Medicine Advances最新文献

{"title":"Nutritional Treatment After Discharge of Older Patients at Nutritional Risk: A Study Protocol for a Feasibility Study","authors":"Martine Kjærsgaard Nielsen,&nbsp;Tina Munk,&nbsp;Anne Marie Beck,&nbsp;Jacob Rosenberg,&nbsp;Jesper Ryg","doi":"10.1002/med4.70078","DOIUrl":"https://doi.org/10.1002/med4.70078","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Malnutrition is prevalent among older hospitalized patients, increasing the risk of complications, extended hospital stays, and reduced quality of life. Upon discharge, a nutritional gap frequently arises, leading to insufficient intake for optimal recovery. Ensuring nutritional treatment in research settings after hospital discharge has demonstrated improvements in readmission rates, muscle strength, quality of life, and nutritional status. This study aims to evaluate the feasibility and effectiveness of nutritional treatment for older patients at nutritional risk after hospital discharge in a real-life context.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>This is a feasibility study conducted in cooperation with nine municipalities in Denmark and included a historical control group. At hospital discharge, older patients at nutritional risk referred to the liaison team receive a customized food package. Individualized dietary counseling is provided by a hospital dietitian during follow-up 2–4, 30, and 90 days after discharge, with municipal follow-up offered as needed. The primary outcome is feasibility regarding the proportion of patients included, recruited, and retained for nutritional treatment. Secondary outcomes include readmissions, mortality, quality of life, appetite, muscle strength, dietary intake, weight, and muscle mass.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Older patients at nutritional risk may experience a nutritional gap at hospital discharge. Despite evidence highlighting the importance of nutritional care during the transition from hospital to home, cross-sector initiatives have not been effectively implemented. This study will investigate the feasibility of nutritional treatment across sectors when older patients at nutritional risk are discharged. Therefore, the results of this study could contribute to establishing a model for effective large-scale implementation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"363-372"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149043621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differential Transcriptome Analysis of Lung Squamous Cell Carcinoma Under Different RUNX3 Expression Patterns","authors":"Weibin Liu,&nbsp;Xiaobin Zheng,&nbsp;Jianqing Zheng,&nbsp;Yujie Deng,&nbsp;Bifen Huang,&nbsp;Weijin Xiao,&nbsp;Jiarong Zhang,&nbsp;Xuejin Zheng,&nbsp;Xinlong Zheng,&nbsp;Gen Lin,&nbsp;Xiaohui Chen","doi":"10.1002/med4.70077","DOIUrl":"https://doi.org/10.1002/med4.70077","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Runt-related transcription factor 3 (RUNX3) functions as a tumor suppressor gene in numerous cancer types, including non-small cell lung cancer, with its hypermethylation status predicting worse patient prognosis. However, any discrepancy in gene expression profiles in lung squamous cell carcinoma (LUSC) patients with different RUNX3 expression patterns remains unclear. In this study, RNA sequencing analysis was used to examine the transcriptomic differences in LUSC samples depending on their RUNX3 expression status.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Immunohistochemistry staining was used to determine the RUNX3 protein expression patterns in tumor samples. Tumor RNA was extracted from 63 LUSC cases and underwent RNA sequencing. Read counts were analyzed using Spearman's correlation, limma differential expression with Benjamini-Hochberg false discovery rate (BH-FDR) control, and gene set variation analysis (GSVA).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>In our LUSC cohort, 31 (49.21%) patients were classified as RUNX3_Positive (RUNX3_Pos) and 32 (50.79%) were classified as RUNX3_Negative. RUNX3 mRNA expression levels were significantly higher in the RUNX3_Pos group. Using limma with BH correction, no genes passed the BH-FDR &lt; 0.05 threshold between the groups, suggesting subtle gene-level differences. Therefore, we reported an exploratory nominal gene list (<i>p</i> &lt; 0.05 and |log₂ fold-change| &gt; 1; 131 upregulated and 57 downregulated) for hypothesis generation only. Spearman's correlation identified 5047 positively and 25 negatively correlated mRNAs with RUNX3. GSVA suggested exploratory pathway activity patterns, with 57 pathways showing nominally higher and nine pathways showing nominally lower GSVA scores in RUNX3_Pos's tumors.