检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Karamched, Bhargav Hripcsak, George Albers, David Ott, William Department of Mathematics Institute of Molecular Biophysics Florida State University TallahasseeFL32306 United States Department of Biomedical Informatics Columbia University New YorkNY10032 United States Section of Informatics and Data Science Department of Pediatrics Department of Biomedical Engineering Department of Biostatistics and Informatics University of Colorado Anschutz Medical Campus AuroraCO80045 United States Department of Mathematics University of Houston HoustonTX77204 United States

Medical practice in the intensive care unit is based on the assumption that physiological systems such as the human glucose-insulin system are predictable. We demonstrate that delay within the glucose-insulin system can induce sustained temporal chaos, rendering the system unpredictable. Specifically, we exhibit such chaos for the Ultradian glucose-insulin model. This well-validated, finite-dimensional model represents feedback delay as a three-stage filter. Using the theory of rank one maps from smooth dynamical systems, we precisely explain the nature of the resulting delay-induced uncertainty (DIU). We develop a framework one may use to diagnose DIU in a general oscillatory dynamical system. For infinite-dimensional delay systems, no analog of the theory of rank one maps exists. Nevertheless, we show that the geometric principles encoded in our DIU framework apply to such systems by exhibiting sustained temporal chaos for a linear shear flow. Our results are potentially broadly applicable because delay is ubiquitous throughout mathematical *** Codes 92C50, 92C30, 37N25, 37D25, 37D45, 37G35 Copyright © 2020, The Authors. All rights reserved.

关键词： Insulin

来源：评论

学校读者我要写书评

暂无评论

BiomedRAG: A Retrieval augmented Large Language Model for Biomedicine

arXiv

引用

arXiv 2024年

作者： Li, Mingchen Kilicoglu, Halil Xu, Hua Zhang, Rui Division of Computational Health Sciences Department of Surgery University of Minnesota MinneapolisMN United States School of Information Sciences University of Illinois at Urbana-Champaign Champaign United States Section of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States

Large Language Models (LLMs) have swiftly emerged as vital resources for different applications in the biomedical and healthcare domains;however, these models encounter issues such as generating inaccurate information or hallucinations. Retrieval-augmented generation provided a solution for these models to update knowledge and enhance their performance. In contrast to previous retrieval-augmented LMs, which utilize specialized cross-attention mechanisms to help LLM encode retrieved text, BiomedRAG adopts a simpler approach by directly inputting the retrieved chunk-based documents into the LLM. This straightforward design is easily applicable to existing retrieval and language models, effectively bypassing noise information in retrieved documents, particularly in noise-intensive tasks. Moreover, we demonstrate the potential for utilizing the LLM to supervise the retrieval model in the biomedical domain, enabling it to retrieve the document that assists the LM in improving its predictions. Specifically, BIOMEDRAG retrieves relevant documents from a specifically curated, diverse chunk database through a unique, purpose-built chunk scoring mechanism by a tunable scorer. This retrieval process then integrates the selected information directly into the LLM's input, facilitating the generation of expected output, such as structured knowledge. Our experiments reveal that with the tuned scorer, BIOMEDRAG attains superior performance across 4 biomedical NLP tasks, encompassing information extraction (triple extraction, relation extraction), text classification, and link prediction leveraging over 8 datasets. For instance, in the triple extraction task, BIOMEDRAG outperforms other triple extraction systems with micro-F1 scores of 81.42 and 88.83 on GIT and ChemProt corpora, respectively. The outstanding performance underscores the potential of BIOMEDRAG in constructing effective biomedical intervention systems for various tasks. © 2024, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Repurposing Drugs for Alzheimer's Diseases through Link Prediction on Biomedical Literature 11

Repurposing Drugs for Alzheimer's Diseases through Link Pred...

