检索结果-内蒙古大学图书馆

Urban air pollution and emergency department visits for injury in Edmonton and Toronto, Canada (vol 4, 100020, 2022)

引用

HYGIENE AND ENVIRONMENTAL HEALTH ADVANCES 2022年 4卷

作者： Szyszkowicz, Mieczyslaw Thomson, Errol M. de Angelis, Nicholas Lavoie, Curtis Thang Chien Nguyen Environmental Health Science and Research Bureau Health Canada Ottawa Canada Department of Biochemistry Microbiology and Immunology University of Ottawa Ottawa Canada Biomedical Program Department of Mechanical and Aerospace Engineering Carleton University Ottawa Canada Curtis Lavoie Children's Hospital of Eastern Ontario Ottawa Canada University of Ha Noi Information Technology Faculty Ha Noi Viet Nam

Air pollution is associated with a broad spectrum of health conditions. Among the reported associations are central nervous system effects, suggesting that air pollution may also affect human behavior and reaction time, which could in turn increase likelihood of injury. Injuries impose a significant public health and economic toll, but to our knowledge the relationship with air pollution has not been examined. This study investigated associations between air pollution and emergency department (ED) visits for injury and poisoning in two Canadian cities (Edmonton, Toronto). Daily concentrations of carbon monoxide, ozone, sulfur dioxide, nitrogen dioxide, and fine particulate matter (PM 2.5 ), and two air quality indexes (AQHI, AQHIX; incorporating O 3 , NO 2 , and PM 2.5 ), were considered. A time-stratified case-crossover design and conditional Poisson regression models were used to study short-term exposure effects (0 to 14 day lags). The analysis was done by sex, age group, and season. Significant positive associations were observed in both cities, albeit with some differences in the pattern of effects across strata. Relative risks (RR) and 95% confidence intervals (CI) for an interquartile range (IQR) increase of NO 2 (IQR=13.0 ppb, Edmonton) in cold season (October-March) for male were RR=1.012 (95% CI: 1.005, 1.018), 1.025 (1.018, 1.031), 1.026 (1.020, 1.033), and 1.025 (1.019, 1.032), for lags from 0 to 3 days, respectively. The corresponding results in Toronto (IQR=8.8 ppb) were: 1.010 (1.004, 1.017), 1.007 (1.000, 1.013), 1.009 (1.003, 1.016), and 1.007 (1.000, 1.013). The data suggest a potential association between air pollution and increased number of ED visits for injury.

关键词： Ambient air pollution Behavior Exposure Injury Poisoning

来源：评论

学校读者我要写书评

暂无评论

CNN-based cardiac motion extraction to generate deformable geometric left ventricle myocardial models from Cine MRI

arXiv

引用

arXiv 2021年

作者： Upendra, Roshan Reddy Wentz, Brian Jamison Simon, Richard Shontz, Suzanne M. Linte, Cristian A. Center for Imaging Science Rochester Institute of Technology RochesterNY United States Biomedical Engineering Rochester Institute of Technology RochesterNY United States Bioengineering Graduate Program University of Kansas LawrenceKS United States Electrical Engineering and Computer Science University of Kansas LawrenceKS United States Information and Telecommunication Technology Center University of Kansas LawrenceKS United States

Patient-specific left ventricle (LV) myocardial models have the potential to be used in a variety of clinical scenarios for improved diagnosis and treatment plans. Cine cardiac magnetic resonance (MR) imaging provides high resolution images to reconstruct patient-specific geometric models of the LV myocardium. With the advent of deep learning, accurate segmentation of cardiac chambers from cine cardiac MR images and unsupervised learning for image registration for cardiac motion estimation on a large number of image datasets is attainable. Here, we propose a deep leaning-based framework for the development of patient-specific geometric models of LV myocardium from cine cardiac MR images, using the Automated Cardiac Diagnosis Challenge (ACDC) dataset. We use the deformation field estimated from the VoxelMorph-based convolutional neural network (CNN) to propagate the isosurface mesh and volume mesh of the end-diastole (ED) frame to the subsequent frames of the cardiac cycle. We assess the CNN-based propagated models against segmented models at each cardiac phase, as well as models propagated using another traditional nonrigid image registration technique. © 2021, CC BY.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin to Link Flood Models, Sensors, and Earth Observations for Coastal Resilience in Hampton Roads, Virginia, U.S.A

