检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Chen, Richard J. Chen, Tiffany Y. Lipkova, Jana Wang, Judy J. Williamson, Drew F.K. Lu, Ming Y. Sahai, Sharifa Mahmood, Faisal Department of Pathology Brigham and Women's Hospital Harvard Medical School 60 Fenwood Road Hale Building for Transformative Medicine BostonMA02445 United States Department of Biomedical Informatics Harvard Medical School BostonMA United States Cancer Program Broad Institute of Harvard MIT CambridgeMA United States Cancer Data Science Program Dana-Farber Cancer Institute BostonMA United States Boston University School of Medicine BostonMA United States CambridgeMA United States Department of Systems Biology Harvard Medical School BostonMA United States Harvard Medical School BostonMA United States Harvard Data Science Initiative Harvard University CambridgeMA United States

In the current development and deployment of many artificial intelligence (AI) systems in healthcare, algorithm fairness is a challenging problem in delivering equitable care. Recent evaluation of AI models stratified across race sub-populations have revealed inequalities in how patients are diagnosed, given treatments, and billed for healthcare costs. In this perspective article, we summarize the intersectional field of fairness in machine learning through the context of current issues in healthcare, outline how algorithmic biases (e.g.-image acquisition, genetic variation, intra-observer labeling variability) arise in current clinical workflows and their resulting healthcare disparities. Lastly, we also review emerging technology for mitigating bias via federated learning, disentanglement, and model explainability, and their role in AI-SaMD development. Copyright © 2021, The Authors. All rights reserved.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised AI for Efficient Analysis of 3D Pathology Samples

arXiv

引用

arXiv 2023年

作者： Song, Andrew H. Williams, Mane Williamson, Drew F.K. Jaume, Guillaume Zhang, Andrew Chen, Bowen Serafin, Robert Liu, Jonathan T.C. Baras, Alex Parwani, Anil V. Mahmood, Faisal Department of Pathology Brigham and Women’s Hospital Harvard Medical School BostonMA United States Department of Pathology Massachusetts General Hospital Harvard Medical School BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Department of Biomedical Informatics Harvard Medical School BostonMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Department of Mechanical Engineering Bioengineering Laboratory Medicine & Pathology University of Washington SeattleWA United States Department of Pathology Johns Hopkins Hospital BaltimoreMD United States Department of Biomedical Engineering Johns Hopkins Hospital BaltimoreMD United States Department of Pathology The Ohio State University ColumbusOH United States

Human tissue consists of complex structures that display a diversity of morphologies, forming a tissue microenvironment that is, by nature, three-dimensional (3D). However, the current standard-of-care involves slicing 3D tissue specimens into two-dimensional (2D) sections and selecting a few for microscopic evaluation1,2, with concomitant risks of sampling bias and misdiagnosis3–6. To this end, there have been intense efforts to capture 3D tissue morphology and transition to 3D pathology, with the development of multiple high-resolution 3D imaging modalities7–18. However, these tools have had little translation to clinical practice as manual evaluation of such large data by pathologists is impractical and there is a lack of computational platforms that can efficiently process the 3D images and provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy12–14 or microcomputed tomography15,16 and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting that there is value in capturing larger extents of spatially heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, M

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Should workers be physically active after work?Associations of leisure-time physical activity with cardiovascular and all-cause mortality across occupational physical activity levels-An individual participant data meta-analysis

引用

Journal of Sport and Health science 2025年第1期14卷 49-60页

作者： Bart Cillekens Pieter Coenen Maaike A.Huysmans Andreas Holtermann Richard P.Troiano Paul Jarle Mork Steinar Krokstad Els Clays Dirk De Bacquer Mette Aadahl Line Lund Kårhus Anette Sjøl Lars Bo Andersen Jussi Kauhanen Ari Voutilainen Richard Pulsford Emmanuel Stamatakis Uri Goldbourt Annette Peters Barbara Thorand Annika Rosengren Lena Björck Kyle Sprow Kristin Franzon Miguel Rodriguez-Barranco Leila Luján-Barroso Lars Alfredsson Martin Bahls Till Ittermann Miriam Wanner Matthias Bopp Jacob Louis Marott Peter Schnohr Børge G.Nordestgaarda Knut Eirik Dalene Ulf Ekelund Johan Clausen Magnus T.Jensen Christina Bjørk Petersen Niklas Krause Jos Twisk Willem van Mechelen Allard J.van der Beek Department of Public and Occupational Health Amsterdam Public Health Research InstituteVrije Universiteit AmsterdamAmsterdam UMCAmsterdam 1081 HVthe Netherlands National Research Centre for the Working Environment Copenhagen 2100Denmark Department of Sports Science and Clinical Biomechanics University of Southern DenmarkOdense 5230Denmark U.S.Public Health Service ArlingtonVA 22201USA Department of Public Health and Nursing Norwegian University of Science and TechnologyTrondheim 8905Norway Levanger Hospital Nord-Trøndelag Hospital TrustLevanger 7601Norway Department of Public Health and Primary Care Ghent UniversityGhent 9000Belgium Center for Clinical Research and Prevention Bispebjerg and Frederiksberg HospitalFrederiksberg 2000Denmark The Capital Region of Denmark Copenhagen 1172Denmark Western Norway University of Applied Sciences Faculty of EducationArts and SportsSogndal 5414Norway Institute of Public Health and Clinical Nutrition University of Eastern FinlandKuopio 1627Finland Faculty of Health and Life Sciences University of ExeterExeter EX12LUUK Mackenzie Wearables Research Hub Charles Perkins CentreThe University of SydneyNSW 2050Australia School of Health Sciences Faculty of Medicine and HealthThe University of SydneyNSW 2050Australia Sackler Medical faculty in Tel Aviv University Tel Aviv 6997801Israel Institute of Epidemiology Helmholtz Zentrum MünchenGerman Research Center for Environmental HealthNeuherberg 85764Germany German Centre for Cardiovascular Research(DZHK e.V.) partner site Munich Heart AllianceMunich 80636Germany Institute for Medical Information Processing Biometryand Epidemiology(IBE)Pettenkofer School of Public HealthFaculty of MedicineLudwig-Maximilians-UniversitätMunich 80636Germany Institute of Medicine Department of Molecular and Clinical MedicineSahlgrenska AcademyUniversity of GothenburgGothenburg 40530Sweden Region Västra Götaland Sahlgrenska University HospitalDepartment of Medicine Geriatrics and Emergency Medicine/ÖstraGothenb

