检索结果-内蒙古大学图书馆

1st International Conference on Advances in Electrical, Electronics and Computational Intelligence, ICAEECI 2023

作者： Yadav, Abhivyakti Divya, S. Oviya, I.R. Raja, Kalpana Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Medicine Yale University Section for Biomedical Informatics and Data Science New HavenCT United States

ISBN: (纸本)9798350342796

DNA Barcodes, which are particular fragments derived from brief sections of DNA (such as mitochondrial, nuclear, and plastid sequences), can be used to identify organisms from the major life kingdoms. In addition to supporting conventional taxonomic techniques, DNA barcoding is a potent tool that advances our knowledge of species diversity and their ecological functions. On a variety of organisms, the use of this approach for species categorization has been successful. In this paper, we examine how DNA barcoding has been used to classify species based on DNA barcodes as well as other related research that has been done over the years on the subject. After experimenting with a number of deep learning models, we have propose a Variational Auto Encoder + Feed Forward Neural Network workflow for classifiying species using DNA barcodes. The models have been assessed on the basis of performance factors including accuracy, recall, and precision. COI, rbcL, matK, and ITS are the specific gene sections that have been identified as barcodes. For both simulated and real datasets, the model can attain an average accuracy of greater than 95 percent. This DNA barcoding approach has the ability to simplify DNA barcode-based species identification and serve as a tool for species categorization. © 2023 IEEE.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Predicting Protein-Protein Interactions Using Self-Attention-Based Deep Neural Networks and FastText Embeddings 15

Predicting Protein-Protein Interactions Using Self-Attention...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Oviya, I.R. Shanmukha Sravya, N. Raja, Kalpana Amrita Vishwa Vidyapeetham Amrita School Of Computing Department of Computer Science Engineering Chennai601103 India Yale University Section for Biomedical Informatics and Data Science School of Medicine New HavenCT United States

ISBN: (纸本)9798350370249

Predicting Protein-protein interactions are central to understanding the intricate mechanisms governing cellular functions, as proteins seldom act in isolation. While current machine learning and deep learning models focus on encoding protein sequences based on residue composition or physicochemical properties, they often overlook the complex relationships between amino acid segments within lengthy sequences. To address these limitations, we propose a novel hybrid model that combines a self-attention to enhance Deep neural network feature extraction with an with FastText Protein embeddings for predicting PPI. Utilizing transfer learning via the unsupervised FastText embedding technique to derive statistical representations of protein sequences, offers advantages over traditional protein encoding techniques in the context of analysing k-Mer sequences. Our model's performance is assessed through 5-fold cross-validation on datasets of *** and Human-Bacillus Anthracis protein interactions, resulting in accuracies of 92.28% and 94.08%, respectively. Compared to existing machine learning models, our model demonstrates superior performance on both datasets. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

R2V-PPI: Enhancing Prediction of Protein-Protein Interactions Using Word2Vec Embeddings and Deep Neural Networks 4

R2V-PPI: Enhancing Prediction of Protein-Protein Interaction...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Oviya, I.R. Sravya N, Shanmukha Raja, Kalpana Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science Engineering Chennai601103 India Yale University Section for Biomedical Informatics and Data Science School of Medicine New HavenCT United States

ISBN: (纸本)9798350343670

Proteins play a crucial role in living organisms, and understanding protein-protein interactions is vital for comprehending their functions and aiding drug discovery. In recent years, advanced deep learning models have been developed to predict protein-protein interactions from sequences. However, these large-scale approaches often suffer from deficiencies, resulting in both false positive and false negative predictions. Traditional encoding methods struggle to effectively represent the semantic meaning of individual residues in protein sequences and their impact on neighbouring residues. To overcome these deficiencies, we propose a novel method named R2V-PPI (Residue-to-Vector embeddings based Protein-Protein Interaction Framework) that effectively represents protein sequences and predicts protein-protein interactions. Inspired by Word2Vec, R2V-PPI learns informative representations of individual amino acid residues, capturing the context and relationships between them in raw protein sequences. These representations provide valuable input features for a downstream deep learning model. Our methodology offers a robust and versatile approach for predicting protein-protein interactions, especially when structural information is limited or unavailable. Evaluation on the S. cerevisiae dataset demonstrates that R2V-PPI outperforms existing state-of-the-art machine learning models. © 2024 IEEE.

关键词： Deep Learning Machine Learning Protein Feature Encoding Protein Protein interaction Protein sequence

来源：评论

学校读者我要写书评

暂无评论

Generative Artificial Intelligence in Clinical Medicine and Impact on Gastroenterology

引用

Gastroenterology 2025年

作者： Ali Soroush Mauro Giuffrè Sunny Chung Dennis L Shung Division of Data-Driven and Digital Medicine (D3M) Icahn School of Medicine at Mount Sinai Henry D. Janowitz Division of Gastroenterology Icahn School of Medicine at Mount Sinai Charles Bronfman Institute for Personalized Medicine Icahn School of Medicine at Mount Sinai. Section of Digestive Diseases Department of Medicine Yale School of Medicine. Section of Digestive Diseases Department of Medicine Yale School of Medicine Department of Biomedical Informatics & Data Science Yale School of Medicine. Electronic address: dennis.shung@yale.edu.

