Demonstrating an important improvement in diagnostic performance, the proposed model achieves a classification accuracy of 98.039% on the test dataset, with precision and recall rates above 96% for all categories. These results underscore the possibility of the model as a reliable diagnostic tool in clinical settings, significantly surpassing existing diagnostic protocols for brain tumors.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1487713"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11601128/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142738993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum: A comprehensive review of <i>Mycoplasma pneumoniae</i> infection in chronic lung diseases: recent advances in understanding asthma, COPD, and bronchiectasis.","authors":"Zai-Qiang Guo, Shun-Yi Gu, Zhi-Hua Tian, Bo-Ying Du","doi":"10.3389/fmed.2024.1512825","DOIUrl":"https://doi.org/10.3389/fmed.2024.1512825","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fmed.2024.1437731.].</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1512825"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11582828/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The correlation between non-high-density lipoprotein cholesterol to high-density lipoprotein cholesterol ratio (NHHR) with non-alcoholic fatty liver disease: an analysis of the population-based NHANES (2017-2018).","authors":"Yuhao Yang, Shengxi Li, Zhenmei An, Shuangqing Li","doi":"10.3389/fmed.2024.1477820","DOIUrl":"10.3389/fmed.2024.1477820","url":null,"abstract":"<p><strong>Background/objective: </strong>Non-alcoholic fatty liver disease (NAFLD) encompasses a spectrum of liver disorders, from benign steatosis to more severe conditions like non-alcoholic steatohepatitis, with risks of progressing to fibrosis, cirrhosis, and hepatocellular carcinoma. The non-high-density lipoprotein cholesterol to high-density lipoprotein cholesterol ratio (NHHR) indicates lipid metabolic dysregulation and is associated with increased risks of various diseases. This study examines the relationship between NHHR and NAFLD to evaluate NHHR as a potential predictive biomarker for NAFLD.</p><p><strong>Methods: </strong>Data from the 2017-2018 National Health and Nutrition Examination Survey (NHANES) were used for cross-sectional analysis. After excluding individuals with incomplete data, hepatitis infections, heavy alcohol use, and those under 18, the study included 2,757 adults. The relationship between NHHR and NAFLD was analyzed using multivariable logistic regression, including subgroup analysis and interaction testing.</p><p><strong>Results: </strong>Among the 2,757 participants (mean age 49.91 years), 44.9% had NAFLD. NHHR showed a significant positive association with NAFLD, with an unadjusted odds ratio (OR) of 1.71 and a fully adjusted OR of 1.45. Quartile analysis revealed a 228% higher prevalence of NAFLD in the highest NHHR quartile, with an OR of 3.28. This positive association was consistent across various subgroups.</p><p><strong>Conclusion: </strong>Our findings suggest that elevated NHHR is positively correlated with the prevalence of NAFLD and possesses predictive value. We recommend that future research validate the clinical utility of NHHR, particularly for early detection of high-risk individuals and guiding personalized interventions.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1477820"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11581862/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Case report: STRN3-NTRK3 fusion in uterine sarcoma with spleen metastasis: a new variant in the spectrum of NTRK-rearranged tumors.","authors":"Piergiuseppe Colombo, Giuseppina Adriana Buonamassa, Anita Giulianini, Letizia Hassan, Noemi Rudini, Antonio Rizzo, Enrico Cavallo, Carlo Carnaghi, Salumeh Goudarzi, Sebastiano Mongiovì, Sarah Pafumi, Stefano Marletta","doi":"10.3389/fmed.2024.1448491","DOIUrl":"10.3389/fmed.2024.1448491","url":null,"abstract":"<p><p>Neurotrophic tyrosine receptor kinase (NTRK) fusions are infrequent genetic events that can occur in various tumor types. Specifically, NTRK-rearranged sarcoma has been observed in pediatric mesenchymal tumors and, to a lesser extent, in adult mesenchymal tumors like fibrosarcoma. Recently, NTRK-rearranged uterine sarcoma (US) has been identified as a rare entity characterized by constitutive activation or overexpression of the TRK receptor, which plays a role in cell proliferation and differentiation. Since its initial description in 2018, only 46 cases of NTRK-rearranged US have been reported. In this context, herein we describe an exceptional case of an <i>STRN3::NTRK3</i> fused US with histologically confirmed splenic metastasis. Notably, such localization has not been previously associated with pure uterine sarcomas in the literature. The fusion involved <i>STRN3</i> (exon-3) and <i>NTRK3</i> (exon-14) genes and was identified through next-generation sequencing analysis. Recognizing this specific molecular rearrangement is crucial, as it not only enables targeted therapy but also holds diagnostic significance in specific clinical scenarios.