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The RUNX3-defined groups showed no BH-FDR-significant differentially expressed genes, but exhibited exploratory, nominal pathway activity patterns. These results generate testable hypotheses on RUNX3-related biological programs in LUSC for future validation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"373-382"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Outcomes of Kinematic Alignment Versus Mechanical Alignment in Total Knee Arthroplasty: An Umbrella Review of Published Meta-Analyses and Systematic Reviews","authors":"Chuanxin Wang,&nbsp;Haisheng Yu,&nbsp;Bingyang Yan,&nbsp;Dezhi Yan,&nbsp;Wenfei Wu,&nbsp;Di Luo,&nbsp;Yanbo Guo,&nbsp;Wenzhao Wang,&nbsp;Liang Ma","doi":"10.1002/med4.70061","DOIUrl":"https://doi.org/10.1002/med4.70061","url":null,"abstract":"<p>Mechanical alignment (MA) has long been the standard in total knee arthroplasty, but kinematic alignment (KA) has gained attention as an alternative aiming to restore native knee kinematics; however, comparative evidence on its efficacy and safety remains inconclusive. This study presents an umbrella review comparing KA and MA techniques in total knee arthroplasty. A comprehensive database search was conducted for meta-analyses published up to January 2023. The original articles included in those meta-analyses were also retrieved for further analysis. Eleven meta-analyses, incorporating 30 original studies and 2963 patients, were included. Re-analysis of controversial outcomes and revision rate data revealed the following: (1) KA was associated with a higher Knee Society Score and Oxford Knee Score; (2) KA yielded lower Western Ontario and McMaster Universities Osteoarthritis Index scores compared with MA; (3) KA resulted in greater flexion range of motion but worse extension range of motion than MA; (4) KA was associated with a higher Forgotten Joint Score-12; (5) KA resulted in greater femoral valgus and tibial valgus angles, and (6) revision rates were comparable between KA and MA. In patients undergoing total knee arthroplasty, KA demonstrated better clinical outcomes, improved postoperative osteoarthritis-related symptoms, and greater flexion mobility. Patients in the KA group also reported a higher level of prosthesis “forgetting,” suggesting a more natural postoperative experience. While KA resulted in greater femoral valgus and tibial inversion angles, it may serve as a viable alternative to MA and has the potential to improve patient satisfaction.</p>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"261-273"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70061","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patient-Reported Quality of Life-Based Machine Learning Model Predicting Sudden Cardiac Death in Heart Failure With Preserved Ejection Fraction: Kansas City Cardiomyopathy Questionnaire-Based Sudden Cardiac Death Score","authors":"Xiao Liu,&nbsp;Zenghui Zhang,&nbsp;Mingyue Cui,&nbsp;Chunjie Shu,&nbsp;Weiliang Yu,&nbsp;Hong Pan,&nbsp;Ayiguli Abudukeremu,&nbsp;Ke Zhao,&nbsp;Minglong Zheng,&nbsp;Zhengyu Cao,&nbsp;Jingfeng Wang,&nbsp;Yuling Zhang,&nbsp;Yangxin Chen","doi":"10.1002/med4.70081","DOIUrl":"https://doi.org/10.1002/med4.70081","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Sudden cardiac death (SCD) is the most frequent cause of mortality in patients with heart failure with preserved ejection fraction (HFpEF). While the Kansas City Cardiomyopathy Questionnaire (KCCQ) assesses disease severity in HFpEF, its ability to predict SCD remains unclear. We aimed to develop a machine learning model to stratify the risk of SCD in HFpEF using patients' reported quality of life scores.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Using data from the Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist trial, we developed six models (convolutional neural network [CNN], logistic regression, LASSO-regularized logistic regression, random forest, gradient boosting, and K-nearest neighbors) to predict SCD in HFpEF, using age, sex, and the KCCQ score.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Among 3445 patients (mean age: 69.1 years, 48.5% men), 111 experienced SCD over a mean follow-up of 3.37 years. The CNN model outperformed the other models, with a C-statistic of 0.74 (95% confidence interval [CI]: 0.65–0.83), followed by the logistic regression model (0.66, 95% CI: 0.56–0.76), XGBoost (0.65, 95% CI: 0.56–0.75), Light-GBM (0.62, 95% CI: 0.51–0.74), random forest (0.54, 95% CI: 0.41–0.66), and K-nearest neighbors (0.54, 95% CI: 0.43–0.64). The total symptom score, social limitation score, self-efficacy score, and overall summary score were ranked as the most important variables. The KCCQ-SCD score was associated with a fivefold higher risk of SCD (hazard ratio: 5.69, 95% CI: 1.92–16.81). An online tool to implement the CNN model is available at https://huggingface.co/spaces/KCCQ/KCCQ_SCD_Predictor.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>A CNN-based machine learning model incorporating age, sex, and KCCQ scores provides a simple and accurate tool for stratifying the risk of SCD in patients with HFpEF. External validation in more diverse populations and real-world clinical settings is essential before the KCCQ-SCD score is used for broad clinical applications.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"352-362"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70081","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149048029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-Enabled Cardiac Rehabilitation for Patients With Heart Failure After Myocardial Infarction: Current Status and Future Prospects","authors":"Xinyuan Huang,&nbsp;Di Chen,&nbsp;Yumin Cai,&nbsp;Zihan Chen,&nbsp;Dongmei Xie,&nbsp;Chaoquan Peng,&nbsp;Yuanlong Li","doi":"10.1002/med4.70082","DOIUrl":"https://doi.org/10.1002/med4.70082","url":null,"abstract":"<p>Heart failure remains one of the most significant complications following myocardial infarction, severely impairing patients' quality of life and contributing to elevated mortality rates. In clinical practice, these patients commonly undergo cardiac rehabilitation (CR) to enhance their functional status and overall quality of life, but the uptake of CR remains below 50%. Here, we integrated artificial Intelligence (AI) approaches with vital signs, lifestyle habits, and adherence to CR programs in patients who have suffered myocardial infarction complicated by heart failure. Also, we present the current applications of AI related to the current landscape of CR, encompassing machine learning and deep learning. This review might inform future research and clinical practice of AI-enabled cardiac rehabilitation for patients with heart failure post-myocardial infarction.