The pace of artificial intelligence (AI) integration into healthcare has accelerated with rapid advances in generative AI (GenAI). Gastroenterology and hepatology in particular will be transformed due to the multimodal workflows that integrate endoscopic video, radiologic imaging, tabular data, and unstructured note text. GenAI will impact the entire spectrum of clinical experience, from administrative tasks, diagnostic guidance and treatment recommendations. Unlike traditional machine learning approaches, GenAI is more flexible, with one platform able to be used across multiple tasks. Initial evidence suggests benefit in lower-level administrative tasks such as clinical documentation, medical billing and scheduling, and information tasks such as patient education and summarization of the medical literature. No evidence exists for GenAI solutions for more complex tasks relevant to clinical care, such as clinical reasoning for diagnostic and treatment decisions that may affect patient outcomes. Challenges of output reliability, data privacy, and useful integration remain, with potential solutions include robust validation, regulatory oversight, and "human-AI teaming" strategies to ensure safe, effective deployment. We remain optimistic in the potential of GenAI to augment clinical expertise due to the adaptability of GenAI to handle multiple data modalities to obtain and focus relevant information flows and the human-friendly interfaces that facilitate ease of use. We believe that the potential of GenAI for dynamic human-algorithmic interactions may allow for a degree of clinician-directed customization to enhance human presence.

关键词： AI Safety Gastroenterology Generative Artificial Intelligence Human-AI Collaboration

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Gastroenterology and Hepatology: Potential and Perils

引用

Gastroenterology 2025年

作者： Dennis L Shung Marietta Iacucci Section of Digestive Diseases Department of Medicine Department of Biomedical Informatics and Data Science Yale School of Medicine New Haven CT United States. Electronic address: dennis.shung@yale.edu. Microbiome Ireland College of Medicine and Health University College Cork Mercy/Cork University Hospitals Cork Ireland. Electronic address: miacucci@ucc.ie.

来源：评论

学校读者我要写书评

暂无评论

Factors Associated With Influenza Vaccination in a National Veteran Cohort

引用

AJPM Focus 2025年第1期4卷 100290-100290页

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

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

关键词： Influenza vaccination vaccination coverage vaccine hesitancy veterans

来源：评论

学校读者我要写书评

暂无评论

From Survey to Ontology, the challenges and opportunities in ontologizing questions and answers 13

From Survey to Ontology, the challenges and opportunities in...

引用

13th International Conference on biomedical Ontology, ICBO 2022

作者： Chan, Lauren Phuong, Jimmy Thessen, Anne Hong, Stephanie Essaid, Shahim Haendel, Melissa College of Public Health and Human Sciences Oregon State University CorvallisOR97331 United States Division of Biomedical Health and Informatics University of Washington Medicine SeattleWA98195 United States Department of Biomedical Informatics University of Colorado Anschutz Medical Campus AuroraCO80054 United States Section of Biomedical Informatics and Data Science Johns Hopkins University School of Medicine BaltimoreMD21218 United States

Surveys are an essential tool for gathering data from individuals in a wide variety of fields. Common data Elements (CDEs) are routinely used in surveys to streamline frequently asked questions and support question reuse. While CDEs are a widespread method for collecting survey data, they face a variety of problems including inconsistent file formats, lack of computational encoding, little to no community development standards, and frequent duplication of CDEs across various registries. Alternative approaches such as ontologies can serve as meaningful translation tools to not only support interoperability between similar/duplicate CDEs, but also to coordinate survey data with other ontology aligned data from heterogeneous methodologies including wet lab, clinical, or field research. To capitalize on the extensive data collected using CDEs, we propose a two-step approach of 1) aligning CDEs with ontology terminology to coordinate similar questions based on primary topic and 2) using standardized enumerations for CDE responses that can support data harmonization for meta analytics. Using this approach, greater data integration can support higher powered analytics and coordination of heterogeneous data types which are often difficult to study in tandem. © 2022 Copyright for this paper by its authors.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Identifying Deprescribing Opportunities With Large Language Models in Older Adults: Retrospective Cohort Study

JMIR Aging

引用

JMIR Aging 2025年 8卷 e69504页

作者： Socrates, Vimig Wright, Donald S. Huang, Thomas Fereydooni, Soraya Dien, Christine Chi, Ling Albano, Jesse Patterson, Brian Kanaparthy, Naga Sasidhar Wright, Catherine X. Loza, Andrew Chartash, David Iscoe, Mark Taylor, Richard Andrew Department of Biomedical Informatics and Data Science School of Medicine Yale University New Haven CT United States Program of Computational Biology and Bioinformatics Yale University New Haven CT United States Department of Emergency Medicine School of Medicine Yale University New Haven CT United States VA Connecticut Healthcare System US Department of Veterans Affairs West Haven CT United States Department of Pharmacy Yale New Haven Hospital New Haven CT United States BerbeeWalsh Department of Emergency Medicine University of Wisconsin–Madison Madison WI United States Section of Cardiovascular Medicine Department of Internal Medicine Yale School of Medicine New Haven CT United States School of Medicine University College Dublin Dublin Ireland Department of Biostatistics School of Public Health Yale University New Haven CT United States

