检索结果-内蒙古大学图书馆

arXiv 2024年

作者： van Calster, Ben Collins, Gary S. Vickers, Andrew J. Wynants, Laure Kerr, Kathleen F. Barreñada, Lasai Varoquaux, Gael Singh, Karandeep Moons, Karel G.M. Hernandez-Boussard, Tina Timmerman, Dirk McLernon, David J. van Smeden, Maarten Steyerberg, Ewout W. Dept Development and Regeneration KU Leuven Leuven Belgium KU Leuven Leuven Belgium Dept Biomedical Data Sciences Leiden University Medical Center Leiden Netherlands Centre for Statistics in Medicine Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences University of Oxford United Kingdom Department of Epidemiology and Biostatistics Memorial Sloan Kettering Cancer Center New YorkNY United States Department of Epidemiology CAPHRI Care and Public Health Research Institute Maastricht University Maastricht Netherlands Department of Biostatistics University of Washington School of Public Health SeattleWA United States Parietal project team INRIA Saclay-Île de France Palaiseau France Division of Biomedical Informatics Department of Medicine University of California San DiegoCA United States Julius Centre for Health Sciences and Primary Care University Medical Centre Utrecht Utrecht University Utrecht Netherlands Stanford University StanfordCA United States Department of Biomedical Data Science Stanford University StanfordCA United States Department of Obstetrics and Gynecology University Hospitals Leuven Leuven Belgium Institute of Applied Health Sciences University of Aberdeen Aberdeen United Kingdom

A myriad of measures to illustrate performance of predictive artificial intelligence (AI) models have been proposed in the literature. Selecting appropriate performance measures is essential for predictive AI models that are developed to be used in medical practice, because poorly performing models may harm patients and lead to increased costs. We aim to assess the merits of classic and contemporary performance measures when validating predictive AI models for use in medical practice. We focus on models with a binary outcome. We discuss 32 performance measures covering five performance domains (discrimination, calibration, overall, classification, and clinical utility) along with accompanying graphical assessments. The first four domains cover statistical performance, the fifth domain covers decision-analytic performance. We explain why two key characteristics are important when selecting which performance measures to assess: (1) whether the measure’s expected value is optimized when it is calculated using the correct probabilities (i.e., a "proper" measure), and (2) whether they reflect either purely statistical performance or decision-analytic performance by properly considering misclassification costs. Seventeen measures exhibit both characteristics, fourteen measures exhibited one characteristic, and one measure possessed neither characteristic (the F1 measure). All classification measures (such as classification accuracy and F1) are improper for clinically relevant decision thresholds other than 0.5 or the prevalence. We recommend the following measures and plots as essential to report: AUROC, calibration plot, a clinical utility measure such as net benefit with decision curve analysis, and a plot with probability distributions per outcome category. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adherence to Hydroxychloroquine Dosing Guidelines at the University of California

引用

Ophthalmology Retina 2025年

作者： Moussa, Kareem Virk, Jaipreet S. Paciotti, Brian Durbin-Johnson, Blythe P. Shantha, Jessica G. Tsui, Edmund Sun, Catherine Q. Baxter, Sally L. Gore, Charlotte Yiu, Glenn Y. Department of Ophthalmology and Vision Science University of California Davis Sacramento California United States University of California Davis School of Medicine Sacramento California United States Information Technology University of California Davis Health System Sacramento California United States Department of Public Health Sciences University of California Davis Health System Sacramento California United States Department of Ophthalmology University of California San Francisco San Francisco California United States F.I. Proctor Foundation University of California San Francisco San Francisco California United States UCLA Stein Eye Institute University of California Los Angeles Los Angeles California United States Division of Ophthalmology Informatics and Data Science Viterbi Family Department of Ophthalmology and Shiley Eye Institute University of California La Jolla San Diego California United States Division of Biomedical Informatics Department of Medicine University of California La Jolla San Diego California United States Department of Ophthalmology University of California Irvine Irvine California United States

The American Academy of Ophthalmology has published several guidelines on dosing and screening recommendations for hydroxychloroquine. In this cross-sectional study we report 36% of patients prescribed hydroxychloroqu... 详细信息