A Digital Twin to Link Flood Models, Sensors, and Earth Obse...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Thomas R. Allen Sridhar Katragadda Yin-Hsuen Chen Brian Terry Joshua Baptist Oguz Yetkin Navid Tahvildari Sunghoon Han Blake Steiner George McLeod Soenke Dangendor Qiang Sun Heather Richter Geography Program and Institute for Coastal Adaptation and Resilience (ICAR) Old Dominion University Norfolk Virginia U.S.A. Information Technology City of Virginia Beach Virginia U.S.A. Center for Geospatial Education and Analytics Old Dominion University Norfolk Virginia U.S.A. Analytical Mechanics Associates Hampton Virginia U.S.A. Department of Civil and Environmental Engineering Old Dominion University Norfolk Virginia U.S.A. Dept. of River-Coastal Science and Engineering Tulane University New Orleans Louisiana U.S.A. Hampton Roads Biomedical Research Consortium Old Dominion University Norfolk Virginia U.S.A.

A Digital Twin (DT) for coastal resilience in a low-lying coastal city necessarily entails characterizing the geophysical terrain, complex hydrologic flows, and infrastructure modifications that affect flooding. Coastal flooding in ports such as Hampton Roads, Virginia, arise from coastal storms, regular tidal estuarine circulation processes, seasonal to interannual external forcing from the ocean via the Gulf Stream and Atlantic Meridional Overturning Circulation (AMOC), and associated local influences on sea-level anomalies. We take a geospatial, hub-based approach to integrate digital linkages and threads among real-time Internet of Things (IoT) water level and flood sensors, an operational hydrodynamic model, localized probabilistic sea-level rise projections, hydro-corrected LiDAR Digital Elevation Models and GIS stormwater infrastructure, and an open data cube that ingests, hosts, and processes Application-Ready Datasets (ARDs.) Our paper describes the structure and cloud integration of a flood sensor network, StormSense, and its augmentation with end-user identified gap sites to improve network coverage and sensitivity to vulnerable communities. The enhancement of the multiple flood sensor networks incorporates multiple APIs and Amazon Web Services to normalize and homogenize data feeds among municipal sensors, private sector sensors, NOAA and USGS gauges, and new sensors sited in partnership with emergency managers, non-profits, and the National Weather Service. We describe the development and improvements of a Delft3D model for hydrodynamic simulation, including characterization and grid improvements of shallow estuarine creeks. The model includes sea-level rise parameters for the Hampton Roads study area. The paper also outlines Earth Observing data in the Virginia Open Data Cube, including products from NASA, NOAA, ESA, and newly incorporated drone data. The data cube hosts multi-purpose data products, such as satellite derived Land Use/Land Cover, MODIS,

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Open Data Cube Platform as a Coastal Digital Twin: Prototypes to Inform Flooding and Environmental Health

An Open Data Cube Platform as a Coastal Digital Twin: Protot...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Thomas R. Allen Yin-Hsuen Chen Blake Steiner George McLeod Sridhar Katragadda Brian Terry Joshua Baptist Oguz Yetkin Navid Tahvildari Sunghoon Han Brandon Feldhaus Heather Richter Geography Program and Institute for Coastal Adaptation and Resilience (ICAR) Old Dominion University Norfolk Virginia U.S.A. Center for Geospatial Science Education and Analytics Old Dominion University Norfolk Virginia U.S.A. Information Technology Virginia U.S.A. Analytical Mechanics Associates Hampton Virginia U.S.A. Department of Civil and Environmental Engineering Old Dominion University Norfolk Virginia U.S.A. Brandon E. Feldhaus Virginia Modeling and Simulation Center Old Dominion University Suffolk Virginia U.S.A. Hampton Roads Biomedical Research Consortium Old Dominion University Norfolk Virginia U.S.A.

