检索结果-内蒙古大学图书馆

Gastroenterology 2025年第5期168卷 1040-1041页

作者： Dennis L. Shung Section of Digestive Diseases Department of Medicine Yale School of Medicine New Haven Connecticut Department of Biomedical Informatics and Data Science Yale School of Medicine New Haven Connecticut

来源：评论

学校读者我要写书评

暂无评论

Effects of Tirzepatide in Type 2 Diabetes: Individual Variation and Relationship to Cardiometabolic Outcomes

引用

Journal of the American College of Cardiology 2025年第19期85卷 1858-1872页

作者： Aminorroaya, Arya Oikonomou, Evangelos K. Biswas, Dhruva Jastreboff, Ania M. Khera, Rohan Section of Cardiovascular Medicine Department of Internal Medicine Yale School of Medicine New Haven CT United States Cardiovascular Data Science (CarDS) Lab Yale School of Medicine New Haven CT United States Section of Endocrinology and Metabolism Department of Medicine Yale School of Medicine New Haven CT United States Section of Pediatric Endocrinology Department of Pediatrics Yale School of Medicine New Haven CT United States Yale Obesity Research Center (Y-Weight) Yale School of Medicine New Haven CT United States Center for Outcomes Research and Evaluation (CORE) Yale New Haven Hospital New Haven CT United States Section of Biomedical Informatics and Data Science Yale School of Medicine New Haven CT United States Section of Health Informatics Department of Biostatistics Yale School of Public Health New Haven CT United States

Background: Tirzepatide—a dual GIP/GLP-1 receptor agonist—exerts pleiotropic effects on cardiometabolic health. Objectives: The authors sought to investigate the efficacy of tirzepatide in improving different cardiometabolic risk factors across individuals and subpopulations. Methods: Using an independent, global data-sharing and analytics platform, we performed an individual participant data meta-analysis by pooling data from 7 Phase 3 randomized clinical trials that compared tirzepatide with placebo or standard antihyperglycemic agents in individuals with type 2 diabetes. The study outcomes were the presence of a range of cardiometabolic abnormalities, representing components of metabolic syndrome (MetS) (elevated waist circumference, triglycerides, blood pressure, and fasting blood glucose, and decreased high-density lipoprotein cholesterol), as well as elevated body mass index and MetS (≥3 cardiometabolic abnormalities). Outcomes were modeled using mixed-effects models, with inverse probability weighting to account for study design differences. Results: We included 7,805 participants with a weighted median age of 59 years (Q1-Q3: 51-66 years) and 43.2% women. Over a weighted median treatment duration of 41.0 weeks, tirzepatide reduced the odds of all cardiometabolic abnormalities, ranging from 34% reduction for the odds of decreased high-density lipoprotein cholesterol (OR: 0.66 [95% CI: 0.52-0.84]) to 96% reduction in the odds of elevated body mass index (OR: 0.04 [95% CI:0.02-0.08]), and 72% reduction for the odds of MetS (OR: 0.28 [95% CI: 0.24-0.33]). Tirzepatide's superior efficacy in resolving MetS was consistent across demographic and clinical subpopulations, with higher efficacy in age <65 years vs ≥65 years, and in individuals without vs with baseline use of sodium-glucose cotransporter 2 inhibitors (P for interaction = 0.008 and 0.009, respectively). Conclusions: This pooled analysis suggests that tirzepatide may improve cardiometabolic abnormalities a

关键词： diabetes mellitus type 2 heart disease risk factors meta-analysis randomized controlled trial tirzepatide

来源：评论

学校读者我要写书评

暂无评论

Revealing cancer driver genes through integrative transcriptomic and epigenomic analyses with Moonlight

引用

PLoS Computational Biology 2025年第4 April期21卷 e1012999页

作者： Nourbakhsh, Mona Zheng, Yuanning Noor, Humaira Chen, Hongjin Akhuli, Subhayan Tiberti, Matteo Gevaert, Olivier Papaleo, Elena Cancer Systems Biology Section for Bioinformatics Department of Health Technology Technical University of Denmark Lyngby Denmark Cancer Structural Biology Danish Cancer Institute Copenhagen Denmark Department of Biomedical Data Science Stanford Center for Biomedical Informatics Research Palo AltoCA United States