关键词： Hydroxychloroquine Pharmacology Public health Retinal toxicity

来源：评论

学校读者我要写书评

暂无评论

Language Enhanced Model for Eye (LEME): An Open-Source Ophthalmology-Specific Large Language Model

arXiv

引用

arXiv 2024年

作者： Gilson, Aidan Ai, Xuguang Xie, Qianqian Srinivasan, Sahana Pushpanathan, Krithi Singer, Maxwell B. Huang, Jimin Kim, Hyunjae Long, Erping Wan, Peixing Del Priore, Luciano V. Ohno-Machado, Lucila Xu, Hua Liu, Dianbo Adelman, Ron A. Tham, Yih-Chung Chen, Qingyu Department of Ophthalmology Massachusetts Eye and Ear Harvard Medical School BostonMA United States Department of Biomedical Informatics and Data Science Yale School of Medicine Yale University New Haven United States Singapore Eye Research Institute Singapore National Eye Centre Singapore Centre for Innovation and Precision Eye Health Department of Ophthalmology Yong Loo Lin School of Medicine National University of Singapore Singapore Department of Ophthalmology and Visual Science Yale School of Medicine Yale University New Haven United States Department of Computer Science Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of Division of Cancer Epidemiology and Genetics National Cancer Institute National Institutes of Health BethesdaMD United States Center for Cancer Research National Cancer Institute National Institutes of Health BethesdaMD United States Ophthalmology and Visual Science Academic Clinical Program Duke-NUS Medical School Singapore Singapore

Large Language Models (LLMs) are poised to revolutionize healthcare. Ophthalmology-specific LLMs remain scarce and underexplored. We introduced an open-source, specialized LLM for ophthalmology, termed Language Enhanced Model for Eye (LEME). LEME was initially pre-trained on the Llama2 70B framework and further fine-tuned with a corpus of ~127,000 non-copyrighted training instances curated from ophthalmology-specific case reports, abstracts, and open-source study materials. We benchmarked LEME against eight other LLMs, namely, GPT-3.5, GPT-4, three Llama2 models (7B, 13B, 70B), PMC-LLAMA 13B, Meditron 70B, and EYE-Llama (another ophthalmology-specific LLM). Evaluations included four internal validation tasks: abstract completion, fill-in-the-blank, multiple-choice questions (MCQ), and short-answer QA. External validation tasks encompassed long-form QA, MCQ, patient EHR summarization, and clinical QA. Evaluation metrics included Rouge-L scores, accuracy, and expert evaluation of correctness, completeness, and readability. In internal validations, LEME consistently outperformed its counterparts, achieving Rouge-L scores of 0.20 ± 0.03 in abstract completion (all p © 2024, CC BY.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

A decomposi+on of Fisher’s informa+on to inform sample size for developing fair and precise clinical predic+on models – part 1: binary outcomes

arXiv

引用

arXiv 2024年

作者： Riley, Richard D. Collins, Gary S. Whittle, Rebecca Archer, Lucinda Snell, Kym I.E. Dhiman, Paula Kirton, Laura Legha, Amardeep Liu, Xiaoxuan Denniston, Alastair Harrell, Frank E. Wynants, Laure MarKn, Glen P. Ensor, Joie Institute of Applied Health Research College of Medical and Dental Sciences University of Birmingham Birmingham United Kingdom Birmingham Biomedical Research Centre Birmingham United Kingdom Centre for Statistics in Medicine Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences University of Oxford OxfordOX3 7LD United Kingdom Cancer Research UK Clinical Trials Unit Institute of Cancer and Genomic Sciences College of Medical and Dental Sciences University of Birmingham Birmingham United Kingdom Department of Biostatistics Vanderbilt University School of Medicine NashvilleTN United States Maastricht University Maastricht Netherlands Department of Development and Regeneration KU Leuven Leuven Belgium 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 prediction model, the sample size of the development dataset is important. Smaller sample increase concerns of overfibng, instability, poor predictive performance and a lack of fairness. For models estimating the risk of a binary outcome, previous research has outlined minimum sample size calculations to minimise overfibng and precisely estimate the overall risk. However, even when meeting these criteria, the uncertainty (instability) in individual-level risk estimates may be considerable. Methods We propose a decomposition of Fisher’s information matrix to help examine and calculate the sample size required for developing a model with acceptably precise risk estimates to inform decisions and improve fairness. We outline a five-step process for use before data collection or when an existing dataset is available. It requires researchers to specify the overall risk in the target population, the (anticipated) distribution of key predictors in the model, and an assumed ‘core model’ either specified directly (i.e., a logistic regression equation is provided) or based on a specified C-statistic and relative effects of (standardised) predictors. Results We produce closed-form solutions that decompose the variance of an individual’s risk estimate into the Fisher’s unit information matrix, predictor values and the total sample size;this allows researchers to quickly calculate and examine individual-level uncertainty interval widths for specified sample sizes, alongside prediction and classification instability plots. The information can be presented to key stakeholders (e.g., health professionals, patients, grant funders) to determine a target sample size or whether an existing dataset is sufficient. Our proposal is implemented in our new soSware module pmstabilityss. We provide two real examples and emphasise the importance of clinical context, including any risk thresholds for decision making, and fairness checks. Conclusions Our appro