引用

11th IEEE International Conference on Healthcare informatics, ICHI 2023

作者： Xiao, Yongkang Hou, Yu Zhou, Huixue Diallo, Gayo Fiszman, Marcelo Wolfson, Julian Kilicoglu, Halil Chen, You Xu, Hua Mantyh, William G. Zhang, Rui University of Minnesota Institute for Health Informatics MinneapolisMN United States University of Minnesota Department of Surgery MinneapolisMN United States University of Bordeaux Inria Sistm Team AHeaD Inserm 1219 Bordeaux Population Health F-33000 France Pontifical Catholic University of Rio de Janeiro Nites - Núcleo de Inovação e Tecnologia em Saúde Brazil University of Minnesota Division of Biostatistics School of Public Health MinneapolisMN United States University of Illinois Urbana-Champaign School of Information Sciences ChampaignIL United States Vanderbilt University Medical Center Department of Biomedical Informatics NashvilleTN United States Yale University Section of Biomedical Informatics and Data Science New HavenCT United States University of Minnesota Department of Neurology MinneapolisMN United States

ISBN: (纸本)9798350302639

Recently, computational drug repurposing has emerged as a promising method for identifying new interventions for diseases. This study predicts novel drugs for Alzheimer's disease (AD) through link prediction on our developed biomedical knowledge graph. We constructed a comprehensive knowledge graph containing AD concepts and various potential interventions, called ADInt, by integrating a dietary supplement (DS) domain knowledge graph, SuppKG, with semantic triples from SemMedDB database. Four knowledge graph embedding models (TransE, RotatE, DistMult and ComplEX) and two graph convolutional network models (R-GCN and CompGCN) were compared to learn the representation of ADInt. R-GCN outperformed other models by evaluating on the time slice test set and the clinical trial test set, and was used to generate the score tables for the link prediction task. According to the results of link prediction, we proposed candidate drugs for AD. In conclusion, we presented a novel methodology to extend an existing knowledge graph and discover novel drugs for AD. Our method can potentially be applied to other clinical problems, such as discovering drug adverse reactions and drug-drug interactions. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SeNiors empOWered via Big data to Joint-Manage Their Medication-Related Risk of Falling in Primary Care: The SNOWDROP Project

SeNiors empOWered via Big Data to Joint-Manage Their Medicat...

引用

2024 Commit2data, C2D 2024

作者： Westerbeek, Leonie Blom, André Hogenes, Meefa Medlock, Stephanie van der Velde, Nathalie van Weert, Julia Dormosh, Noman Heymans, Martijn Linn, Annemiek Schut, Martijn van Weert, Henk Abu-Hanna, Ameen Amsterdam School of Communication Research ASCoR University of Amsterdam Netherlands Amsterdam Public Health Research Institute Netherlands Uw Zorg Online Amsterdam Netherlands Department of Medical Content ExpertDoc Rotterdam Netherlands Department of Medical Informatics Amsterdam Netherlands UMC location University of Amsterdam Netherlands Department of Internal Medicine Section of Geriatric Medicine Amsterdam Netherlands Department of Epidemiology and Data Science Amsterdam Netherlands UMC location Vrije Universiteit Amsterdam Netherlands Department of Laboratory Medicine Amsterdam Netherlands Department of General Practice Amsterdam Netherlands

ISBN: (纸本)9783959773515

In older persons, falls are the leading cause of injuries, often resulting in emergency room visits, serious injuries, and possibly even death. Medications are a major risk factor for falls. Because we lack tools to assess individualized risks, general practitioners (GPs) struggle with fall related medication management for seniors, and senior patients are not properly equipped to engage in the joint management of their medications. Our aim in this project is to develop and evaluate a comprehensive data-driven science approach for valid prediction of personalized risk of falling that effectively supports joint medication management between seniors and GPs. The project has two objectives. First, we aim to develop and validate prediction models from electronic health records for assessing individualized risk of medication-related falls. data science challenges include free text analysis;accounting for missing values;searching medication hierarchies;engineering new predictors, and understanding limitations of our approach. Second, we aim to develop and evaluate a joint medication management strategy for older patients and GPs, consisting of a clinical decision support system (CDSS) and a patient portal. We evaluate the effects of this strategy on changes in the quality of shared decision-making during a medication review consultation, medication management, and patient outcomes. The learnings from this project and the architecture underpinned by predictive modelling to support both GPs and patients can also be applied to other major health problems in the future. © Leonie Westerbeek, Noman Dormosh, André Blom, Martijn Heymans, Meefa Hogenes, Annemiek Linn, Stephanie Medlock, Martijn Schut, Nathalie van der Velde, Henk van Weert, Julia van Weert, and Ameen Abu-Hanna