Cancer involves dynamic changes caused by (epi)genetic alterations such as mutations or abnormal DNA methylation patterns which occur in cancer driver genes. These driver genes are divided into oncogenes and tumor suppressors depending on their function and mechanism of action. Discovering driver genes in different cancer (sub)types is important not only for increasing current understanding of carcinogenesis but also from prognostic and therapeutic perspectives. We have previously developed a framework called Moonlight which uses a systems biology multi-omics approach for prediction of driver genes. Here, we present an important development in Moonlight2 by incorporating a DNA methylation layer which provides epigenetic evidence for deregulated expression profiles of driver genes. To this end, we present a novel functionality called Gene Methylation Analysis (GMA) which investigates abnormal DNA methylation patterns to predict driver genes. This is achieved by integrating the tool EpiMix which is designed to detect such aberrant DNA methylation patterns in a cohort of patients and further couples these patterns with gene expression changes. To showcase GMA, we applied it to three cancer (sub)types (basal-like breast cancer, lung adenocarcinoma, and thyroid carcinoma) where we discovered 33, 190, and 263 epigenetically driven genes, respectively. A subset of these driver genes had prognostic effects with expression levels significantly affecting survival of the patients. Moreover, a subset of the driver genes demonstrated therapeutic potential as drug targets. This study provides a framework for exploring the driving forces behind cancer and provides novel insights into the landscape of three cancer sub(types) by integrating gene expression and methylation data. © 2025 Nourbakhsh et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, p

关键词： Transcription

来源：评论

学校读者我要写书评

暂无评论

rmlnomogram: An R package to construct an explainable nomogram for any machine learning algorithms

arXiv

引用

arXiv 2025年

作者： Sufriyana, Herdiantri Su, Emily Chia-Yu Institute of Biomedical Informatics College of Medicine National Yang Ming Chiao Tung University Taipei Taiwan Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan Clinical Big Data Research Center Taipei Medical University Hospital Taipei Taiwan Institute of Biomedical Informatics College of Medicine National Yang Ming Chiao Tung University 155 Section 2 Linong Street Beitou District Taipei112304 Taiwan

Background: Current nomogram can only be created for regression algorithm. Providing nomogram for any machine learning (ML) algorithms may accelerate model deployment in clinical settings or improve model availability. We developed an R package and web application to construct nomogram with model explainability of any ML algorithms. Methods: We formulated a function to transform an ML prediction model into a nomogram, requiring datasets with: (1) all possible combinations of predictor values;(2) the corresponding outputs of the model;and (3) the corresponding explainability values for each predictor (optional). Web application was also created. Results: Our R package could create 5 types of nomograms for categorical predictors and binary outcome without probability (1), categorical predictors and binary outcome with probability (2) or continuous outcome (3), and categorical with single numerical predictors and binary outcome with probability (4) or continuous outcome (5). Respectively, the first and remaining types optimally allowed maximum 15 and 5 predictors with maximum 3,200 combinations. Web application is provided with such limits. The explainability values were possible for types 2 to 5. Conclusions: Our R package and web application could construct nomogram with model explainability of any ML algorithms using a fair number of predictors. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Artificial Intelligence for Innovation in Interventional Cardiovascular Care

引用

Journal of the Society for Cardiovascular Angiography and Interventions 2025年第3期4卷 102562-102562页

作者： Aminorroaya, Arya Biswas, Dhruva Pedroso, Aline F. Khera, Rohan Section of Cardiovascular Medicine Department of Internal Medicine Yale School of Medicine New Haven Connecticut United States Cardiovascular Data Science (CarDS) Lab Yale School of Medicine New Haven Connecticut United States Center for Outcomes Research and Evaluation (CORE) Yale New Haven Hospital New Haven Connecticut United States Section of Biomedical Informatics and Data Science Yale School of Medicine New Haven Connecticut United States Section of Health Informatics Department of Biostatistics Yale School of Public Health New Haven Connecticut United States