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Translational Personas and Hospital Library Services

引用

Journal of Hospital Librarianship 2020年第3期20卷 204-216页

作者： Gonzales, Sara O’Keefe, Lisa Gutzman, Karen Viger, Guillaume Wescott, Annie B. Farrow, Bailey Heath, Allison P. Kim, Meen Chul Taylor, Deanne Champieux, Robin Yen, Po-Yin L. Holmes, Kristi Galter Health Sciences Library and Learning Center Northwestern University Feinberg School of Medicine Chicago IL United States Center for Data-Driven Discovery in Biomedicine The Children’s Hospital of Philadelphia Philadelphia PA United States Department of Pediatrics Perelman School of Medicine at the University of Pennsylvania Philadelphia PA United States Department of Biomedical and Health Informatics The Children's Hospital of Philadelphia Philadelphia PA United States The Oregon Health Science University Library Oregon Health Science University Portland OR United States Institute for Informatics Department of Medicine Division of General Medical Sciences Washington University School of Medicine St. Louis MO United States Goldfarb School of Nursing Barnes-Jewish College BJC HealthCare St. Louis MO United States Department of Preventive Medicine Division of Health and Biomedical Informatics Northwestern University Feinberg School of Medicine Chicago IL United States

Academic health centers, CTSA hubs, and hospital libraries experience similar funding challenges and charges to do more with less. In recent years academic health center and hospital librarians have risen to these challenges by examining their service models, and beyond that, examining their patron base and users’ needs. To meet the needs of employees, patients, and those who assist patients, hospital librarians can employ the CTS Personas, a project of the Clinical and Translational science Awards (CTSA) Program National Center for data to Health. The Persona profiles, which outline the motivations, goals, pain points, wants, and needs of twelve employees and two patients in translational science, provide vital information and insights that can inform everything from designing software tools and educational services, to advertising these services, to designing impactful and collaborative library spaces. © 2020 The Author(s). Published with license by Taylor & Francis Group, LLC.

关键词： Academic health centers hospital libraries organizational structure service models translational science

来源：评论

学校读者我要写书评

暂无评论

Determination of the tonographic effect in the human eye using a pneumatic pressure modulator

引用

ACTA OPHTHALMOLOGICA 2022年第S267期100卷

作者： Link, Dietmar Krauss, Benedikt Stodtmeister, Richard Nagel, Edgar Vilser, Walthard Klee, Sascha Institute for Biomedical Engineering and Informatics Technische Universität Ilmenau Ilmenau Germany Department of Optoelectrophysiological Engineering Technische Universität Ilmenau Ilmenau Germany Imedos Systems GmbH Jena Germany University Hospital Carl Gustav Carus Technische Universität Dresden Dresden Germany Augenspezialisten Saar Augenarzt Völklingen Germany Ophthalmic Private Practice Rudolstadt Germany Department of General Health Studies Division Biostatistics and Data Science Karl Landsteiner University of Health Sciences Krems Austria

Purpose The tonographic effect has been observed in several studies in occulopression, repeated tonometry or ophthalmodynamometry. It describes an intraocular pressure (IOP) decrease caused by an artifical IOP increase. In healthy eyes, an IOP drop of 2–3 mmHg/min was reported. However, there are studies that show a reduced decrease of the IOP drop for instance in glaucoma patients. In this work, we present a proof of principle to determine the tonographic effect in healthy eyes by utilizing a novel pneumatic pressure modulator. Methods The study was conducted on 8 healthy subjects (4 m, 4 f, 1 eye each, mean age 27.4 ± 7.1 yr). All subjects passed an ophthalmic examination procedure, including visual acuity determination, tonometry, objective refraction, slit lamp examination. Exclusion criteria were myopia < -8 dpt, anamnestic surgeries, corneal scars, eye diseases, ocular hypertension, and ongoing ocular local therapy. No anaesthetics were used. A pressure modulator (IOPstim, Imedos Systems GmbH, Jena, Germany) was used to increase the IOP to initially pathologic IOP values of about 35 mmHg (36.6 ± 2.5 mmHg). The applied pressure was kept constant for 2 minutes. The IOP was measured 4 times (at 0s, 40s, 80s, and 120s) using a rebound tonometer (Icare PRO, Icare Finland Oy, Helsinki, Finland). Linear regression was performed to calculate the average IOP decrease within the 2-minutes interval. Results For all 8 subjects, a typical decrease of the IOP was observed during a 2 min constant pressure stimulation. The mean decrease of the pressure profiles was 2.77 mmHg/min ( R 2 = 0.94). Conclusions We successfully applied a pneumatic pressure modulator to determine the tonographic effect in the human eye. For 2 min we measured the mean decrease of the IOP drop with similar values known by the literature. Application of the pneumatic pressure modulator allows the investigation of pathological reduced IOP drops that differ from normal values as shown in this study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal learning with graphs

