检索结果-内蒙古大学图书馆

A decomposition of Fisher’s information to inform sample size for developing fair and precise clinical prediction models - Part 2: time-to-event outcomes

arXiv

引用

arXiv 2025年

作者： Riley, Richard D. Collins, Gary S. Archer, Lucinda While, Rebecca Legha, Amardeep Kirton, Laura Dhiman, Paula Sadatsafavi, Mohsen Adderley, Nicola J. Alderman, Joseph MarGn, Glen P. Ensor, Joie Department of Applied Health Sciences School of Health Sciences College of Medicine and Health University of Birmingham Birmingham United Kingdom Birmingham Biomedical Research Centre Birmingham United Kingdom Centre for Sta?s?cs in Medicine Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences University of Oxford OxfordOX3 7LD United Kingdom Cancer Research UK Clinical Trials Unit Ins?tute of Cancer and Genomic Sciences College of Medical and Dental Sciences University of Birmingham Birmingham United Kingdom Respiratory Evalua?on Sciences Program Faculty of Pharmaceu?cal Sciences The University of Bri?sh Columbia Vancouver Canada Ins?tute of Inflamma?on and Ageing College of Medicine and Health University of Birmingham Birmingham United Kingdom Queen Elizabeth Hospital University Hospitals Birmingham NHS Founda?on Trust Birmingham United Kingdom Division of Informatics Imaging and Data Science Faculty of Biology Medicine and Health University of Manchester Manchester Academic Health Science Centre Manchester United Kingdom

Background When developing a clinical predicGon model using Gme-to-event data (i.e., with censoring and different lengths of follow-up), previous research focuses on the sample size needed to minimise overfifng and precisely esGmaGng the overall risk. However, instability of individual-level risk esGmates may sGll be large. Methods We propose using a decomposiGon of Fisher’s informaGon matrix to help examine and calculate the sample size required for developing a model that aims for precise and fair risk esGmates. We propose a six-step process which can be used before data collecGon or when an exisGng dataset is available. Steps (1) to (5) require researchers to specify the overall risk in the target populaGon at a key Gme-point of interest;an assumed pragmaGc ‘core model’ in the form of an exponenGal regression model;the (anGcipated) joint distribuGon of core predictors included in that model;and the distribuGon of any censoring. The ‘core model’ can be specified directly or based on a specified C-index and relaGve effects of (standardised) predictors. The joint distribuGon of predictors may be available directly in an exisGng dataset, in a pilot study, or in a syntheGc dataset provided by other researchers. Results We derive closed-form soluGons that decompose the variance of an individual’s esGmated event rate into Fisher’s unit informaGon matrix, predictor values and total sample size;this allows researchers to calculate and examine uncertainty distribuGons around individual risk esGmates and misclassificaGon probabiliGes for specified sample sizes. We provide an illustraGve example in breast cancer and emphasise the importance of clinical context, including any risk thresholds for decision making, and examine fairness concerns for pre- and post-menopausal women. Lastly, in two empirical evaluaGons, we provide reassurance that uncertainty interval widths based on our exponenGal approach are close to using more flexible parametric models. Conclusions Our approach

关键词： Fisher information matrix

来源：评论

学校读者我要写书评

暂无评论

Making shiny objects illuminating: the promise and challenges of large language models in U.S. health systems

npj Health Systems

引用

npj Health Systems 2025年第1期2卷 1-3页

作者： Rui Zhang Genevieve B. Melton James Zou Ashley N. Beecy Yiye Zhang Jiang Bian Cui Tao Department of Surgery and Center for Learning Health System Sciences University of Minnesota Minneapolis MN USA Institute for Health Informatics University of Minnesota Minneapolis MN USA Department of Biomedical Data Science Stanford University Stanford CA USA Department of Medicine Division of Cardiology Weill Cornell Medicine New York NY USA Information Technology NewYork-Presbyterian Hospital New York NY USA Department of Population Health Sciences Weill Cornell Medicine New York New York NY USA Biostatistics and Health Data Science School of Medicine Indiana University Indianapolis IN USA Regenstrief Institute Indianapolis IN USA Department of Artificial Intelligence and Informatics Mayo Clinic Jacksonville FL USA