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Earth science Digital Twins are rapidly evolving to advance earth science understanding and societally relevant decision making. Coastal hazards pose complex and compound threats to dynamic human settlements and land use, inviting their analysis using digital twin technologies. A geospatial approach requires a framework for data assimilation that spans Earth observations, in situ sensor networks, environmental models, and characterization of human population and infrastructure assets. In our study, an Open Data Cube is developed as the core integration platform for a series of prototype case studies: 1) coastal mosquito-borne disease exposure assessment; 2) dasymetric mapping of vulnerable populations; and 3) integrated modeling and observational assessment of a King Tide flood event for Hampton Roads, Virginia (USA.) These prototypes are described with preliminary results. The paper also discusses benefits of the ODC as a Digital Twin as well as impediments and future developments for enhanced capabilities.

关键词： Satellites Roads Prototypes Sea measurements Digital twins Rivers Floods

来源：评论

学校读者我要写书评

暂无评论

Accelerating Real-Time Imaging for Radiotherapy: Leveraging Multi-GPU Training with PyTorch

Accelerating Real-Time Imaging for Radiotherapy: Leveraging ...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Ruth Obe Brandt Kaufmann Kaelen Baird Sam Kadel Yasmin Soltani Mostafa Cham Matthias K. Gobbert Carlos A. Barajas Zhuoran Jiang Vijay R. Sharma Lei Ren Stephen W. Peterson Jerimy C. PoIf Dept. of Computer Science and of Software Engineering U. of Houston-Clear Lake USA Dept. of Mathematics and Statistics U. of San Francisco USA Dept. of Computer Science and of Mathematics Skidmore College USA Dept. of Computer Science and of Psychology Mount Holyoke College USA Dept. of Biomedical Engineering U. of Houston USA Dept. of Information Systems U. of Maryland Baltimore County Dept. of Mathematics and Statistics U. of Maryland Baltimore County Medical Physics Graduate Program Duke University USA Dept. of Radiation Oncology U. of Maryland School of Medicine USA Department of Radiation Oncology U. of Maryland School of Medicine USA Dept. of Physics U. of Cape Town South Africa H3D Inc. USA

Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mit-igate unnecessary radiation exposure in healthy tissues. Real-time imaging of prompt gamma rays with Compton cameras has been suggested to improve therapy efficacy. However, the camera's non-zero time resolution leads to incorrect interaction classifications and noisy images that are insufficient for accurately assessing proton delivery in patients. To address the challenges posed by the Compton camera's image quality, machine learning techniques are employed to classify and refine the generated data. These machine-learning techniques include recurrent and feedforward neural networks. A PyTorch model was designed to improve the data captured by the Compton camera. This decision was driven by PyTorch's flexibility, powerful capabilities in handling sequential data, and enhanced G PU usage. This accelerates the model's computations on large-scale radiotherapy data. Through hyperparameter tuning, the validation accuracy of our PyTorch model has been improved from an initial 7 % to over 60 %. Moreover, the PyTorch Distributed Data Parallelism strategy was used to train the RNN models on multiple G PU s, which significantly reduced the training time with a minor impact on model accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Question-Answering System Extracts information on Injection Drug Use from Clinical Notes

arXiv

引用

arXiv 2023年

作者： Mahbub, Maria Goethert, Ian Danciu, Ioana Knight, Kathryn Srinivasan, Sudarshan Tamang, Suzanne Rozenberg-Ben-Dror, Karine Solares, Hugo Martins, Susana Trafton, Jodie Begoli, Edmon Peterson, Gregory D. Cyber Resilience and Intelligence Division Oak Ridge National Laboratory Oak RidgeTN United States Information Technology Services Division Oak Ridge National Laboratory Oak RidgeTN United States Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak RidgeTN United States Department of Biomedical Informatics Vanderbilt University NashvilleTN United States Program Evaluation and Resource Center Office of Mental Health and Suicide Prevention Department of Veterans Affairs United States Department of Medicine Stanford University School of Medicine StanfordCA United States Veterans Affairs Great Lakes Health Care System WestchesterIL United States Department of Electrical Engineering and Computer Science University of Tennessee Knoxville KnoxvilleTN United States