Background There is insufficient evidence to provide recommendations for leisure-time physical activity among workers across various occupational physical activity *** study aimed to assess the association of leisure-time physical activity with cardiovascular and all-cause mortality across occupational physical activity *** This study utilized individual participant data from 21 cohort studies,comprising both published and unpublished *** criteria included individual-level data on leisure-time and occupational physical activity(categorized as sedentary,low,moderate,and high)along with data on all-cause and/or cardiovascular mortality.A 2-stage individual participant data meta-analysis was conducted,with separate analysis of each study using Cox proportional hazards models(Stage 1).These results were combined using random-effects models(Stage 2).Results Higher leisure-time physical activity levels were associated with lower all-cause and cardiovascular mortality risk across most occupational physical activity levels,for both males and *** males with sedentary work,high compared to sedentary leisure-time physical activity was associated with lower all-cause(hazard ratios(HR)=0.77,95%confidence interval(95%CI):0.70-0.85)and cardiovascular mortality(HR=0.76,95%CI:0.66-0.87)*** males with high levels of occupational physical activity,high compared to sedentary leisure-time physical activity was associated with lower all-cause(HR=0.84,95%CI:0.74-0.97)and cardiovascular mortality(HR=0.79,95%CI:0.60-1.04)risk,while HRs for low and moderate levels of leisure-time physical activity ranged between 0.87 and 0.97 and were not statistically *** females,most effects were similar but more imprecise,especially in the higher occupational physical activity *** Higher levels of leisure-time physical activity were generally associated with lower mortality ***,results for workers with moderate and high

关键词： Mortality Individual participant data Physical activity paradox Job demands

来源：评论

学校读者我要写书评

暂无评论

High-resolution dynamic imaging of chromatin DNA communication using Oligo-LiveFISH

引用

Cell 2025年

作者： Zhu, Yanyu Balaji, Ashwin Han, Mengting Andronov, Leonid Roy, Anish R. Wei, Zheng Chen, Crystal Miles, Leanne Cai, Sa Gu, Zhengxi Tse, Ariana Yu, Betty Chentzu Uenaka, Takeshi Lin, Xueqiu Spakowitz, Andrew J. Moerner, W.E. Qi, Lei S. Department of Bioengineering Stanford University Stanford 94305 CA United States Department of Chemistry Stanford University Stanford 94305 CA United States Biophysics PhD Program Stanford University Stanford 94305 CA United States Computational Biology Program Public Health Sciences Division and Translational Data Science IRC Fred Hutchinson Cancer Center Seattle 98109 WA United States Department of Chemical Engineering Stanford University Stanford 94305 CA United States Department of Materials Science and Engineering Stanford University Stanford 94305 CA United States Institute for Stem Cell Biology & Regenerative Medicine and Department of Pathology Stanford University School of Medicine Stanford 94305 CA United States Sarafan ChEM-H Stanford University Stanford 94305 CA United States Chan Zuckerberg Biohub San Francisco 94080 CA United States

Three-dimensional (3D) genome dynamics are crucial for cellular functions and disease. However, real-time, live-cell DNA visualization remains challenging, as existing methods are often confined to repetitive regions, suffer from low resolution, or require complex genome engineering. Here, we present Oligo-LiveFISH, a high-resolution, reagent-based platform for dynamically tracking non-repetitive genomic loci in diverse cell types, including primary cells. Oligo-LiveFISH utilizes fluorescent guide RNA (gRNA) oligo pools generated by computational design, in vitro transcription, and chemical labeling, delivered as ribonucleoproteins. Utilizing machine learning, we characterized the impact of gRNA design and chromatin features on imaging efficiency. Multi-color Oligo-LiveFISH achieved 20-nm spatial resolution and 50-ms temporal resolution in 3D, capturing real-time enhancer and promoter dynamics. Our measurements and dynamic modeling revealed two distinct modes of chromatin communication, and active transcription slows enhancer-promoter dynamics at endogenous genes like FOS. Oligo-LiveFISH offers a versatile platform for studying 3D genome dynamics and their links to cellular processes and disease. © 2025 Elsevier Inc.