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1448491"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11581886/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Determinants of out-of-pocket expenditure on medicines among adults in Saudi Arabia: a cross-sectional study.","authors":"Mohammed Khaled Al-Hanawi, Mpho Keetile","doi":"10.3389/fmed.2024.1478412","DOIUrl":"10.3389/fmed.2024.1478412","url":null,"abstract":"<p><strong>Introduction: </strong>To achieve universal health coverage consistent with World Health Organization recommendations, monitoring financial protection is vital, even in the context of free medical care. Toward this end, this study investigated out-of-pocket (OOP) expenditure on medicines and their determinants among adults in Saudi Arabia.</p><p><strong>Methods: </strong>This analysis was based on cross-sectional data derived from the Family Health Survey conducted by the General Authority for Statistics in 2018. Data analyses for this study were based on the total sample of 10,785 respondents. Descriptive statistics were used to identify the sample distribution for all variables included in the study. Tobit regression analysis was used to examine the determinants of OOP expenditure on medicines.</p><p><strong>Results: </strong>The average OOP expenditure on medicines was estimated to be 279.69 Saudi Riyal in the sampled population. Tobit regression analysis showed that age, average household monthly income, education level, and suffering a chronic condition were the main determinants of OOP expenditure on medicines. Conversely, being married and employed were associated with a lower probability of OOP expenditure on medicines.</p><p><strong>Conclusion: </strong>This study could assist policy makers to provide additional insurance funding and benefits to reduce the possibility of catastrophic OOP expenditure on medicines, especially for the most vulnerable demographic.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1478412"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11584940/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A cluster randomized trial on inspiratory effort-targeted pressure support adjustment strategy in patients undergoing assisted mechanical ventilation: protocol for the IT-PSV study.","authors":"Wen-Yi Lu, Ming-Yue Miao, Ran Gao, Yan-Lin Yang, Linlin Zhang, Li Weng, Feng-Xue Zhu, Lei Liu, Jian-Xin Zhou","doi":"10.3389/fmed.2024.1483976","DOIUrl":"10.3389/fmed.2024.1483976","url":null,"abstract":"<p><strong>Background: </strong>Pressure support ventilation (PSV) is one of the most frequently used ventilator modes in the intensive care unit (ICU). The successful implementation of PSV depends on matching the patient's inspiratory effort with the ventilator support. In clinical practice, the pressure support level is usually set and adjusted according to tidal volume and respiratory rate. However, these parameters may not fully represent the patient's effort. Previous studies have shown that pressure muscle index (PMI), which is measured as the difference between the peak and plateau airway pressure during an end-inspiratory airway occlusion, could reliably determine the low and high inspiratory effort during PSV. Herein we present the study protocol for the Inspiratory effort-Targeted Pressure Support Ventilation (IT-PSV) trial to determine the effect of a PMI-targeted pressure support setting strategy on clinical outcomes in patients undergoing PSV.</p><p><strong>Methods and analysis: </strong>This is a cluster randomized controlled trial. Sixteen ICUs in academic hospitals will be included, eight of which will be randomly allocated to the PMI-targeted group and eight to the tidal volume/respiratory rate-targeted group. Before the initiation of the study, a four-week comprehensive training program, which includes courses of PSV initiation, pressure support adjustment, and weaning process, will be conducted for all staff in the participating ICUs. Adult patients with acute hypoxic respiratory failure and undergoing PSV within 24 h will be included. Pressure support setting and adjustment will follow the strategy according to the grouping. The primary outcome is the ventilator-free days at 28 days after enrollment. The patients will be followed up until successful weaning or separation of mechanical ventilation, death, hospital discharge, or until 28 days after randomization, whichever comes first.</p><p><strong>Discussion: </strong>The IT-PSV trial will examine the effect of an inspiratory effort-targeted PSV setting strategy on the duration of mechanical ventilation. If positive, it will provide a new physiological-based PSV management that could potentially facilitate protective assisted ventilation.</p><p><strong>Clinical trial registration: </strong>ClinicalTrials.gov, identifier NCT06526598.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1483976"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11583156/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142708884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum: Predicting 24-hour intraocular pressure peaks and averages with machine learning.","authors":"Ranran Chen, Jinming Lei, Yujie Liao, Yiping Jin, Xue Wang, Xiaomei Li, Danping Wu, Hong Li, Yanlong Bi, Haohao Zhu","doi":"10.3389/fmed.2024.1513862","DOIUrl":"https://doi.org/10.3389/fmed.2024.1513862","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fmed.2024.1459629.].</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1513862"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11582410/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Continuing medical education program completion and influencing factors: a cross-sectional study in Sichuan Province, China.","authors":"Xuedong Liu, Mengliang Ye","doi":"10.3389/fmed.2024.1464039","DOIUrl":"10.3389/fmed.2024.1464039","url":null,"abstract":"<p><strong>Objectives: </strong>This cross-sectional study was designed to explore the completion of continuing medical education (CME) programs and identify the factors influencing their completion.