Background: Injection drug use (IDU) is a dangerous health behavior that increases mortality and morbidity. Identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients’ electronic health records (EHR) is difficult because there is no International Classification of Disease (ICD) code and the only place IDU information can be indicated is unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools. Methods: To address this gap in clinical information, we design and demonstrate a question-answering (QA) framework to extract information on IDU from clinical notes. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We utilize 2323 clinical notes of 1145 patients sourced from the VA Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model’s ability to extract IDU-related information on temporally out-of-distribution data. Results: Here we show that for a strict match between gold-standard and predicted answers, the QA model achieves 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data. Conclusions: Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care. © 2023, CC BY-NC-ND.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

Treatment Algorithm for the Resorption of Calcific Tendinitis Using Extracorporeal Shockwave Therapy: A Data Mining Study

引用

Orthopaedic Journal of Sports Medicine 2024年第3期12卷 23259671241231609页

作者： Chou, Wen-Yi Cheng, Jai-Hong Lien, Yu-Jui Huang, Tian-Hsiang Ho, Wen-Hsien Chou, Paul Pei-Hsi Doctoral Degree Program in Biomedical Engineering College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Department of Orthopedic Surgery Kaohsiung Chang Gung Memorial Hospital Chang Gung University College of Medicine Kaohsiung Taiwan Department of Leisure and Sport Management Cheng Shiu University Kaohsiung Taiwan Center for Shockwave Medicine and Tissue Engineering Department of Medical Research Kaohsiung Chang Gung Memorial Hospital Chang Gung University College of Medicine Kaohsiung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan College of Professional Studies National Pingtung University of Science and Technology Pingtung Taiwan Department of Sports Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Division of Sports Medicine Department of Orthopaedic Surgery Kaohsiung Medical University Hospital Kaohsiung Taiwan Department of Orthopaedics School of Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Department of Orthopaedic Surgery Kaohsiung Municipal Hsiao-Kang Hospital Kaohsiung Taiwan

Background: Although evidence indicates that extracorporeal shockwave therapy (ESWT) is effective in treating calcifying shoulder tendinitis, incomplete resorption and dissatisfactory results are still reported in many cases. Data mining techniques have been applied in health care in the past decade to predict outcomes of disease and treatment. Purpose: To identify the ideal data mining technique for the prediction of ESWT-induced shoulder calcification resorption and the most accurate algorithm for use in the clinical setting. Study Design: Case-control study. Methods: Patients with painful calcified shoulder tendinitis treated by ESWT were enrolled. Seven clinical factors related to shoulder calcification were adopted as the input attributes: sex, age, side affected, symptom duration, pretreatment Constant-Murley score, and calcification size and type. The 5 data mining techniques assessed were multilayer perceptron (neural network), naïve Bayes, sequential minimal optimization, logistic regression, and the J48 decision tree classifier. Results: A total of 248 patients with calcified shoulder tendinitis were enrolled in this study. Shorter symptom duration yielded the highest gain ratio (0.374), followed by smaller calcification size (0.336) and calcification type (0.253). With the J48 decision tree method, the accuracy of 3 input attributes was 89.5% by 10-fold cross-validation, indicating satisfactory accuracy. A treatment algorithm using the J48 decision tree indicated that a symptom duration of ≤10 months was the most positive indicator of calcification resorption, followed by a calcification size of ≤10.82 mm. Conclusion: The J48 decision tree method demonstrated the highest precision and accuracy in the prediction of shoulder calcification resorption by ESWT. A symptom duration of ≤10 months or calcification size of ≤10.82 mm represented the clinical scenarios most likely to show resorption after ESWT. © The Author(s) 2024.

