Frontiers in Medicine最新文献

{"title":"Development of risk prediction model for small incision lenticule extraction.","authors":"Shaowei Zhang, Yulin Yan, Zhengwei Shen, Lei Liu, Pengqi Wang, Jian Zhu, Yanning Yang","doi":"10.3389/fmed.2025.1518889","DOIUrl":"10.3389/fmed.2025.1518889","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to identify risk factors associated with small-incision lenticule extraction (SMILE) surgery and develop a risk prediction model to aid in determining patient suitability for SMILE.</p><p><strong>Methods: </strong>This retrospective study included myopia patients from four medical centers in China, enrolled between January 2021 and December 2023. The data were randomly divided into training and test cohorts at an 8:2 ratio. A random forest (RF) model was developed and optimized using three-fold cross-validation, with feature importance assessed.</p><p><strong>Results: </strong>The study included a total of 2,667 patients, with 2,134 patients in the training cohort and 533 patients in the test cohort. Significant statistical differences were observed in the Belin/Ambrosio Enhanced Ectasia Display and the total deviation value (BAD-D), Corvis Biomechanical Index (CBI), Tomographic and Biomechanical Index (TBI), and spherical equivalent between patients suitable for SMILE and those not suitable, in both the training and test cohorts. The univariate analysis identified ten key features relevant to SMILE. The RF model developed from the training data demonstrated high performance, with an accuracy of 96.0% in the validation set and 95.7% in the test set, an F1 score of 0.967, and an area under the curve (AUC) of 0.976 (95% CI: 0.962-0.990).</p><p><strong>Conclusion: </strong>SMILE is not appropriate for all patients with myopia. The RF model, based on clinical characteristics, showed excellent performance in predicting SMILE suitability and has potential as a valuable tool for clinical decision-making in the future.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1518889"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162615/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301633","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 nomogram for one-year risk of death after hip fracture.","authors":"Jiale Guo, Liuyang Shi, Kehai Shi, Ru Dai, Jian Wang, Yehai Li","doi":"10.3389/fmed.2025.1500049","DOIUrl":"10.3389/fmed.2025.1500049","url":null,"abstract":"<p><strong>Background: </strong>Hip fractures are catastrophic events with a significant risk of mortality, making early identification of high-risk patients crucial. While previous studies have primarily focused on post-surgical mortality in hip fracture patients, less attention has been given to those who did not undergo surgery. This study aimed to develop a nomogram to predict 1-year mortality in older adults following hip fractures.</p><p><strong>Methods: </strong>Patients hospitalized with hip fractures at a university hospital between May 2016 and December 2021 were included. Participants were randomly divided into training and validation cohorts (70:30 ratio). After selecting key variables, the nomogram was constructed, and its performance was evaluated in both cohorts.</p><p><strong>Results: </strong>A total of 619 patients were included, with 136 (21.97%) experiencing mortality within one year. LASSO regression was used to account for multicollinearity, selecting variables such as age, coronary heart disease, surgery, hemoglobin, aspartate transaminase, and blood urea nitrogen. The nomogram achieved AUCs of 0.83 (95% CI: 0.78-0.88) and 0.81 (95% CI: 0.73-0.89) in the training and validation cohorts, respectively, demonstrating excellent calibration and clinical utility.</p><p><strong>Conclusion: </strong>The nomogram effectively predict 1-year mortality risk in older adults following hip fractures.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1500049"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162923/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301611","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 study on the prediction of targeted therapy efficacy in advanced lung adenocarcinoma patients with EGFR mutations using CT-based delta-radiomics model.","authors":"Zekai Wu, Peiyan Hua, Xiuying Chen, Jie Lei, Laian Zhang, Peng Zhang","doi":"10.3389/fmed.2025.1599206","DOIUrl":"10.3389/fmed.2025.1599206","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to evaluate the predictive performance of integrated clinical and CT-based radiomic models for assessing targeted therapy efficacy in advanced lung adenocarcinoma patients with EGFR (epidermal growth factor receptor) mutations.