Artificial intelligence (AI) serves as a powerful tool that can revolutionize how personalized, patient-focused care is provided within interventional cardiology. Specifically, AI can augment clinical care across the spectrum for acute coronary syndrome, coronary artery disease, and valvular heart disease, with applications in coronary and structural heart interventions. This has been enabled by the potential of AI to harness various types of health data. We review how AI-driven technologies can advance diagnosis, preprocedural planning, intraprocedural guidance, and prognostication in interventional cardiology. AI automates clinical tasks, increases efficiency, improves reliability and accuracy, and individualizes clinical care, establishing its potential to transform care. Furthermore, AI-enabled, community-based screening programs are yet to be implemented to leverage the full potential of AI to improve patient outcomes. However, to transform clinical practice, AI tools require robust and transparent development processes, consistent performance across various settings and populations, positive impact on clinical and care quality outcomes, and seamless integration into clinical workflows. Once these are established, AI can reshape interventional cardiology, improving precision, efficiency, and patient outcomes. © 2025 The Author(s)

关键词： artificial intelligence interventional cardiology percutaneous coronary intervention structural heart intervention

来源：评论

学校读者我要写书评

暂无评论

Use of Intravascular Ultrasound during Peripheral Vascular Interventions for Claudication Is Not Associated with Improved Outcomes

引用

Annals of Vascular Surgery 2025年 119卷 14-28页

作者： Dun, Chen Weaver, M. Libby Bose, Sanuja McDermott, Katherine M. Deery, Sarah E. Black, James H. Siracuse, Jeffrey J. Columbo, Jesse Hicks, Caitlin W. Department of Biomedical Informatics and Data Science The Johns Hopkins University School of Medicine Baltimore MD United States Department of Surgery The Johns Hopkins University School of Medicine Baltimore MD United States Division of Vascular and Endovascular Surgery University of Virginia Charlottesville VA United States Division of Vascular Surgery and Endovascular Therapy The Johns Hopkins University School of Medicine Baltimore MD United States Division of Vascular Surgery Maine Medical Center Portland ME United States Division of Acute Care Surgery Department of Surgery Beth Israel Deaconess Medical Center and Harvard Medical School Boston MA United States Section of Vascular Surgery Heart and Vascular Center Dartmouth Hitchcock Medical Center Lebanon NH United States

Background: The efficacy of intravascular ultrasound (IVUS) for improving outcomes of peripheral vascular interventions (PVIs) has not been well studied. We aimed to evaluate the association of IVUS with long-term outcomes in patients undergoing PVI for claudication. Methods: We conducted a two-cohort study using data from 100% of Medicare fee-for-service claims (2018–2022) and the Vascular Quality Initiative Vascular Implant Surveillance and Interventional Outcomes Network (VISION;2016–2019). For both cohorts, we identified all patients who underwent an index (first-time) femoropopliteal PVI for claudication, excluding patients with chronic limb-threatening ischemia (CLTI) and acute limb ischemia. We compared IVUS use over time and by procedure type and setting. We used multivariable Cox proportional hazards models to assess the associations of IVUS with repeat PVI, conversion to CLTI, and amputation. For the Medicare cohort, adjustments were made for baseline patient characteristics, while for the VISION cohort, additional adjustments were made for detailed anatomic factors. All models were clustered by physician. Results: In the Medicare dataset, 69,092 patients (median age 74 years;40.5% female;12.1% non-Hispanic Black) underwent an index femoropopliteal PVI for claudication, of whom 22.1% (N = 15,253) received IVUS. In the VISION dataset, 6,722 patients (median age 72 years;38.7% female;11.6% non-Hispanic Black) underwent an index femoropopliteal PVI for claudication, of whom 3.8% (N = 254) received IVUS. The mean follow-up time for both cohorts was 2.7 years. For both the Medicare and VISION cohorts, IVUS use significantly increased over time, particularly in ambulatory surgery center/office-based laboratory settings and in conjunction with atherectomy procedures (P < 0.001). In the Medicare cohort, IVUS use was associated with a higher hazard of repeat PVI (adjusted hazard ratio [aHR] 1.07, 95% CI 1.02–1.12) and progression to CLTI (aHR 1.11, 95% CI 1.03–1.20

关键词： amputation chronic limb-threatening ischemia endovascular reintervention ultrasound