</p><p><strong>Methods: </strong>The data for this study were generated from the National CME Program Application and Information Feedback Online System and the Sichuan CME Administrative Platform. The data were processed using descriptive analysis, Chi-square test, and binary logistic regression methods. The completion of each CME program was determined by the research team members according to the criteria created by the Office of the Sichuan CME Commission.</p><p><strong>Results: </strong>A total of 180 hospitals and 3,622 CME programs were included. Among the 3,622 CME programs, 2,936 (81.1%) were determined to be completed. Comparative analysis showed that in terms of hospital characteristics, specialist hospitals, county hospitals, hospitals with 500-1,000 beds, and hospitals in the regions with government medical expenditure input equal to or more than 3,000 million RMB displayed the highest completion rates. For program attributes, national programs, programs in the field of pharmacy, and programs with 1-3 duration days demonstrated the highest completion rates. The binary logistic regression analysis showed that hospital region with different government medical expenditure input had the strongest positive association with the completion of CME programs [OR = 2.922, 95%CI (1.642-5.198)], while the duration time showed the strongest negative association [OR = 0.235, 95%CI (0.141-0.393)].</p><p><strong>Conclusion: </strong>This is the first study in China to analyze the completion of CME programs and identify its influencing factors at the provincial level. It is recommended that the government in the region should pay great attention to the construction of measures regarding the factors affecting the completion of CME programs. This includes providing more financial support to CME providers to ensure the formal operation of their CME activities, formulating guidelines on the application of CME programs to reasonably allocate and control the distribution of accredited CME programs across different hospital scales and disciplines, especially offering more training support to county hospitals, promulgating administrative documents to raise attention to the completion of CME programs, and special scrutiny on CME programs with longer durations to provide and protect training opportunities for those in need.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1464039"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11581879/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of factors influencing bronchiectasis patients with active pulmonary tuberculosis and development of a nomogram prediction model.","authors":"Yitian Yang, Lianfang Du, Weilong Ye, Weifeng Liao, Zhenzhen Zheng, Xiaoxi Lin, Feiju Chen, Jingjing Pan, Bainian Chen, Riken Chen, Weimin Yao","doi":"10.3389/fmed.2024.1457048","DOIUrl":"10.3389/fmed.2024.1457048","url":null,"abstract":"<p><strong>Background: </strong>To identify the risk factors for bronchiectasis patients with active pulmonary tuberculosis (APTB) and to develop a predictive nomogram model for estimating the risk of APTB in bronchiectasis patients.</p><p><strong>Methods: </strong>A retrospective cohort study was conducted on 16,750 bronchiectasis patients hospitalized at the Affiliated Hospital of Guangdong Medical University and the Second Affiliated Hospital of Guangdong Medical University between January 2019 and December 2023. The 390 patients with APTB were classified as the case group, while 818 patients were randomly sampled by computer at a 1:20 ratio from the 16,360 patients with other infections to serve as the control group. Relevant indicators potentially leading to APTB in bronchiectasis patients were collected. Patients were categorized into APTB and inactive pulmonary tuberculosis (IPTB) groups based on the presence of tuberculosis. The general characteristics of both groups were compared. Variables were screened using the least absolute shrinkage and selection operator (LASSO) analysis, followed by multivariate logistic regression analysis. A nomogram model was established based on the analysis results. The model's predictive performance was evaluated using calibration curves, C-index, and ROC curves, and internal validation was performed using the bootstrap method.</p><p><strong>Results: </strong>LASSO analysis identified 28 potential risk factors. Multivariate analysis showed that age, gender, TC, ALB, MCV, FIB, PDW, LYM, hemoptysis, and hypertension are independent risk factors for bronchiectasis patients with APTB (<i>p</i> < 0.05). The nomogram demonstrated strong calibration and discrimination, with a C-index of 0.745 (95% CI: 0.715-0.775) and an AUC of 0.744 for the ROC curve. Internal validation using the bootstrap method produced a C-index of 0.738, further confirming the model's robustness.</p><p><strong>Conclusion: </strong>The nomogram model, developed using common clinical serological characteristics, holds significant clinical value for assessing the risk of APTB in bronchiectasis patients.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"11 ","pages":"1457048"},"PeriodicalIF":3.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11581853/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}