</p><p><strong>Materials and methods: </strong>This retrospective study included 106 EGFR-mutated advanced lung adenocarcinoma patients treated with targeted therapies at the Second Hospital of Jilin University (2020-2023). Patients were classified as responders (PR) or non-responders (SD/PD) based on RECIST (Response Evaluation Criteria in Solid Tumors) 1.1 criteria, then randomly divided into training (<i>n</i> = 74) and validation (<i>n</i> = 32) cohorts at a 7:3 ratio. We segmented tumor regions on pre-and post-treatment CT scans using ITK-SNAP, then extracted radiomic features and applied mRMR-LASSO (Minimum Redundancy Maximum Relevance-Least Absolute Shrinkage and Selection Operator). A delta-radiomics model was developed by quantifying feature changes between treatment phases. Significant clinical predictors identified by logistic regression were integrated with radiomic features to build a combined model. Performance was assessed via AUC, sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), DeLong's test, calibration curves, and decision curve analysis.</p><p><strong>Results: </strong>In the pre-treatment radiomics model, the AUC, accuracy, sensitivity, specificity, PPV, and NPV of the training cohorts were 0.751, 0.690, 0.737, 0.639, 0.683, and 0.697; in validation cohorts, these values were 0.726, 0.656, 0.778, 0.500, 0.667, and 0.636. In the delta-radiomics model, the AUC, accuracy, sensitivity, specificity, PPV, and NPV of the training cohorts were 0.906, 0.865, 0.868, 0.861, 0.868, and 0.861, vs. 0.825, 0.719, 0.722, 0.714, 0.765, and 0.667 in validation. For the clinical model, the AUC, accuracy, sensitivity, specificity, PPV, and NPV of the training cohorts were 0.828, 0.729, 0.737, 0.722, 0.737, and 0.722, compared to 0.766, 0.750, 0.722, 0.786, 0.812, and 0.688 in validation. In the combined model, the AUC, accuracy, sensitivity, specificity, PPV, and NPV of the training cohorts were 0.977, 0.946, 0.947, 0.944, 0.947, and 0.944, while in the validation cohorts, these values were 0.913, 0.781, 0.778, 0.786, 0.824, and 0.733.</p><p><strong>Conclusion: </strong>The combined model integrating delta-radiomics with clinical predictors demonstrates superior predictive performance for evaluating targeted therapy efficacy in EGFR-mutated advanced lung adenocarcinoma, significantly outperforming conventional radiomics models relying exclusively on pre-treatment imaging data.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1599206"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162602/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301612","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":"Prevalence and molecular insights into carbapenem resistance: a 2-year retrospective analysis of superbugs in South India.","authors":"Rahul Harikumar Lathakumari, Leela Kakithakara Vajravelu, Jayaprakash Thulukanam, Dakshina M Nair, Poornima Baskar Vimala, Vishnupriya Panneerselvam","doi":"10.3389/fmed.2025.1571231","DOIUrl":"10.3389/fmed.2025.1571231","url":null,"abstract":"<p><strong>Background: </strong>Carbapenem-resistant Gram-negative bacteria (CR-GNB) pose a serious global health threat, especially in low- and middle-income countries. Local surveillance is crucial for informing antimicrobial stewardship and infection control strategies. This study aimed to evaluate the prevalence, demographic distribution, and temporal fluctuations of carbapenem resistance among key Gram-negative pathogens in a South Indian tertiary care center over a two-year period.</p><p><strong>Methods: </strong>A retrospective study was conducted on 8,359 non-duplicate Gram-negative isolates obtained from clinical specimens between July 2022 and July 2024. Organisms were identified, and antimicrobial susceptibility was determined using the VITEK^® 2 Compact system (BioMérieux). Resistance to imipenem (IPM) and meropenem (MEM) was assessed. Data were stratified by age, sex, ward type, specimen source, and quarterly distribution. A subset of resistant isolates underwent molecular screening for carbapenemase genes using real time PCR.</p><p><strong>Results: </strong>Carbapenem resistance was observed in 24% (2007) of Gram-negative isolates. <i>Acinetobacter baumannii</i> (48.0%) and <i>Klebsiella pneumoniae</i> (38.6%) accounted for the majority of resistant cases. Resistance was significantly higher in males (64.3%) and in patients aged 61-80 years (<i>p</i> < 0.001). Surgical wards showed greater resistance rates compared to medical departments. A peak in resistance was identified during January-March 2023, particularly for <i>A. baumannii</i> (76.3%). IPM-MEM resistance discrepancies were found in <i>Citrobacter</i> and <i>Proteus</i> species. Gene profiling of resistant strains revealed the predominance of <i>bla</i> _NDM, <i>bla</i> _VIM in <i>all organism.</i></p><p><strong>Conclusion: </strong>The findings reveal a high and fluctuating burden of carbapenem resistance, especially in elderly males and surgical settings. Continuous surveillance and targeted interventions are vital to curbing the spread of CR-GNB in high-risk healthcare environments.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1571231"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162471/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301652","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":"Correlation between serum autotaxin levels and optic neuropathy in early diabetic retinopathy: a case-control study.","authors":"Wenjun Chen, Xiaori Chen, Yaming Wang, Chuanheng Guo, Shaowen Yu, Wen Zhao","doi":"10.3389/fmed.2025.1553136","DOIUrl":"10.3389/fmed.2025.1553136","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To explore the correlation between serum autotaxin (ATX) levels and optic neuropathy in early diabetic retinopathy (DR).