来源：评论

学校读者我要写书评

暂无评论

Mitigating medical dataset bias by learning adaptive agreement from a biased council

引用

Medical Image Analysis 2025年

作者： Luyang Luo Xin Huang Minghao Wang Zhuoyue Wan Wanteng Ma Hao Chen Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Biomedical Informatics Harvard University Cambridge USA Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Computing The Hong Kong Polytechnic University Hong Kong China Department of Statistics and Data Science University of Pennsylvania Philadelphia USA Division of Life Science Hong Kong University of Science and Technology Hong Kong China HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Futian Shenzhen China State Key Laboratory of Molecular Neuroscience The Hong Kong University of Science and Technology Hong Kong China

dataset bias in images is an important yet less explored topic in medical images. Deep learning could be prone to learning spurious correlation raised by dataset bias, resulting in inaccurate, unreliable, and unfair models, which impedes its adoption in real-world clinical applications. Despite its significance, there is a dearth of research in the medical image classification domain to address dataset bias. Furthermore, the bias labels are often agnostic, as identifying biases can be laborious and depend on post-hoc interpretation. This paper proposes learning Adaptive Agreement from a Biased Council (Ada-ABC), a debiasing framework that does not rely on explicit bias labels to tackle dataset bias in medical images. Ada-ABC develops a biased council consisting of multiple classifiers optimized with generalized cross entropy loss to learn the dataset bias. A debiasing model is then simultaneously trained under the guidance of the biased council. Specifically, the debiasing model is required to learn adaptive agreement with the biased council by agreeing on the correctly predicted samples and disagreeing on the wrongly predicted samples by the biased council. In this way, the debiasing model could learn the target attribute on the samples without spurious correlations while also avoiding ignoring the rich information in samples with spurious correlations. We theoretically demonstrated that the debiasing model could learn the target features when the biased model successfully captures dataset bias. Moreover, we constructed the first medical debiasing benchmark focusing on addressing spurious correlation from four datasets containing seven different bias scenarios. Our extensive experiments practically showed that our proposed Ada-ABC outperformed competitive approaches, verifying its effectiveness in mitigating dataset bias for medical image classification. The codes and organized benchmark datasets can be accessed via https://***/LLYXC/Ada-ABC .

关键词：

来源：评论

学校读者我要写书评

暂无评论

ChatGPT versus Google Gemini: a comparison to evaluate patient education guide created on common neurological disorders

引用

Discover Artificial Intelligence 2024年第1期4卷 79页

作者： Phillips, Vidith Kiryakoza, Fadi Arefin, Shamsul Choudhary, Nishtha Garifullin, Renat Division of Biomedical Informatics & amp Data Science Institute School of Medicine John Hopkins University BaltimoreMD United States Ibn Sena Teaching Hospital Mosul Iraq NHS Trust Nottingham Univesity Hospitals Nottingham United Kingdom Jhalawar Medical College Rajasthan Jhalawar India University of New Mexico AlbuquerqueNM United States

Introduction: This study assesses the effectiveness of AI tools, ChatGPT and Google Gemini, in educating the public about neurological conditions such as Bell’s palsy, Tetanus, and Headaches, and assess chatbot-generated patient guides based on readability and ease of understanding. Methodology: In March 2024, the authors conducted a cross-sectional study to develop patient education brochures for Bell’s palsy, Tetanus vaccination, and Persistent Headache, leveraging AI models ChatGPT and Google Gemini. The brochures’ quality was assessed through readability, similarity, and a modified DISCERN score for reliability. Statistical analysis, performed in R software, compared responses from both AI models using unpaired T-tests. The correlation between ease score and reliability was explored using Pearson’s Coefficient of Correlation. Results: The study revealed no significant variances in word count, sentence count, or average words per sentence between the two AI tools. However, materials generated by ChatGPT exhibited significantly higher ease scores, highlighting its proficiency in creating more understandable content (p © The Author(s) 2024.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Special Section Guest Editorial: Advances in Breast Imaging

引用

Journal of Medical Imaging 2019年第3期6卷 031401-031401页

作者： Krupinski, Elizabeth A. Astley, Sue Marti, Robert Tornai, Martin Zwiggelaar, Reyer Emory University Department of Radiology and Imaging Sciences AtlantaGA United States University of Manchester Division of Informatics Imaging and Data Science Manchester United Kingdom University of Girona Department of Architecture and Computer Technology Girona Spain Duke University Departments of Radiology and Biomedical Engineering DurhamNC United States Aberystwyth University Department of Computer Science Aberystwyth United Kingdom

This guest editorial introduces the special section on Advances in Breast Imaging.