关键词： calcific tendinitis data mining extracorporeal shockwave therapy J48 decision tree shoulder

来源：评论

学校读者我要写书评

暂无评论

Negative prognostic factors and clinical improvement prediction modeling for extracorporeal shockwave therapy in calcific shoulder tendinitis using artificial intelligence techniques

引用

Journal of Shoulder and Elbow Surgery 2025年

作者： Chou, Wen-Yi Huang, Tian-Hsiang Cheng, Jai-Hong Lien, Yu-Jui Ho, Wen-Hsien Chou, Paul Pei-Hsi Ph.D. Program in Biomedical Engineering College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Department of Orthopedic Surgery Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine Kaohsiung Taiwan Department of Leisure and Sport Management Cheng Shiu University Kaohsiung Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan Department of Medical Research Center for Shockwave Medicine and Tissue Engineering Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine Kaohsiung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung Taiwan College of Professional Studies National Pingtung University of Science and Technology Pingtung Taiwan Precision Sports Medicine and Health Promotion Center Kaohsiung Medical University Kaohsiung Taiwan Department of Sports Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Division of Sports Medicine Department of Orthopaedic Surgery Kaohsiung Medical University Hospital Kaohsiung Taiwan Department of Orthopaedics School of Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan

Background: The efficacy of extracorporeal shockwave therapy (ESWT) for treating shoulder calcific tendinitis can be influenced by various prognostic factors. This study aimed to identify prognostic factors associated with the failure of ESWT for symptom relief and to evaluate the predictive capability of the eXtreme Gradient Boosting (XGBoost) algorithm of artificial intelligence techniques in this context. Methods: This retrospective study enrolled patients with persistent shoulder pain attributed to calcific tendinitis who underwent ESWT after failed conservative treatment between January 1998 and December 2022. Age, sex, duration of symptoms, calcification classification and size, pre-ESWT visual analog scale (VAS), and pre-ESWT Constant-Murley score (CMS) served as potential input attributes. The difference in VAS and CMS were defined as the output attributes. The XGBoost model was used to predict treatment outcomes based on these factors. The dataset was balanced using the synthetic minority oversampling technique, and the model's performance was assessed using 10-fold cross-validation. Spearman's rank correlation coefficient analysis was adopted to explore the relationships between significant continuous input attributes and post-ESWT VAS and CMS scores. Results: A total of 296 patients with calcific tendinitis were enrolled and completed the 1-year follow-up. The findings revealed that a prolonged symptom duration (>10 months), severe pain (pre-ESWT VAS >5), and higher pre-ESWT CMS (>55) were significant prognostic factors for the failure of ESWT for symptom relief. Using these factors as inputs, the XGBoost model demonstrated high accuracy, precision, recall, and F1 score. By reducing the input attributes to age, calcification size, pre-ESWT CMS, and symptom duration, the model maintained a high prediction rate, suggesting that these factors are sufficient for effective prediction. Discussion: The present study identified significant prognostic factors asso

关键词： Artificial intelligence Basic science Study calcific tendinitis CMS Development of Predictive Computer Modeling Using AI/Machine Learning ESWT shoulder VAS XGBoost

来源：评论

学校读者我要写书评

暂无评论

A consensus protocol for functional connectivity analysis in the rat brain (vol 26, pg 673, 2023)