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Biomedrag: A Retrieval Augmented Large Language Model for Biomedicine

SSRN

引用

SSRN 2024年

作者： Li, Mingchen Kilicoglu, Halil Xu, Hua Zhang, Rui Division of Computational Health Sciences Department of Surgery University of Minnesota MinneapolisMN United States School of Information Sciences University of Illinois at Urbana-Champaign Champaign IL United States Section of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States

Retrieval-augmented generation (RAG) offers a solution by retrieving knowledge from an established database to avoid hallucination of large language models (LLM). However, these models utilize specialized cross-attention mechanisms to help LLMs encode the retrieved text, hindering the application of RAG in closed LLMs (such as GPT-4). Additionally, these models retrieve information at the sentence or paragraph level, potentially introducing noise and affecting the generation quality. To address these issues, we propose a novel BiomedRAG framework that directly feeds automatically retrieved chunk-based documents into the LLM. Our evaluation of BiomedRAG across four biomedical natural language processing tasks using eight datasets demonstrates that our proposed framework not only improves the performance of LLMs 12.12% averagely but also achieves state of-the-art results compared to various baseline models by 5.33%. The BiomedRAG paves the way for more accurate and adaptable LLM applications in the biomedical domain. © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Correction: How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment

引用

JMIR Medical Education 2024年 10卷 e57594页

作者： Gilson, Aidan Safranek, Conrad W. Huang, Thomas Socrates, Vimig Chi, Ling Taylor, Richard Andrew Chartash, David Section for Biomedical Informatics and Data Science Yale University School of Medicine New Haven CT United States Department of Emergency Medicine Yale University School of Medicine New Haven CT United States Program of Computational Biology and Bioinformatics Yale University New Haven CT United States School of Medicine University College Dublin National University of Ireland Dublin Dublin Ireland Section for Biomedical Informatics and Data Science Yale University School of Medicine 300 George Street Suite 501 New Haven 06511 CT United States

In “How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge” (MIR Med Educ 2023;9:e45312) three additions were made to enhance discoverability. The title originally appeared as: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment And has been changed to: How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge In the “Objective” section of the Abstract, the following sentence: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. Has been changed to read as: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination (USMLE) Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. Finally, the abbreviation “USMLE” has been added to the Keywords section. The correction will appear in the online version of the paper on the JMIR Publications website on February 27, 2024 together with the publication of this correction notice. Because this was made after submission to PubMed, PubMed Central, and other full-text repositories, the corrected article has also been resubmitted to those repositories. © 2024 JMIR Publications Inc.. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations

arXiv

引用

arXiv 2024年

作者： Li, Yiming Peng, Xueqing Li, Jianfu Zuo, Xu Peng, Suyuan Pei, Donghong Tao, Cui Xu, Hua Hong, Na McWilliams School of Biomedical Informatics The University of Texas Health Science Center at Houston HoustonTX77030 United States Section of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT06510 United States Department of Artificial Intelligence and Informatics Mayo Clinic JacksonvilleFL32224 United States Institute of Information on Traditional Chinese Medicine China Academy of Chinese Medical Sciences Beijing100010 China The University of Texas MD Anderson Cancer Center HoustonTX77030 United States