关键词： Digital breast tomosynthesis Breast imaging Breast cancer Breast Cancer Digital mammography Computer simulations Mammography Optical filters Radiology

来源：评论

学校读者我要写书评

暂无评论

Environment scan of generative AI infrastructure for clinical and translational science

Npj health systems

引用

Npj health systems 2025年第1期2卷 4页

作者： Betina Idnay Zihan Xu William G Adams Mohammad Adibuzzaman Nicholas R Anderson Neil Bahroos Douglas S Bell Cody Bumgardner Thomas Campion Mario Castro James J Cimino I Glenn Cohen David Dorr Peter L Elkin Jungwei W Fan Todd Ferris David J Foran David Hanauer Mike Hogarth Kun Huang Jayashree Kalpathy-Cramer Manoj Kandpal Niranjan S Karnik Avnish Katoch Albert M Lai Christophe G Lambert Lang Li Christopher Lindsell Jinze Liu Zhiyong Lu Yuan Luo Peter McGarvey Eneida A Mendonca Parsa Mirhaji Shawn Murphy John D Osborne Ioannis C Paschalidis Paul A Harris Fred Prior Nicholas J Shaheen Nawar Shara Ida Sim Umberto Tachinardi Lemuel R Waitman Rosalind J Wright Adrian H Zai Kai Zheng Sandra Soo-Jin Lee Bradley A Malin Karthik Natarajan W Nicholson Price Ii Rui Zhang Yiye Zhang Hua Xu Jiang Bian Chunhua Weng Yifan Peng Department of Biomedical Informatics Columbia University Irving Medical Center New York NY USA. Department of Population Health Sciences Weill Cornell Medicine New York NY USA. Department of Pediatrics Boston Medical Center Boston MA USA Chobanian & Avedisian School of Medicine Boston University Boston MA USA. Oregon Clinical and Translational Research Institute Oregon Health and Science University Portland OR USA. Department of Public Health Sciences University of California Davis Davis CA USA. Keck School of Medicine University of Southern California Los Angeles CA USA. Department of Medicine David Geffen School of Medicine University of California Los Angeles Los Angeles CA USA. Department of Pathology and Laboratory Medicine University of Kentucky College of Medicine Lexington KY USA. Clinical and Translational Science Center Weill Cornell Medicine New York NY USA. Division of Pulmonary Critical Care and Sleep Medicine University of Kansas School of Medicine Kansas City KS USA. Department of Biomedical Informatics and Data Science Heersink School of Medicine University of Alabama Birmingham AL USA. Harvard Law School Petrie-Flom Center for Health Law Policy Biotechnology and Bioethics Harvard University Cambridge MA USA. Department of Biomedical Informatics University at Buffalo Buffalo NY USA. Center for Clinical and Translational Science Mayo Clinic Rochester MN USA. Technology and Digital Solutions Stanford Medicine Stanford University Stanford CA USA. Center for Biomedical Informatics Rutgers Cancer Institute New Brunswick NJ USA. Department of Learning Health Sciences University of Michigan Medical School Ann Arbor MI USA. Altman Clinical and Translational Research Institute (ACTRI) University of California San Diego La Jolla CA USA. Department of Biostatistics and Health Data Science School of Medicine Indiana University Indianapolis IN USA. Department of Ophthalmology CCTSI University of Colorado Aurora CO USA. Center for Clinic

This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the CTSA Program led by the National Center for Advancing Translational sciences (NCATS) of the National Institutes of Health (NIH) at the United States. Key findings indicate a diverse range of institutional strategies, with most organizations in the experimental phase of GenAI deployment. The results underscore the need for a more coordinated approach to GenAI governance, emphasizing collaboration among senior leaders, clinicians, information technology staff, and researchers. Our analysis reveals that 53% of institutions identified data security as a primary concern, followed by lack of clinician trust (50%) and AI bias (44%), which must be addressed to ensure the ethical and effective implementation of GenAI technologies.