引用

NATURE NEUROscience 2023年第6期26卷 1127-1128页

作者： Grandjean, Joanes Desrosiers-Gregoire, Gabriel Anckaerts, Cynthia Angeles-Valdez, Diego Ayad, Fadi Barriere, David A. Blockx, Ines Bortel, Aleksandra Broadwater, Margaret Cardoso, Beatriz M. Celestine, Marina Chavez-Negrete, Jorge E. Choi, Sangcheon Christiaen, Emma Clavijo, Perrin Colon-Perez, Luis Cramer, Samuel Daniele, Tolomeo Dempsey, Elaine Diao, Yujian Doelemeyer, Arno Dopfel, David Dvorakova, Lenka Falfan-Melgoza, Claudia Fernandes, Francisca F. Fowler, Caitlin F. Fuentes-Ibanez, Antonio Garin, Clement M. Gelderman, Eveline Golden, Carla E. M. Guo, Chao C. G. Henckens, Marloes J. A. G. Hennessy, Lauren A. Herman, Peter Hofwijks, Nita Horien, Corey Ionescu, Tudor M. Jones, Jolyon Kaesser, Johannes Kim, Eugene Lambers, Henriette Lazari, Alberto Lee, Sung-Ho Lillywhite, Amanda Liu, Yikang Liu, Yanyan Y. Lopez-Castro, Alejandra Lopez-Gil, Xavier Ma, Zilu MacNicol, Eilidh Madularu, Dan Mandino, Francesca Marciano, Sabina McAuslan, Matthew J. McCunn, Patrick McIntosh, Alison Meng, Xianzong Meyer-Baese, Lisa Missault, Stephan Moro, Federico Naessens, Daphne M. P. Nava-Gomez, Laura J. Nonaka, Hiroi Ortiz, Juan J. Paasonen, Jaakko Peeters, Lore M. Pereira, Mickael Perez, Pablo D. Pompilus, Marjory Prior, Malcolm Rakhmatullin, Rustam Reimann, Henning M. Reinwald, Jonathan Del Rio, Rodrigo Triana Rivera-Olvera, Alejandro Ruiz-Perez, Daniel Russo, Gabriele Rutten, Tobias J. Ryoke, Rie Sack, Markus Salvan, Piergiorgio Sanganahalli, Basavaraju G. Schroeter, Aileen Seewoo, Bhedita J. Selingue, Erwan Seuwen, Aline Shi, Bowen Sirmpilatze, Nikoloz Smith, Joanna A. B. Smith, Corrie Sobczak, Filip Stenroos, Petteri J. Straathof, Milou Strobelt, Sandra Sumiyoshi, Akira Takahashi, Kengo Torres-Garcia, Maria E. Tudela, Raul van den Berg, Monica van der Marel, Kajo van Hout, Aran T. B. Vertullo, Roberta Vidal, Benjamin Vrooman, Roel M. Wang, Victora X. Wank, Isabel Watson, David J. G. Yin, Ting Zhang, Yongzhi Zurbruegg, Stefan Achard, Sophie Alcauter, Sarael Auer, Dorothee P. Barbier, Emmanuel L. Baudewig, Juergen Beckmann, Chri Donders Institute for Brain Behaviour and Cognition Radboud University Nijmegen The Netherlands Department for Medical Imaging Radboud University Medical Center Nijmegen The Netherlands Cerebral Imaging Centre Douglas Mental Health University Institute Verdun QC Canada Integrated Program in Neuroscience McGill University Montreal QC Canada Bio-imaging Lab University of Antwerp Antwerp Belgium µNEURO Research Centre of Excellence University of Antwerp Antwerp Belgium Instituto de Neurobiología Universidad Nacional Autónoma de México Campus Juriquilla Querétaro Mexico Biological and Biomedical Engineering McGill University Montreal QC Canada McConnell Brain Imaging Centre McGill University Montreal QC Canada Montreal Neurological Institute McGill University Montreal QC Canada UMR INRAE/CNRS 7247 Physiologie des Comportements et de la Reproduction Physiologie de la reproduction et des comportements Centre de recherche INRAE de Nouzilly Tours France Department of Neurology and Neurosurgery McGill University Montreal QC Canada Center for Animal MRI University of North Carolina at Chapel Hill Chapel Hill NC USA Department of Neurology University of North Carolina at Chapel Hill Chapel Hill NC USA Biomedical Research Imaging Center University of North Carolina at Chapel Hill Chapel Hill NC USA Preclinical MRI Champalimaud Research Champalimaud Centre for the Unknown Lisbon Portugal Laboratoire des Maladies Neurodégénératives Molecular Imaging Research Center (MIRCen) Université Paris-Saclay Commissariat à l’Énergie Atomique et aux Énergies Alternatives (CEA) CNRS Fontenay-aux-Roses France Departamento de Neurobiología Conductual y Cognitiva Instituto de Neurobiología Universidad Nacional Autónoma de México Campus Juriquilla Querétaro México Translational Neuroimaging and Neural Control Group High-Field Magnetic Resonance Max Planck Institute for Biological Cybernetics Tuebingen Germany Graduate Training Centre of Neuroscience International Max