arXiv

引用

arXiv 2022年

作者： Ektefaie, Yasha Dasoulas, George Noori, Ayush Farhat, Maha Zitnik, Marinka Bioinformatics and Integrative Genomics Program Harvard Medical School BostonMA02115 United States Department of Biomedical Informatics Harvard University BostonMA02115 United States Harvard College CambridgeMA02138 United States Broad Institute of MIT and Harvard CambridgeMA02142 United States Harvard Data Science Initiative CambridgeMA02138 United States Division of Pulmonary and Critical Care Department of Medicine Massachusetts General Hospital BostonMA United States

Artificial intelligence for graphs has achieved remarkable success in modeling complex systems, ranging from dynamic networks in biology to interacting particle systems in physics. However, the increasingly heterogeneous graph datasets call for multimodal methods that can combine different inductive biases—the set of assumptions that algorithms use to make predictions for inputs they have not encountered during training. Learning on multimodal datasets presents fundamental challenges because the inductive biases can vary by data modality and graphs might not be explicitly given in the input. To address these challenges, multimodal graph AI methods combine different modalities while leveraging cross-modal dependencies using graphs. Diverse datasets are combined using graphs and fed into sophisticated multimodal architectures, specified as image-intensive, knowledge-grounded and language-intensive models. Using this categorization, we introduce a blueprint for multimodal graph learning, use it to study existing methods and provide guidelines to design new models. © 2022, CC BY.

关键词： Blueprints

来源：评论

学校读者我要写书评

暂无评论

Minimum Sample Size for Developing a Multivariable Prediction Model using Multinomial Logistic Regression

arXiv

引用

arXiv 2022年

作者： Pate, Alexander Riley, Richard D. Collins, Gary S. van Smeden, Maarten Van Calster, Ben Ensor, Joie Martin, Glen P. Division of Informatics Imaging and Data Science Faculty of Biology Medicine and Health University of Manchester Manchester Academic Health Science Centre Manchester United Kingdom Centre for Prognosis Research School of Medicine Keele University Staffordshire United Kingdom Centre for Statistics in Medicine Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences University of Oxford Oxford United Kingdom NIHR Oxford Biomedical Research Centre John Radcliffe Hospital Oxford United Kingdom Julius Center for Health Sciences University Medical Center Utrecht Utrecht University Utrecht Netherlands Department of Clinical Epidemiology Leiden University Medical Center Leiden Netherlands Department of Development and Regeneration KU Leuven Leuven Belgium Department of Biomedical Data Sciences Leiden University Medical Centre Netherlands EPI-center KU Leuven Leuven Belgium

Multinomial logistic regression models allow one to predict the risk of a categorical outcome with > 2 categories. When developing such a model, researchers should ensure the number of participants (n) is appropriate relative to the number of events (Ek) and the number of predictor parameters (pk) for each category k. We propose three criteria to determine the minimum n required in light of existing criteria developed for binary outcomes. The first criteria aims to minimise the model overfitting. The second aims to minimise the difference between the observed and adjusted R2 Nagelkerke. The third criterion aims to ensure the overall risk is estimated precisely. For criterion (i), we show the sample size must be based on the anticipated Cox-snell R2 of distinct "one-to-one" logistic regression models corresponding to the sub-models of the multinomial logistic regression, rather than on the overall Cox-snell R2 of the multinomial logistic regression. We tested the performance of the proposed criteria (i) through a simulation study, and found that it resulted in the desired level of overfitting. Criterion (ii) and (iii) are natural extensions from previously proposed criteria for binary outcomes. We illustrate how to implement the sample size criteria through a worked example considering the development of a multinomial risk prediction model for tumour type when presented with an ovarian mass. Code is provided for the simulation and worked example. We will embed our proposed criteria within the pmsampsize R library and Stata modules. © 2022, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Development of a Natural Language Processing Model for Extracting Kidney Biopsy Pathology Diagnoses