In acupuncture therapy, the accurate location of acupoints is essential for its effectiveness. The advanced language understanding capabilities of large language models (LLMs) like Generative Pre-trained Transformers (GPT) present a significant opportunity for extracting relations related to acupoint locations from textual knowledge sources. This study aims to compare the performance of GPT with traditional deep learning models (Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers for Biomedical Text Mining (BioBERT)) in extracting acupoint-related location relations and assess the impact of pretraining and fine-tuning on GPT's performance. Materials and Methods We utilized the World Health Organization Standard Acupuncture Point Locations in the Western Pacific Region (WHO Standard) as our corpus, which consists of descriptions of 361 acupoints. Five types of relations ('direction_of,' 'distance_of,' 'part_of,' 'near_acupoint,' and 'located_near') (n= 3,174) between acupoints were annotated. Five models were compared: BioBERT, LSTM, pre-trained GPT-3.5, fine-tuned GPT-3.5, as well as pre-trained GPT-4. Performance metrics included micro-average exact match precision, recall, and F1 scores. Results Our results demonstrate that fine-tuned GPT-3.5 consistently outperformed other models in F1 scores across all relation types. Overall, it achieved the highest micro-average F1 score of 0.92. Conclusion This study underscores the effectiveness of LLMs like GPT in extracting relations related to acupoint locations, with implications for accurately modeling acupuncture knowledge and promoting standard implementation in acupuncture training and practice. The findings also contribute to advancing informatics applications in traditional and complementary medicine, showcasing the potential of LLMs in natural language processing. Copyright © 2024, The Authors. All rights reserved.

关键词： Acupuncture

来源：评论

学校读者我要写书评

暂无评论

Discovery of novel ancestry specific genes for androgens and hypogonadism in Million Veteran Program Men

引用

Nature Communications 2025年第1期16卷 1-12页

作者： Pagadala, Meghana S. Teerlink, Craig C. Jasuja, Guneet K. Palnati, Madhuri Anglin-Foote, Tori Chang, Nai-Chung N. Deka, Rishi Lee, Kyung M. Agiri, Fatai Y. Amariuta, Tiffany Seibert, Tyler M. Rose, Brent S. Pridgen, Kathryn M. Lynch, Julie A. Carter, Hannah K. Panizzon, Matthew S. Hauger, Richard L. Research Service VA San Diego Healthcare System San Diego CA United States Medical Scientist Training Program University of California San Diego La Jolla CA United States Biomedical Science Program University of California San Diego La Jolla CA United States VA Informatics and Computing Infrastructure (VINCI) VA Salt Lake City Healthcare System Salt Lake City UT United States Department of Internal Medicine Division of Epidemiology University of Utah School of Medicine Salt Lake City UT United States Center for Healthcare Organization and Implementation Research (CHOIR) VA Bedford Healthcare System Bedford MA United States Section of General Internal Medicine Boston University School of Medicine Boston MA United States Department of Health Law Policy and Management Boston University School of Public Health Boston MA United States Department of Radiation Medicine and Applied Sciences University of California San Diego La Jolla CA United States Department of Psychiatry University of California San Diego La Jolla CA United States Department of Medicine University of California San Diego La Jolla CA United States Halicioglu Data Science Institute University of California San Diego La Jolla CA United States Department of Radiology University of California San Diego La Jolla CA United States Department of Bioengineering University of California San Diego La Jolla CA United States Department of Urology University of California San Diego La Jolla CA United States Center for Behavior Genetics of Aging University of California San Diego La Jolla CA United States Center of Excellence for Stress and Mental Health (CESAMH) VA San Diego Healthcare System San Diego CA United States

Given the various roles of testosterone in men’s health, we conducted a multi-ancestral genetic analysis of total testosterone, free testosterone, SHBG, and hypogonadism in men within the Million Veteran Program (MVP). Here we identified 157 significant testosterone genetic variants, of which 8 have significant ancestry-specific associations. These variants implicate several genes, including SERPINF2, PRPF8, BAIAP2L1, SHBG, PRMT6, and PPIF, related to liver function. Genetic regulators of testosterone have cell type-specific effects in the testes, liver, and adrenal gland and are associated with disease risk. We conducted a meta-analysis amongst ancestry groups to identify 188 variants significantly associated with testosterone, of which 22 are novel associations. We constructed genetic scores for total testosterone, SHBG levels, and hypogonadism and find that men with higher testosterone genetic scores have lower odds of diabetes, hyperlipidemia, gout, and cardiac disorders. These findings provide insight into androgen regulation and identify novel variants for disease risk stratification. © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Kamino: A Scalable Architecture to Support Medical AI Research Using Large Real World data