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A total of 90 patients with early DR who were treated in our hospital from August 2022 to December 2023 were selected as the Non diabetic neuropathy (NDN) group, and another 90 patients with early DR combined with optic neuropathy were selected as the combined diabetic neuropathy (DN) group. In addition 90 healthy patients were selected as a normal control group. The general data of the two groups of patients were collected, and the levels of inflammatory factors were compared, including the platelet-to-lymphocyte ratio (PLR), neutrophil-to-lymphocyte ratio (NLR), lymphocyte-to-monocyte ratio (LMR), systemic inflammation response index (SIRI), platelet-to-albumin ratio (PAR), serum C-reactive protein (CRP), tumor necrosis factor-α (TNF-α), and interleukin-6 (IL-6). The levels of ATX, glial fibrillary acid protein (GFAP), and neurofilament light chain protein (NfL) were also compared between the two groups. Retinal OCT examination was performed in both groups to record the foveal avascular zone (FAZ) area, acircularity index (AI), mean RNFL thickness at the disk margin, temporal, superior, nasal, and inferior, and mean macular ganglion cell inner plexiform layer (mGCIPL) thickness and vascular density (VD) levels. Pearson analysis was used to analyze the correlation between ATX and inflammatory factors, GFAP, NfL, mGCIPL, and VD levels. Multivariate Logistic regression analysis was used to analyze the influencing factors of optic neuropathy in DR patients. ROC curve analysis was used to analyze the clinical value of ATX in diagnosing optic neuropathy in DR patients.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;There were no significant differences in PLR, NLR, LMR, PAR, SIRI index, serum TNF-α, CRP, and IL-6 levels between the healthy group, the NDN group and the combined DN group (&lt;i&gt;P &gt;&lt;/i&gt; 0.05). However, serum ATX, GFAP, and NfL levels in the combined DN group were significantly higher than those in the healthy group and the NDN group, and the difference was statistically significant (&lt;i&gt;P &lt;&lt;/i&gt; 0.05). The mGCIPL and VD levels of the combined DN group were significantly lower than those of the healthy group and the NDN group, and the difference was statistically significant (&lt;i&gt;P&lt;/i&gt; &lt; 0.001). Pearson correlation analysis showed that the ATX level of DR patients was positively correlated with GFAP and NfL (&lt;i&gt;P&lt;/i&gt; &lt; 0.05), and negatively correlated with mGCIPL and VD levels (&lt;i&gt;P&lt;/i&gt; &lt; 0.001). The results of multivariate logistic regression analysis showed that serum ATX, GFAP, and NfL levels were independent risk factors for optic neuropathy in DR patients (&lt;i&gt;P&lt;/i&gt; &lt; 0.05), and GFAP and NfL were independent protective factors (&lt;i&gt;P&lt;/i&gt; = 0.001). The results of ROC curve analysis showed that the area under the curve (AUC) of ATX for diagnosing optic neuropathy in DR patient","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1553136"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12163047/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301632","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: ¹⁸F-FDG PET/CT revealed diffuse pancreatic metastasis in paranasal sinuses rhabdomyosarcoma after treatment improvement.","authors":"Xianwen Hu, Haojun Duan, Ying Zhao, Yongpeng Wang, Dongfeng Pan","doi":"10.3389/fmed.2025.1609837","DOIUrl":"10.3389/fmed.2025.1609837","url":null,"abstract":"<p><p>Metastasis of rhabdomyosarcoma (RMS) from primary paranasal sinuses to the pancreas is rare. Herein, we present a rare case of diffuse pancreatic metastasis in a 44-year-old man. He was diagnosed with sinus RMS 1 year ago and the lesion disappeared after systematic treatment. The patient came to our hospital in November 2022 due to abdominal pain. Abdominal ultrasound showed diffuse enlargement of the pancreas, with enlarged lymph nodes visible around the pancreas and retroperitoneum. He then underwent positron emission tomography/computed tomography (PET/CT) imaging and the results showed that the pancreas had diffusely increased fluorine-18 fluorodeoxyglucose (¹⁸F-FDG) uptake, and the surrounding pancreas and retroperitoneal lymph nodes also had increased ¹⁸F-FDG uptake, suggesting a possibility of malignant tumor. Ultimately, a pancreatic puncture biopsy confirmed RMS with pancreatic and abdominal lymph nodes metastasis. Our case suggests that although diffuse metastatic tumors of the pancreas are relatively rare, which should be considered as one of the differential diagnoses for diffuse pancreatic hypermetabolic lesions on PET/CT imaging.