</p>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"305-315"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70082","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Deep Learning and Hybrid Architectures in Biomedical Data Analysis for Advances in Medicine","authors":"Lifeng Li,&nbsp;Ashfaque Khowaja,&nbsp;Yucheng Song,&nbsp;Mingwei Zhang,&nbsp;Shabir Hussain","doi":"10.1002/med4.70079","DOIUrl":"https://doi.org/10.1002/med4.70079","url":null,"abstract":"<p>Traditional diagnostic methods in biomedicine are often constrained by subjectivity, misdiagnosis, and the inability to efficiently process large, complex, and multimodal datasets. Recent advances in deep learning and hybrid architectures have enabled the automated learning of discriminative representations from high-dimensional biomedical data, supporting robust classification and integrative analysis across imaging, physiological signals, and clinical texts. This review synthesizes the current progress in applying deep learning to neuroimaging, cardiovascular disease diagnosis, functional connectivity analysis, and biomedical text mining, focusing on hybrid and ensemble strategies that combine complementary modeling strengths. These approaches show improved accuracy, scalability, and adaptability while extending situational awareness by incorporating patient-generated and clinical textual data. Despite promising outcomes, challenges remain in data availability, computational efficiency, interpretability, and clinical integration. Future directions emphasize the development of explainable, multimodal, and generalizable frameworks capable of supporting precision medicine and advancing patient-centered care.</p>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"274-286"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70079","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early Mpox Detection: Integrating Skin Lesion Imaging, Epidemiology, and Treatment for Deep Learning Approaches","authors":"Taskin Sabit,&nbsp;Faiza Tasnim","doi":"10.1002/med4.70086","DOIUrl":"https://doi.org/10.1002/med4.70086","url":null,"abstract":"<p>Mpox, previously known as monkeypox, is an evolving zoonotic infection that raises serious public health issues, especially in low-income settings. The recent outbreaks have indicated the existence of a need for fast, accurate and scalable diagnostics. The article under review examines how up to date convolutional neural networks may be combined with clinical knowledge in the process of early detection of mpox based on pictures of skin lesions. Among the architectures evaluated, MobileNetV2, VGG16 and GoogLeNet reported accuracy exceeding 95% in experiments conducted on publicly available datasets. While these findings demonstrate technical feasibility, such performance does not constitute evidence of clinical readiness. The reported performance reflects controlled offline validation and may be influenced by sample size, limited demographic diversity, and absence of standardized external evaluation. Future work involves building heterogeneous, labeled data sets and the integration of multi-modal data for higher diagnostic consistency. Although deep learning-based systems show promising experimental accuracy and computational efficiency, their integration into clinical workflows requires prospective validation, multi-center evaluation, and regulatory assessment before real-world deployment can be recommended.</p>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"287-296"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70086","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Past Achievements to Future Hotspots: Bibliometric View of Influential Studies on Microfracture Research","authors":"Boshen Shu","doi":"10.1002/med4.70080","DOIUrl":"https://doi.org/10.1002/med4.70080","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Microfracture has historically been considered an acceptable method for treating cartilage defects. A substantial body of literature on this technique has accumulated over the past few decades. Citation metrics serve as a critical tool for assessing scholarly impact and prompting scientific developments. The aim of this study was to analyze the top 100 most-cited articles in this field.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Accessible articles published from inception to 2023 were extracted from the Web of Science Core Collection database. The top 100 publications were identified and analyzed in terms of citation count, year of publication, authorship, citation density (citations per article age), journal, impact factor, geographic origin, evidence level, study design, and institutional affiliation.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Citation counts for the included articles ranged from 945 to 51, with citation densities between 49.7 and 2.9. Publication years spanned from 1999 to 2019. Randomized controlled trials were the most common study design, while Level IV represented the most frequent evidence level. “Autologous chondrocyte implantation,” “osteochondral autograft transplantation,” and “arthroscopic treatment” have emerged as current focal points in the field.