来源：评论

学校读者我要写书评

暂无评论

An Overview and Recent Developments in the Analysis of Multistate Processes

arXiv

引用

arXiv 2025年

作者： Gorfine, Malka Cook, Richard J. Andersen, Per Kragh Therneau, Terry M. Joly, Pierre Putter, Hein Perme, Maja Pohar Abrahamowicz, Michal Department of Statistics and Operations Research Tel Aviv University Israel Department of Statistics and Actuarial Science University of Waterloo Canada Section of Biostatistics University of Copenhagen Denmark Division of Biomedical Statistics and Informatics Mayo Clinic New York United States Inserm ISPED Bordeaux Populations Health Research Center University of Bordeaux France Department of Biomedical Data Sciences Leiden University Medical Center Leiden Netherlands Department of Biostatistics and Medical Informatics Medical Faculty University of Ljubljana Slovenia Department of Epidemiology Biostatistics and Occupational Health McGill University MontrealQC Canada

Multistate models offer a powerful framework for studying disease processes and can be used to formulate intensity-based and more descriptive marginal regression models. They also represent a natural foundation for the construction of joint models for disease processes and dynamic marker processes, as well as joint models incorporating random censoring and intermittent observation times. This article reviews the ways multistate models can be formed and fitted to life history data. Recent work on pseudo-values and the incorporation of random effects to model dependence on the process history and between-process heterogeneity are also discussed. The software available to facilitate such analyses is listed. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

T2 Coach: A Qualitative Study of an Automated Health Coach for Diabetes Self-Management 25

T2 Coach: A Qualitative Study of an Automated Health Coach f...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Elliot G Mitchell Pooja Desai Arlene Smaldone Andrea Cassells, MPH Jonathan N. Tobin, PhD David Albers Matthew Levine Lena Mamykina Geisinger Health Danville Pennsylvania USA Department of Biomedical Informatics Columbia University Irving Medical Center New York New York USA School of Nursing Columbia University New York New York USA College of Dental Medicine Columbia University New York New York USA Clinical Directors Network New York New York USA Clinical Directors Network (CDN) New York New York USA Center for Clinical and Translational Science The Rockefeller University New York New York USA Department of Pediatrics Section of Informatics and Data Science University of Colorado Anschutz Medical Center Aurora Colorado USA Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Massachusetts USA Department of Biomedical Informatics Columbia University New York New York USA

ISBN: (纸本)9798400713941

Computational intelligence is increasingly common in interactive systems in many domains, including health. Health coaching with conversational agents (CA) can reach wide populations, but the level of computational intelligence needed for a positive coaching experience is unclear. We conducted a study with sixteen individuals with diabetes and prediabetes who used a CA for health coaching, T2 Coach. Qualitative interviews revealed that participants saw T2 Coach as reliable in helping them stay on track with self-management, appreciated the flexibility in choosing personally meaningful goals and engaging on their own terms, and felt it provided encouragement and even compared it favorably with human coaches. However, they also noted that coaching experience could be improved with more fluid conversations, more tailoring to their personal preferences and lifestyles, and more sensitivity to specific contexts, all of which require more computational intelligence. We discuss implications and design directions for more intelligent coaching CA in health.

关键词： Health

来源：评论

学校读者我要写书评

暂无评论

Expert of Experts Verification and Alignment (EVAL) Framework for Large Language Models Safety in Gastroenterology

引用

npj Digital Medicine 2025年第1期8卷 1-14页

作者： Giuffrè, Mauro You, Kisung Pang, Ziteng Kresevic, Simone Chung, Sunny Chen, Ryan Ko, Youngmin Chan, Colleen Saarinen, Theo Ajcevic, Milos Crocè, Lory S. Garcia-Tsao, Guadalupe Gralnek, Ian Sung, Joseph J. Y. Barkun, Alan Laine, Loren Sekhon, Jasjeet Stadie, Bradly Shung, Dennis L. Section of Digestive Diseases Department of Medicine Yale School of Medicine New Haven United States Department of Mathematics Baruch College The City University of New York New York United States Department of Statistics and Data Science Northwestern University Chicago United States Department of Engineering and Architecture University of Trieste Trieste Italy Department of Statistics and Data Science Yale University New Haven United States Department of Statistics University of California Berkley Berkley United States Department of Medical Surgical and Health Sciences University of Trieste Trieste Italy Rappaport Faculty of Medicine Technion Israel Institute of Technology Haifa Israel Lee Kong Chian School of Medicine Nanyang Technological University Singapore Singapore Division of Gastroenterology McGill University Montreal Canada Department of Biomedical Informatics and Data Science Yale School of Medicine New Haven United States