Background: Polypharmacy, the concurrent use of multiple medications, is prevalent among older adults and associated with increased risks for adverse drug events including falls. Deprescribing, the systematic process of discontinuing potentially inappropriate medications, aims to mitigate these risks. However, the practical application of deprescribing criteria in emergency settings remains limited due to time constraints and criteria complexity. Objective: This study aims to evaluate the performance of a large language model (LLM)–based pipeline in identifying deprescribing opportunities for older emergency department (ED) patients with polypharmacy, using 3 different sets of criteria: Beers, Screening Tool of Older People’s Prescriptions, and Geriatric Emergency Medication Safety Recommendations. The study further evaluates LLM confidence calibration and its ability to improve recommendation performance. Methods: We conducted a retrospective cohort study of older adults presenting to an ED in a large academic medical center in the Northeast United States from January 2022 to March 2022. A random sample of 100 patients (712 total oral medications) was selected for detailed analysis. The LLM pipeline consisted of two steps: (1) filtering high-yield deprescribing criteria based on patients’ medication lists, and (2) applying these criteria using both structured and unstructured patient data to recommend deprescribing. Model performance was assessed by comparing model recommendations to those of trained medical students, with discrepancies adjudicated by board-certified ED physicians. Selective prediction, a method that allows a model to abstain from low-confidence predictions to improve overall reliability, was applied to assess the model’s confidence and decision-making thresholds. Results: The LLM was significantly more effective in identifying deprescribing criteria (positive predictive value: 0.83;negative predictive value: 0.93;McNemar test for paired proportion

关键词： calibration deprescribing emergency medicine geriatrics large language models natural language processing potentially inappropriate medication list

来源：评论

学校读者我要写书评

暂无评论

Tomato Disease Classification Using CNN 4th

Tomato Disease Classification Using CNN

引用

4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023

作者： Archanaa, N. Daniel, V. Vifert Jenuben Divya, S. Raja, Kalpana Oviya, I.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Sciences Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States

ISBN: (纸本)9789819736898

Plant disease detection using various machine learning techniques is a very popular research area. Many promising results have been obtained, but only a few specific applications can still make farmers’ lives easier. This research focuses on the important task of identifying tomato diseases at an early stage to prevent their spread and protect crop yields more broadly, emphasizing the idea that disease prevention will more important than treatment. Leveraging the capabilities of convolutional neural networks (CNN), we developed a model that diagnoses eight distinct tomato diseases using only their images. Diseases listed include bacterial spot, early blight, late blight, leaf mold, septoria leaf spot, two-spotted spider mite, target spot, and tomato yellow leaf curl virus. An integral part of our approach involves sophisticated image prepossessing and enhancement techniques, ensuring data quality and model robustness. Feature extraction plays a key role in transforming raw image data into recognizable patterns. The architecture of the CNN has been meticulously designed, consisting of multiple layers with a notable focus on the ReLU activation function and other relevant hyper-parameters. Our main dataset comes from PlantVillage, known for synthesizing rich and diverse plant images. After rigorous training and validation, the CNN model showed exceptional accuracy of 96.88% in tomato disease identification. However, challenges such as overfitting, image quality variability, and class imbalances were encountered but were resolved through strategic data augmentation, careful CNN overlay. In summary, our research presents a practical solution for farmers and agricultural entities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Mapping Study Variables to Common data Elements Using GPT for Sheets: Towards Standardized data Collection and Sharing

Mapping Study Variables to Common Data Elements Using GPT fo...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Pritham Ram Na Hong Hua Xu Xiaoqian Jiang Section of Biomedical Informatics and Data Science School of Medicine Yale University New Haven CT USA McWilliams School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston TX USA

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

Secondary use or reuse of biomedical research data has drawn significant attention and is of growing importance. Non-standardized representation and wide variability of clinical and observational data of biomedical research pose a major challenge to data collection, integration, analysis, and sharing. To address this requirement, we present experiences of using GPT for Sheets as a tool to map study-level biomedical research variables or data elements to Common data Elements (CDEs). In this study, the trial variables were extracted from the data dictionaries in the RADx-rad program, and the NIH Pediatric COVID-19 Working Group recommended CDEs that include children (0 – 21 years) were used as the reference CDEs. Mapping experimental variables (vague data elements) to CDEs resulted in an Fl-score of 0.82 when considering only the first recommendation and 0.85 when considering either the first or second recommendation. Our results indicate that GPT language models can differentiate freely defined study variables and map them to standard CDEs. This, in turn, potentially further enhances interoperability with a wider range of biomedical studies.

关键词： Pediatrics Dictionaries Biological system modeling Medical services data collection data models informatics

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：