关键词： Health services Public health

来源：评论

学校读者我要写书评

暂无评论

Influence of electric field orientation on the effect of ocular current stimulation using full field electroretinogram

Influence of electric field orientation on the effect of ocu...

引用

作者： Blum, Maren-Christina Leydolph, Lilly Klee, Sascha Institute of Biomedical Engineering and Informatics Faculty of Computer Sciences and Automation Technische Universität Ilmenau Ilmenau Germany Department of General Health Studies Division Biostatistics and Data Science Karl Landsteiner University of Health Sciences Krems an der Donau Austria

Ocular current stimulation (CS) exhibits potential for the treatment of neurodegenerative ocular diseases. For a full field electroretinogram (ffERG) we found no CS effect on the characteristic waves (a-wave, b'-wave, and b-wave). To investigate whether the orientation of the generated electric field has an influence on the CS effect, this study repeated the previous ffERG study with changing one CS electrode position and compared the results of both studies. In the first study 15 (8 m, 27.5 ± 4.5 years) and in the second study 17 (7 m, 22.0 ± 1.9 years) healthy volunteers were stimulated with an anodal, cathodal, and sham direct CS of 800 μA for 5 min in three sessions (randomized, different days). For both studies, a cut-sized ring rubber electrode was placed around the eye. A square rubber electrode was placed for the first study at the ipsilateral temple and for the second study at the visual cortex. Before (ERG 1) and during (ERG 2) the CS, the ffERG was measured. For both studies, the difference between the ERG 1 and ERG 2 measurement (CS effect) for the three characteristic waves was analyzed and compared between the studies. For statistical analysis, the Mann-Whitney U test with Bonferroni correction was applied (α = 0.05). The comparison of the data distribution showed only slight differences between the studies. The Mann-Whitney U test found no significant difference of the CS effect between the studies for all amplitudes and CS groups (p ≥ 0.0055). In the mean, the latency differences were smaller than the time resolution, therefore no statements for latency effects were possible. It can be concluded that the retinal cells generating the ffERG are not affected by ocular CS in either electrode montages tested. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Rubber

来源：评论

学校读者我要写书评

暂无评论

Technical light-field setup for 3D imaging of the human nerve head validated with an eye model

Technical light-field setup for 3D imaging of the human nerv...

引用

作者： Schramm, Stefan Dietzel, Alexander Blum, Maren-Christina Link, Dietmar Klee, Sascha Institute of Biomedical Engineering and Informatics Faculty of Computer Sciences and Automation Technische Universität Ilmenau Ilmenau Germany Department of General Health Studies Division Biostatistics and Data Science Karl Landsteiner University of Health Sciences Krems an der Donau Austria

With the new technology of 3D light field (LF) imaging, fundus photography can be expanded to provide depth information. This increases the diagnostic possibilities and additionally improves image quality by digitally refocusing. To provide depth information in the human optic nerve head such as in glaucoma diagnostics, a mydriatic fundus camera was upgraded with an LF imager. The aim of the study presented here was the validation of the technical setup and resulting depth estimations with an appropriate eye model. The technical setup consisted of a mydriatic fundus camera (FF450, Carl Zeiss Meditec AG, Jena, Germany) and an LF imager (R12, Raytrix GmbH, Kiel, Germany). The field of view was set to 30°. The eye model (24.65 mm total length) consisted of a two-lens optical system and interchangeable fundus models with papilla excavations from 0.2 to 1 mm in steps of 0.2 mm. They were coated with red acrylic lacquer and vessels were drawn with a thin brush. 15 images were taken for each papilla depth illuminated with green light (wavelength 520 nm ± 20 nm). Papilla depth was measured from the papilla ground to the surrounding flat region. All 15 measurements for each papilla depth were averaged and compared to the printed depth. It was possible to perform 3D fundus imaging in an eye model by means of a novel LF-based optical setup. All LF images could be digitally refocused subsequently. Depth estimation in the eye model was successfully performed over a 30° field of view. The measured virtual depth and the printed model papilla depth is linear correlated. The presented LF setup allowed high-quality 3D one-shot imaging and depth estimation of the optic nerve head in an eye model. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Optical systems