关键词： CRISPR imaging DNA communication dynamic tracking enhancer-promoter interaction high-resolution imaging live DNA imaging non-repetitive genome imaging Oligo-LiveFISH polymer modeling primary cell

来源：评论

学校读者我要写书评

暂无评论

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

SYNTHETIC data IN MACHINE LEARNING FOR PATHOLOGY

引用

Journal of Pathology Informatics 2022年 13卷 100044-100044页

作者： Chen, Richard J. Lu, Ming Y. Chen, Tiffany Y. Williamson, Drew F.K. Mahmood, Faisal Department of Pathology Brigham and Women’s Hospital and Harvard Medical School Boston MA USA Department of Biomedical Informatics Harvard Medical School Boston MA USA Cancer Program Broad Institute of Harvard and MIT Cambridge MA USA Cancer Data Science Program Dana-Farber Cancer Institute Boston MA USA

来源：评论

学校读者我要写书评

暂无评论

AI-BASED PATHOLOGY PREDICTS ORIGINS FOR cancerS OF UNKNOWN PRIMARY

引用

Journal of Pathology Informatics 2022年 13卷 100045-100045页

作者： Lu, Ming Y. Chen, Tiffany Y. Williamson, Drew F.K. Zhao, Melissa Shady, Maha Lipkova, Jana Mahmood, Faisal Department of Pathology Brigham and Women’s Hospital and Harvard Medical School Boston MA USA Cancer Program Broad Institute of Harvard and MIT Cambridge MA USA Cancer Data Science Program Dana-Farber Cancer Institute Boston MA USA Department of Biomedical Informatics Harvard Medical School Boston MA USA

来源：评论

学校读者我要写书评

暂无评论

PAN-cancer INTEGRATIVE HISTOLOGY-GENOMIC ANALYSIS VIA INTERPRETABLE MULTIMODAL DEEP LEARNING

引用

Journal of Pathology Informatics 2022年 13卷 100057-100057页

作者： Chen, Richard J. Lu, Ming Y. Williamson, Drew F.K. Chen, Tiffany Y. Lipkova, Jana Shaban, Muhammad Shady, Maha Williams, Mane Joo, Bumjin Noor, Zahra Mahmood, Faisal Department of Pathology Brigham and Women’s Hospital Harvard Medical School Boston MA USA Department of Biomedical Informatics Harvard Medical School Boston MA USA Cancer Program Broad Institute of Harvard and MIT Cambridge MA USA Cancer Data Science Program Dana-Farber Cancer Institute Boston MA USA Department of Computer Science Harvard University Cambridge MA USA

来源：评论

学校读者我要写书评

暂无评论

P1.27-04 Phase II Basket Trial of Dual Anti-CTLA-4 and Anti-PD-1 Blockade in Rare Tumors (DART) SWOG S1609: Bronchioloalveolar Carcinoma of the Lung

引用

Journal of Thoracic Oncology 2023年第11期18卷 S284-S285页

作者： Y.K. Chae M. Othus S.P. Patel D.E. Gerber T. Tanvetyanon L.I.-Y. Chung H.S. Kim C.M. McLeod H.X. Chen E. Sharon H. Streicher C.W. Ryan C.D. Blanke R. Kurzrock Northwestern University CHICAGO/IL/USA SWOG Statistics and Data Management Center Seattle/WA/USA University of California at San Diego Moores Cancer Center La Jolla/CA/USA University of Texas Southwestern Medical Center Simmons Cancer Center Dallas/TX/USA Moffitt Cancer Center Tampa/FL/USA SWOG Data Operations Center Seattle/WA/USA National Cancer Institute Investigational Drug Branch Cancer Therapy Evaluation Program Bethesda/MD/USA Oregon Health & Science University Portland/OR/USA SWOG Group Chair’s Office Knight Cancer Institute Portland/OR/USA Medical College of Wisconsin Milwaukee/WI/USA

来源：评论

学校读者我要写书评

暂无评论

EMBRACING DIGITAL AND COMPUTATIONAL PATHOLOGY DURING RESIDENCY TRAINING: PERSPECTIVES FROM TWO FORMER ANATOMIC PATHOLOGY RESIDENTS

引用

Journal of Pathology Informatics 2022年 13卷 100042-100042页

作者： Chen, Tiffany Y. Williamson, Drew F.K. Mahmood, Faisal Department of Pathology Brigham and Women’s Hospital and Harvard Medical School Boston Massachusetts United States Cancer Program Broad Institute of Harvard and MIT Cambridge Massachusetts United States Department of Biomedical Informatics Harvard Medical School Boston Massachusetts United States Cancer Data Science Program Dana-Farber Cancer Institute Boston Massachusetts United States

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：