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1609837"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162518/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301618","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 efficacy and safety of biologics for patients with severe asthma: an umbrella review of systematic reviews and meta-analyses.","authors":"Qionghua Xiao, Yuanming Huang, Bingyu Xue, Minghang Wang","doi":"10.3389/fmed.2025.1573596","DOIUrl":"10.3389/fmed.2025.1573596","url":null,"abstract":"<p><strong>Introduction: </strong>Many systematic reviews and meta-analyses (SR/MAs) have evaluated the efficacy of biologic therapy for severe asthma. However, the quality of these SR/MAs is unclear, which may influence the selection of biologics and lead to misleading clinical decisions. Therefore, this umbrella review aims to objectively evaluate the quality of these SR/MAs and reassess the efficacy of biologic therapy for severe asthma.</p><p><strong>Methods: </strong>A systematic search was performed in PubMed, EMBASE, Cochrane Library, Web of Science, and MEDLINE databases. Literature screening and data extraction were conducted according to inclusion and exclusion criteria. Then, we evaluated the methodological quality of these SR/MAs using A MeaSurement Tool to Assess Reviews 2 (AMSTAR 2). In addition, the re-meta-analysis of study outcomes was performed applying R 4.3.3 software.</p><p><strong>Results: </strong>The umbrella review included 23 SR/MAs. In the evaluation of methodological quality, five SR/MAs were rated as high quality, one was rated as moderate, and 17 were rated as low or critically low. In terms of efficacy evaluation, biologics were associated with a 45% reduction in AER (RR: 0.55; <i>P</i> < 0.0001), a 57% reduction of asthma-related hospitalizations (RR: 0.43; <i>P</i> < 0.0001), an increase in the forced expiratory volume in 1 s (FEV1) of 0.13 L (<i>P</i> < 0.0001), a reduction in asthma control questionnaire (ACQ) scores by 0.33 points (<i>P</i> < 0.0001), an increase in asthma quality of life questionnaire (AQLQ) scores by 0.26 points (<i>P</i> < 0.0001), and a reduction in fractional exhaled nitric oxide (FeNO) levels by 22.52 ppb (<i>P</i> < 0.0001). In terms of safety evaluation, overall, biologics demonstrated favorable safety.</p><p><strong>Conclusion: </strong>This umbrella review has demonstrated that biologics have good efficacy and acceptable safety in the treatment of severe asthma. However, the methodological quality of included SR/MAs was mostly low or critically low, suggesting that we need to be cautious when interpreting the results of this study. Therefore, more high-quality SR/MAs are needed to provide robust clinical evidence.</p><p><strong>Systematic review registration: </strong>https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42024607393.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1573596"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162592/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301664","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":"Coping and quality of life of parents of children with achondroplasia-a narrative review.","authors":"Adekunle Adedeji, Stefanie Witt, Florian Innig, Inês Alves, Chiara Provasi, Marco Sessa, Klaus Mohnike, Julia Quitmann","doi":"10.3389/fmed.2025.1500389","DOIUrl":"10.3389/fmed.2025.1500389","url":null,"abstract":"<p><strong>Background: </strong>Caring for individuals with a chronic disease imposes a substantial burden on parents, significantly impacting their quality of life. For parents of children with achondroplasia, caregiving has notable implications for coping mechanisms and overall wellbeing. This review summarizes findings on these parents' coping strategies and quality of life.</p><p><strong>Methods: </strong>A narrative approach was employed to synthesize research on parental outcomes related to caring for a child with achondroplasia. The PRISMA chart flow was utilized to present the article screening strategy and results, following established guidelines for systematic reviews.</p><p><strong>Results: </strong>The review reveals a scarcity of studies examining the impact of caring for a child with achondroplasia on parental outcomes, with only two studies meeting the inclusion criteria. These studies suggest that having a child with achondroplasia significantly affects parental coping and quality of life, indicating substantial emotional and social implications. Additionally, no specific tools or measures to assess outcomes for these parents, highlighting a significant gap in research and resources.</p><p><strong>Conclusion: </strong>The parental experience of caring for a child with achondroplasia involves significant emotional and social challenges. Stressors from emotional distress, social isolation, altered family dynamics, and demanding healthcare interactions underscore the need for robust support systems. Addressing the research gaps requires developing and validating specific measures to assess the outcomes for parents of children with achondroplasia accurately. This will encourage further research and guide the development and evaluation of interventions to improve the coping and QoL of parents of children with achondroplasia.