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>This study provides a comprehensive analysis of the top 100 most-cited articles on microfracture. Compared with prior bibliometric studies in orthopedics, influential articles on microfracture showed a higher proportion of Level I and II evidence. These findings offer valuable insights into the development of microfracture research and may help clinicians efficiently identify the foundational literature in the field.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"383-400"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70080","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Home-Based Nutritional Counseling After Abdominal Surgery: A Scoping Review Revealing Limited and Heterogeneous Evidence","authors":"Elna A. Dalsgaard,&nbsp;Troels G. Dolin,&nbsp;Tina Munk,&nbsp;Jesper Ryg,&nbsp;Jacob Rosenberg","doi":"10.1002/med4.70084","DOIUrl":"https://doi.org/10.1002/med4.70084","url":null,"abstract":"<p>Patients undergoing abdominal surgery frequently experience inadequate postoperative nutritional intake, potentially compromising recovery. Enhanced Recovery After Surgery (ERAS) protocols emphasize nutrition, but guidance typically ends at hospital discharge, leaving a gap in nutritional support during home recovery. Although post-discharge nutritional counseling by dietitians has shown benefits in non-surgical populations, its effectiveness after abdominal surgery remains unclear. This scoping review mapped and characterized studies on home-based nutritional counseling delivered by dietitians or trained healthcare professionals after abdominal surgery, focusing on intervention components and reported outcomes. A systematic search of PubMed, Embase, Cumulative Index to Nursing and Allied Health Literature (CINAHL), and Cochrane databases was conducted. Eligible studies included original research on home-based nutritional counseling for adults after abdominal surgery, excluding bariatric or obesity-related surgery, enteral or parenteral nutrition, and weight loss interventions. Two reviewers independently screened records, and data were extracted according to a preregistered protocol. From 3783 records, 12 publications were included. Most involved elective surgeries in adults aged ≥ 50 years. Nutritional counseling was primarily delivered remotely by telephone and frequently included oral nutritional supplements and guidance to achieve protein intakes of 1.0–1.5 g/kg/day. Outcomes were heterogeneous. Nutritional intake improved following the interventions, and trends suggested benefits for reduced weight loss, muscle mass, and quality of life, although findings were mixed. Patient-reported outcomes were variably assessed using multiple instruments, and evidence for functional and clinical outcomes was limited. Current evidence on home-based nutritional counseling after abdominal surgery remains limited and heterogeneous. Future studies should provide clearer descriptions of counseling content and adopt standardized outcome measures aligned with core outcome sets to improve comparability and strengthen the evidence for clinical practice.</p>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"297-304"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70084","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large Language Model Benchmarks in Medical Tasks","authors":"Lawrence K. Q. Yan,&nbsp;Qian Niu,&nbsp;Ming Li,&nbsp;Yichao Zhang,&nbsp;Caitlyn Heqi Yin,&nbsp;Cheng Fei,&nbsp;Benji Peng,&nbsp;Ziqian Bi,&nbsp;Pohsun Feng,&nbsp;Keyu Chen,&nbsp;Tianyang Wang,&nbsp;Yunze Wang,&nbsp;Silin Chen,&nbsp;Ming Liu,&nbsp;Junyu Liu,&nbsp;Xinyuan Song,&nbsp;Riyang Bao,&nbsp;Zekun Jiang,&nbsp;Ziyuan Qin","doi":"10.1002/med4.70085","DOIUrl":"https://doi.org/10.1002/med4.70085","url":null,"abstract":"<p>With the increasing application of large language models (LLMs) in the medical domain, evaluating these models' performance using benchmark datasets has become crucial. This paper presents a comprehensive survey of various benchmark datasets used in medical LLM tasks. These datasets span multiple modalities including text, image, and multimodal benchmarks, focusing on various aspects of medical knowledge such as electronic health records, doctor–patient dialogues, medical question answering, and medical image captioning. The survey categorizes the datasets by modality and examines their significance, data structure, and roles in model development and evaluation across tasks such as diagnostic support, report generation, and predictive decision support. Representative resources include Medical Information Mart for Intensive Care III (MIMIC-III), MIMIC-IV, BioASQ, PubMedQA, and CheXpert, which provide data and evaluation settings for research in clinical NLP, medical question answering, and chest-radiograph interpretation. This paper summarizes the challenges and opportunities in leveraging these benchmarks for advancing multimodal medical intelligence, emphasizing the need for datasets with a greater degree of language diversity, structured omics data, and innovative approaches to synthesis. This synthesis is intended to inform future research on the applications of LLMs in medicine and medical artificial intelligence.</p>","PeriodicalId":100913,"journal":{"name":"Medicine Advances","volume":"4 3","pages":"316-341"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/med4.70085","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149047909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}