来源：评论

学校读者我要写书评

暂无评论

Factors Associated With Influenza Vaccination in a National Veteran Cohort

引用

AJPM Focus 2025年第1期4卷 100290-100290页

作者： Chen, Alissa S. Farmer, Melissa M. Han, Ling Runels, Tessa Bade, Brett Crothers, Kristina Bastian, Lori A. Bazan, Isabel S. Bean-Mayberry, Bevanne A. Brandt, Cynthia A. Akgün, Kathleen M. Section of General Medicine Department of Medicine Yale University School of Medicine New Haven Connecticut United States Center for Study of Healthcare Innovation Implementation and Policy (CSHIIP) VA Greater Los Angeles Healthcare System Los Angeles California United States Pain Research Informatics Multimorbidities and Education (PRIME) Center VA Connecticut Healthcare System West Haven CT United States Donald and Barbara Zucker School of Medicine at Hofstra/Northwell Hempstead New York United States VA Puget Sound Seattle WA United States Division of Pulmonary Critical Care and Sleep Medicine University of Washington Seattle WA United States Pulmonary Critical Care & Sleep Medicine Yale University School of Medicine New Haven Connecticut United States Department of Medicine David Geffen School of Medicine University of California Los Angeles Los Angeles California United States Department of Emergency Medicine Yale University School of Medicine New Haven Connecticut United States Section of Biomedical Informatics and Data Science Yale University School of Medicine New Haven Connecticut United States

Introduction: Only 53% of American adults receive influenza vaccination, and disparities in vaccination exist among particular racial and ethnic groups. This study determines how race, ethnicity, sex, and rurality are associated with influenza vaccination adherence in a national Veteran Health Affairs Administration cohort. Methods: The authors examined differences in documented influenza vaccinations for the 2019–2020 influenza season among Veteran Health Affairs Administration patients in a retrospective cohort study using Veteran Health Affairs Administration administrative electronic health record data. The author used logistic regression to model receipt of influenza vaccination in association with race, ethnicity, sex, and rurality while controlling for clinical diagnoses, demographics, and ambulatory care utilization. The authors also stratified the models by sex and rurality. Results: Among 5,943,918 veterans, 48.6% received influenza vaccination. Unadjusted comparisons showed that those who were vaccinated were more likely to be White, to be of male sex, and to be older. Similar proportions of unvaccinated and unvaccinated veterans were from rural settings. In adjusted models, Black race was most strongly associated with decreased vaccination (AOR=0.69;95% CI=0.69, 0.70), and American Indian/Alaskan Native race also had reduced odds of vaccination (AOR=0.94;95% CI=0.92, 0.95) compared with White race. Female veterans had increased odds of vaccination (AOR=1.20;95% CI=1.19, 1.20) compared with men. Rurality (AOR=0.97;95% CI=0.96, 0.97) was associated with a small decreased odds of vaccination compared with urban. In stratified models, Black veterans were less likely to receive influenza vaccination regardless of sex and rurality than White veterans. American Indian/Alaska Native female veterans had equal odds of vaccination as White female veterans, whereas American Indian/Alaska Native male veterans had reduced odds of vaccination compared with White male v

关键词： Influenza vaccination vaccination coverage vaccine hesitancy veterans

来源：评论

学校读者我要写书评

暂无评论

Echocardiographic Features of Right Ventricular Reverse Remodeling in Adults with Repaired Tetralogy of Fallot after Pulmonary Valve Replacement and Impact of Age at Time of Intervention

引用

Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography 2025年

作者： Rebecca L Moore Jan Leonard Alexis Z Tomlinson Stephanie Fuller Yan Wang Laura Mercer-Rosa Yuli Y Kim Division of Cardiology Department of Pediatrics Children's Hospital of Philadelphia Philadelphia PA USA Division of Cardiology Department of Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA. Electronic address: Rebecca.moore2@pennmedicine.upenn.edu. Data Science and Biostatistics Unit Department of Biomedical and Health Informatics Children's Hospital of Philadelphia Philadelphia PA USA. Division of Cardiothoracic Surgery Department of Surgery Children's Hospital of Philadelphia Philadelphia PA USA. Division of Cardiology Department of Pediatrics Children's Hospital of Philadelphia Philadelphia PA USA. Division of Cardiology Department of Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA.

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：