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1500389"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12163005/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301631","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 machine learning-based prediction of diabetic retinopathy using the Korea national health and nutrition examination survey (2008-2012, 2017-2021).","authors":"Min Seok Kim, Young Wook Choi, Borghare Shubham Prakash, Youngju Lee, Soo Lim, Se Joon Woo","doi":"10.3389/fmed.2025.1542860","DOIUrl":"10.3389/fmed.2025.1542860","url":null,"abstract":"<p><strong>Background: </strong>Machine learning technology that uses available clinical data to predict diabetic retinopathy (DR) can be highly valuable in medical settings where fundus cameras are not accessible.</p><p><strong>Objective: </strong>This study aimed to develop and compare machine learning algorithms for predicting DR without fundus image.</p><p><strong>Methods: </strong>We used data from Korea National Health and Nutrition Examination Survey (2008-2012 and 2017-2021) and enrolled individuals aged ≥ 20 years with diabetes who received fundus examination. Predictive models for DR were developed using logistic regression and three machine learning algorithms: extreme gradient boosting, decision tree, and random forest. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) and accuracy for the diagnosis of DR, and feature importance was determined using Shapley Additive Explanations (SHAP).</p><p><strong>Results: </strong>Among the 3,026 diabetic participants (male, 50.7%; mean age, 63.7 ± 10.5 years), 671 (22.2%) had DR. The random forest model, using 16 variables, achieved the highest AUC of 0.748 (95% confidence interval, 0.705-0.790) with a sensitivity 0.669, specificity of 0.729 and an accuracy of 0.715. As interpreted by SHAP, HbA1c, fasting glucose levels, duration of diabetes, and body mass index were identified as common key determinants influencing the model's outcomes.</p><p><strong>Conclusion: </strong>The DR prediction models using machine learning techniques demonstrated reliable performance even without fundus imaging, with the random forest model showing particularly strong results. These models could assist in managing DR by identifying high-risk patients, enabling timely ophthalmic referrals.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1542860"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12163237/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301610","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":"Triglyceride-glucose index is associated with lupus nephritis and gender disparity in systemic lupus erythematosus patients.","authors":"Shuhan Lin, Liangying Tao, Fan Yang, Ruilu Shu, Weimeng Cheng, Lihui Wen, Huayong Zhang","doi":"10.3389/fmed.2025.1579187","DOIUrl":"10.3389/fmed.2025.1579187","url":null,"abstract":"<p><strong>Objective: </strong>Recent studies investigated that triglyceride glucose (TyG) index and triglyceride (TG) are associated with an elevated likelihood of developing and worsening chronic kidney disease (CKD). We aimed to evaluate the correlation between the TyG index and TG with lupus nephritis (LN), respectively, and explore its value in monitoring LN.</p><p><strong>Methods: </strong>1,192 Systemic Lupus Erythematosus (SLE) patients were involved in this cross-sectional investigation. The presence or absence of LN was used to divide the individuals involved into two distinct categories. Multivariate logistic regression, restricted cubic spline, and subgroup analyses were applied to explore the connection between the TyG index and TG with LN, respectively.</p><p><strong>Results: </strong>According to the study, the TyG index and TG were dose-dependently positively correlated with LN. After accounting for additional factors, each standard deviation of an upsurge in the TyG index and TG corresponded to a higher risk for LN by 36.4 and 34%, respectively. Besides, the adjusted ORs (with 95% CIs) for LN were precisely 1.625 (1.097, 2.405) and 1.756 (1.193, 2.585) when comparing the highest tertile to the lowest tertile of the TyG index and TG, respectively. Additionally, both TyG index and TG were significantly positively correlated with LN in age and body mass index (BMI) subgroups, and these two indicators were independently associated with LN in female SLE patients but not in male SLE patients, respectively.</p><p><strong>Conclusion: </strong>Both the elevated TyG index and TG were linked to LN on their own and gender disparity in SLE patients, which suggests that the TyG index and TG could be beneficial in the early screening for those with LN.</p>","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":"12 ","pages":"1579187"},"PeriodicalIF":3.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162929/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144301667","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}