Kamino: A Scalable Architecture to Support Medical AI Resear...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Fongci Lin Patrick Young Huan He Jimin Huang Roger Gagne Daniel Rice Nathan Price Will Byron Yan Hu Donn Felker Will Button Deniella Meeker Allen Hsiao Hua Xu Charles Torre Wade Schulz Section of Biomedical Informatics and Data Science School of Medicine Yale University New Haven CT USA Department of Laboratory Medicine School of Medicine Yale University New Haven CT USA Digital & Technology Solutions Yale New Haven Hospital New Haven CT USA Mcwilliam School of Biomedical Informatics University of Texas Health Science at Houston Houston TX USA Pediatrics and of Emergency Medicine at Yale School of Medicine Yale University New Haven CT USA

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

Electronic Health Records (EHRs) represent a crucial data source for real-world evidence generation. To facilitate biomedical studies using EHRs, standard data models like the OMOP CDM have been developed. Nevertheless, recent advancements in biomedical AI research that leverage EHRs have introduced new challenges, encompassing security considerations, large-scale data retrieval, and computational resource management, including GPUs. This paper introduces Kamino, an innovative architectural solution tailored to support biomedical AI research using EHR data. Kamino offers a user-friendly interface with features designed for efficient team access management in accordance with regulatory requirements. It facilitates direct data retrieval from an OMOP CDM instance and includes a resource allocation system based on Kubernetes orchestration. Here, we demonstrate the practical application and utility of Kamino through a clinical natural language processing task. We firmly believe that such a tool will significantly expedite AI research conducted with EHR data within academic institutions.

关键词： Soft sensors Medical services data models Natural language processing Resource management Security Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Assessing the Performance of Machine Learning Models Using Satellite dataset for Classification of Various Crop Types

Assessing the Performance of Machine Learning Models Using S...

引用

Geoinformatics for Spatial-Infrastructure Development in Earth and Allied sciences (GIS-IDEAS)

作者： Montree Pinkaeo Phaisarn Jeefoo Jirabhorn Chaiwongsai Surachai Chantee Pornthep Rojanavasu Prattana Deeprasertkul Geospatial Data Science School Of Information And Communication Technology University of Phayao Phayao Thailand Geographic Information Science School of Information and Communication Technology University of Phayao Phayao Thailand School of Information and Communication Technology University of Phayao Phayao Thailand Technology and Digital Division Hydro-Informatics Institute (Public Organization) Bangkok Thailand Researcher in Technology and Information Research Section Digital and Technology Development Division Hydro-Informatics Institute (Public Organization) Bangkok Thailand

ISBN: (数字)9798331504243

ISBN: (纸本)9798331504250

This paper aims to evaluate machine learning (ML) models' performance, named Random Forest (RF), Gradient Boosting (GB), Artificial Neural Network (ANN), and Support Vector Machine (SVM) for classifying different crop types using images from the Sentinel 2 satellite. The result shows that RF demonstrated the highest values across all criteria, outperforming the other models with an overall accuracy of 0.7365 (+ 0.010). With an accuracy of 0.7183 (+0.016) overall, GB trailed closely behind. The two models demonstrated robust performance, as evidenced by their respective F1-scores of 0.7344 and 0.7161, which suggest a well-balanced compromise between recall and precision. With total accuracies of 0.5429 (+ 0.0024) and 0.5169 (+ 0.017), respectively, the ANN and SVM algorithms performed comparably worse. In comparison to ensemble techniques like RF and GB, this shows that these models might not be as effective for this specific classification problem. The findings of this study can inform decision-making in the selection of ML algorithms for various applications, such as spatial water management, specifically in agriculture and irrigation, agricultural land management, and planning to mitigate the impact of natural disasters in the agricultural sector.

关键词： Support vector machines Radio frequency Accuracy Satellites Image resolution Crops Artificial neural networks Satellite images Classification algorithms Random forests

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：