Task-free functional connectivity in animal models provides an experimental framework to examine connectivity phenomena under controlled conditions and allows for comparisons with data modalities collected under invasive or terminal procedures. Currently, animal acquisitions are performed with varying protocols and analyses that hamper result comparison and integration. Here we introduce StandardRat, a consensus rat functional magnetic resonance imaging acquisition protocol tested across 20 centers. To develop this protocol with optimized acquisition and processing parameters, we initially aggregated 65 functional imaging datasets acquired from rats across 46 centers. We developed a reproducible pipeline for analyzing rat data acquired with diverse protocols and determined experimental and processing parameters associated with the robust detection of functional connectivity across centers. We show that the standardized protocol enhances biologically plausible functional connectivity patterns relative to previous acquisitions. The protocol and processing pipeline described here is openly shared with the neuroimaging community to promote interoperability and cooperation toward tackling the most important challenges in neuroscience.

关键词： Databases Neural circuits

来源：评论

学校读者我要写书评

暂无评论

A pretrained transformer model for decoding individual glucose dynamics from continuous glucose monitoring data

引用

National science Review 2025年第05期 362-381页

作者： Yurun Lu Dan Liu Zhongming Liang Rui Liu Pei Chen Yitong Liu Jiachen Li Zhanying Feng Lei M.Li Bin Sheng Weiping Jia Luonan Chen Huating Li Yong Wang Center for Excellence in Mathematical Sciences National Center for Mathematics and Interdisciplinary Sciences Hua Loo-Keng Center for Mathematical Sciences Key Laboratory of Management Decision and Information System Academy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematics University of Chinese Academy of SciencesChinese Academy of Sciences Department of Endocrinology and Metabolism Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of MedicineShanghai Diabetes InstituteShanghai Clinical Center for Diabetes Shanghai Key Laboratory of Diabetes Mellitus Key Laboratory of Systems Health Science of Zhejiang Province School of Life ScienceHangzhou Institute for Advanced StudyUniversity of Chinese Academy of Sciences BGI-Research School of Mathematics South China University of Technology Department of Statistics Department of Biomedical Data Science Bio-X ProgramStanford University Department of Computer Science and Engineering Shanghai Jiao Tong University State Key Laboratory of Cell Biology Center for Excellence in Molecular Cell Science Shanghai Institute of Biochemistry and Cell Biology Chinese Academy of Sciences Guangdong Institute of Intelligence Science and Technology Pazhou Laboratory (Huangpu)

Continuous glucose monitoring(CGM) technology has grown rapidly to track real-time blood glucose levels and trends with improved sensor accuracy. The ease of use and wide availability of CGM will facilitate safe and effective decision making for diabetes management. Here, we developed an attention-based deep learning model, CGMformer, pretrained on a well-controlled and diverse corpus of CGM data to represent individual's intrinsic metabolic state and enable clinical applications. During pretraining, CGMformer encodes glucose dynamics including glucose level, fluctuation, hyperglycemia, and hypoglycemia into latent space with self-supervised learning. It shows generalizability in imputing glucose value across five external datasets with different populations and metabolic states(MAE = 3.7 mg/d L). We then fine-tuned CGMformer towards a diverse panel of downstream tasks in the screening of diabetes and its complications using task-specific data, which demonstrated a consistently boosted predictive accuracy over direct fine-tuning on a single task(AUROC = 0.914 for type 2 diabetes(T2D) screening and 0.741 for complication screening). By learning an intrinsic representation of an individual's glucose dynamics,CGMformer classifies non-diabetic individuals into six clusters with elevated T2D risks, and identifies a specific cluster with lean body-shape but high risk of glucose metabolism disorders, which is overlooked by traditional glucose measurements. Furthermore, CGMformer achieves high accuracy in predicting an individual's postprandial glucose response with dietary modelling(Pearson correlation coefficient = 0.763)and helps personalized dietary recommendations. Overall, CGMformer pretrains a transformer neural network architecture to learn an intrinsic representation by borrowing information from a large amount of daily glucose profiles, and demonstrates predictive capabilities fine-tuned towards a broad range of downstream applications, holding promise for the ear

关键词：

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：