Kidney Medicine

引用

Kidney Medicine 2025年

作者： Shane A. Bobart Enshuo Hsu Thomas Potter Luan Truong Amy Waterman Stephen Jones Tariq Shafi Division of Nephrology Hypertension and Transplantation Center for Health Data Science and Analytics McWilliams School of Biomedical Informatics University of Texas Health Science Center at Houston Houston Texas USA Enteprise Development and Integration University of Texas MD Anderson Cancer Center Houston TX USA Department of Pathology J.C. Walter Jr. Transplant Center Houston Methodist Hospital Houston TX USA Division of Nephrology Baylor Scott and White Health Temple TX USA

Rationale & Objective Kidney biopsy reports are in a non-indexed text format, and the diagnosis requires labor-intensive manual abstraction. Natural language processing (NLP) has not been rigorously tested for kidney biopsy diagnosis extraction. Our objective was to develop an accurate model to extract the biopsy diagnosis from free-text reports Study Design Text Classification using NLP Setting & Participants 2,666 patients with 3042 native kidney biopsy reports in PDF format, from June 2016 to December 2023. Predictor Kidney biopsy diagnosis. Outcomes The performance of the NLP algorithm for all and the 20 most common diagnoses by precision, recall, F1 score and area under the receiver operating curve (AUROC). Analytical Approach A domain expert manually abstracted the diagnosis, and a renal pathologist validated a random subset (n=200). Structured query language ( SQL) server and Python processed reports into machine-readable free text. We used PubMed Bidirectional Encoder Representations from Transformers (BERT) to develop our NLP algorithm. We randomly split the reports into training (80%; n=2434) and testing (20%; n=608) sets to train the NLP system. We further divided the testing set into 20% validation and 80% fine-tuning sets. Results The median age was 57 years; with 50% female, 29% Black, and 23% Hispanic. The 5 most frequent glomerular diagnoses were diabetic kidney disease (23.7%), FSGS (15.5%), lupus nephritis (9.7%), IgA nephropathy (8.9) and membranous nephropathy (7.2%). The kappa for interrater reliability was 0.76. PubMed BERT fine-tuned with a training set showed the average AUROC for NLP performance in the testing set of 0.95 across all diagnoses with an F1 of 0.57. For the 20 most common diagnoses, the AUROC was 0.97 with an F1 of 0.72. Limitations Single center, sample size, utility limited to research purposes. Conclusions We demonstrate an accurate and scalable NLP system to extract the primary diagnosis from free text kidney biopsy reports,

关键词： Natural Language Processing Kidney Biopsy Machine Learning Glomerulonephritis Bidirectional Encoder Representations from Transformers

来源：评论

学校读者我要写书评

暂无评论

GPA-tree: Statistical approach for functional-annotation-tree-guided prioritization of GWAS results

arXiv

引用

arXiv 2021年

作者： Khatiwada, Aastha Wolf, Bethany J. Yilmaz, Ayse Selen Ramos, Paula S. Pietrzak, Maciej Lawson, Andrew Hunt, Kelly J. Kim, Hang J. Chung, Dongjun Department of Public Health Sciences Medical University of South Carolina CharlestonSC United States Department of Biomedical Informatics The Ohio State University ColumbusOH United States Department of Medicine Medical University of South Carolina CharlestonSC United States Division of Statistics and Data Science University of Cincinnati CincinnatiOH United States

Motivation: In spite of great success of genome-wide association studies (GWAS), multiple challenges still remain. First, complex traits are often associated with many single nucleotide polymorphisms (SNPs), each with small or moderate effect sizes. Second, our understanding of the functional mechanisms through which genetic variants are associated with complex traits is still limited. functional annotations related to risk-associated SNPs. To address these challenges, we propose GPA-Tree and it simultaneously implements association mapping and identifies key combinations of functional annotations related to risk-associated SNPs by combining a decision tree algorithm with a hierarchical modeling framework. Results: First, we implemented simulation studies to evaluate the proposed GPA-Tree method and compared its performance with existing statistical approaches. The results indicate that GPA-Tree outperforms existing statistical approaches in detecting risk-associated SNPs and identifying the true combinations of functional annotations with high accuracy. Second, we applied GPA-Tree to a systemic lupus erythematosus (SLE) GWAS and functional annotation data including GenoSkyline and GenoSkylinePlus. The results from GPA-Tree highlight the dysregulation of blood immune cells, including but not limited to primary B, memory helper T, regulatory T, neutrophils and CD8+ memory T cells in SLE. These results demonstrate that GPA-Tree can be a powerful tool that improves association mapping while facilitating understanding of the underlying genetic architecture of complex traits and potential mechanisms linking risk-associated SNPs with complex traits. © 2021, CC BY-NC-ND.

关键词： Decision trees

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：