Large language models generate plausible text responses to medical questions, but inaccurate responses pose significant risks in medical decision-making. Grading LLM outputs to determine the best model or answer is time-consuming and impractical in clinical settings;therefore, we introduce EVAL (Expert-of-Experts Verification and Alignment) to streamline this process and enhance LLM safety for upper gastrointestinal bleeding (UGIB). We evaluated OpenAI’s GPT-3.5/4/4o/o1-preview, Anthropic’s Claude-3-Opus, Meta’s LLaMA-2 (7B/13B/70B), and Mistral AI’s Mixtral (7B) across 27 configurations, including zero-shot baseline, retrieval-augmented generation, and supervised fine-tuning. EVAL uses similarity-based ranking and a reward model trained on human-graded responses for rejection sampling. Among the employed similarity metrics, Fine-Tuned ColBERT achieved the highest alignment with human performance across three separate datasets (ρ = 0.81–0.91). The reward model replicated human grading with 87.9% of cases across temperature settings and significantly improved accuracy through rejection sampling by 8.36% overall. EVAL offers scalable potential to assess accuracy for high-stakes medical decision-making. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mapping Emergency Medicine data to the Observational Medical Outcomes Partnership Common data Model: A Gap Analysis of the American College of Emergency Physicians Clinical Emergency data Registry

引用

JACEP Open 2025年第1期6卷 100016-100016页

作者： Cohen, Inessa Diao, Zihan Goyal, Pawan Gupta, Aarti Hawk, Kathryn Malcom, Bill Malicki, Caitlin Sharma, Dhruv Sweeney, Brian Weiner, Scott G. Venkatesh, Arjun Taylor, R. Andrew Department of Emergency Medicine Yale School of Medicine New Haven CT United States Section for Biomedical Informatics and Data Science Yale University School of Medicine New Haven CT United States Program of Computational Biology and Bioinformatics Yale University New Haven CT United States American College of Emergency Physicians Washington DC United States Department of Emergency Medicine Brigham and Women's Hospital Boston MA United States Center for Outcomes Research and Evaluation (CORE) Section of Cardiovascular Medicine Yale School of Medicine New Haven CT United States

Objectives: This study aims to conduct a gap analysis to determine the feasibility of mapping electronic health record data from the Clinical Emergency data Registry (CEDR) to the Observational Medical Outcomes Partnership Common data Model (OMOP-CDM). Methods: We employed a structured approach using a custom-built comparison matrix. This matrix facilitated the alignment of CEDR data fields with the corresponding elements in the OMOP-CDM schema. Each field was evaluated for compatibility, with categorization into 3 distinct types: direct matches, fields requiring transformation, and fields with no OMOP-CDM equivalent. The mapping process was informed by consultations with the Observational Health data sciences and informatics community forums and was guided by existing documentation and best practices in data harmonization. We performed descriptive analyses, quantifying the extent of direct matches and identifying the specific transformations needed for each CEDR-CDM field to ensure compliance with the OMOP-CDM model. Results: Our analysis indicates a high degree of compatibility between CEDR and OMOP, with over 90% (244/269) of CEDR fields being successfully mapped. Specifically, 173 fields had direct matches, whereas 71 required transformations. Challenges identified include addressing fields unique to CEDR with no OMOP-CDM equivalent and managing the transformations required for proper alignment. Conclusion: The OMOP-CDM presents a promising framework for standardizing emergency medicine data, thereby enhancing future query automation, analytics, and cross-institutional collaboration. Despite the potential challenges in capturing unique CEDR fields and addressing necessary transformations, most emergency department data can be standardized within the OMOP-CDM, fostering broader insights and applications in research and public health. © 2024 The Author(s)

关键词： databases electronic health records emergency service informatics opioid/adverse effects quality of health care registries

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：