检索结果-内蒙古大学图书馆

An Urban Population Health Observatory for Disease Causal Pathway Analysis and Decision Support: Underlying Explainable Artificial Intelligence Model

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Brakefield, Whitney S. Ammar, Nariman Shaban-Nejad, Arash Center for Biomedical Informatics Department of Pediatrics College of Medicine University of Tennessee Health Science Center MemphisTN United States Bredesen Center for Data Science University of Tennessee KnoxvilleTN United States Ochsner Xavier Institute for Health Equity and Research Ochsner Clinic Foundation New OrleansLA United States

Background: Many researchers have aimed to develop chronic health surveillance systems to assist in public health decision-making. Several digital health solutions created lack the ability to explain their decisions and actions to human users. Objective: This study sought to (1) expand our existing Urban Population Health Observatory (UPHO) system by incorporating a semantics layer;(2) cohesively employ machine learning and semantic/logical inference to provide measurable evidence and detect pathways leading to undesirable health outcomes;(3) provide clinical use case scenarios and design case studies to identify socioenvironmental determinants of health associated with the prevalence of obesity, and (4) design a dashboard that demonstrates the use of UPHO in the context of obesity surveillance using the provided scenarios. Methods: The system design includes a knowledge graph generation component that provides contextual knowledge from relevant domains of interest. This system leverages semantics using concepts, properties, and axioms from existing ontologies. In addition, we used the publicly available US Centers for Disease Control and Prevention 500 Cities data set to perform multivariate analysis. A cohesive approach that employs machine learning and semantic/logical inference reveals pathways leading to diseases. Results: In this study, we present 2 clinical case scenarios and a proof-of-concept prototype design of a dashboard that provides warnings, recommendations, and explanations and demonstrates the use of UPHO in the context of obesity surveillance, treatment, and prevention. While exploring the case scenarios using a support vector regression machine learning model, we found that poverty, lack of physical activity, education, and unemployment were the most important predictive variables that contribute to obesity in Memphis, TN. Conclusions: The application of UPHO could help reduce health disparities and improve urban population health. The expanded UP

关键词： Semantics

Optimizing Logistics in E-Commerce Using Deep Random Forest for Enhanced User Satisfaction 3

学校读者我要写书评

暂无评论

Optimizing Logistics in E-Commerce Using Deep Random Forest ...

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Nisha, G.Anne Sreetha, P. Seetha, A. Manickam, K. Jagannathan, Sharath Kumar Sekar, S.D. Kyoto Computer Gakuin Department of Informatics Kyoto Japan Kpr Institute of Engineering and Technology Department of Biomedical Engineering Tamil Nadu India S. A. Engineering College Department of Information Technology Thiruverkadu Chennai India Sona College of Technology Department of Mathematics Tamil Nadu India Data Science Institute Saint Peter's University NJ United States R.M.K.Engineering College Department of Mechanical Engineering TamilNadu Chennai India

ISBN: (纸本)9798331542375

Operational efficiency is one of the most important factors affecting customer satisfaction directly in e-commerce. Still, constant addressing of timely delivery, path simplification, and reduction of delays remains challenging problems. Deep Random Forest (DRF) is a new approach presented in this work to examine and forecast significant logistics metrics including delivery times and satisfaction scores. Development of this approach targeted to solve these issues. The model makes use of e-commerce past performance including order volumes, customer comments, and delivery times. Findings: The suggested approach achieves 10% increase in user satisfaction, 12% cost reduction, and 15% faster delivery times than baseline methods. This is accomplished by means of DRF, applied to examine trends and carry out predictive modifications. Results and Methodology: These results outperform those of the benchmarks established by Gradient Boosting and XGBoost, which displayed respective rises in satisfaction of 9% and 8%. Apart from improving the quality of service, the use of DRF not only strengthened user loyalty but also contributed to improve the transportation efficiency. This approach exposes the transforming opportunities of artificial intelligence in logistics management for e-commerce systems. This approach guarantees operations with a customer-centric concentration benefiting from measurable advantages. © 2025 IEEE.

关键词： Marketplaces

From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations 21

学校读者我要写书评

暂无评论

From reflection to action: Combining machine learning with e...

2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021

作者： Mitchell, Elliot G. Heitkemper, Elizabeth M. Burgermaster, Marissa Levine, Matthew E. Miao, Yishen Hwang, Maria L. Desai, Pooja M. Cassells, Andrea Tobin, Jonathan N. Tabak, Esteban G. Albers, David J. Smaldone, Arlene M. Mamykina, Lena Department of Biomedical Informatics Columbia University United States School of Nursing The University of Texas at Austin United States Department of Population Health Dell Medical School and Department of Nutritional Sciences The University of Texas at Austin United States Department of Computing and Mathematical Sciences California Institute of Technology United States Department of Molecular Cellular and Developmental Biology University of California Santa Barbara United States Department of Science and Math Fashion Institute of Technology United States United States and The Rockefeller University United States Courant Institute of Mathematical Sciences United States University of Colorado Anschutz Medical Campus Section of Informatics and Data Science United States Departments of Pediatrics Biomedical Engineering and Biostatistics and Informatics United States School of Nursing Columbia University United States

ISBN: (纸本)9781450380966

Self-tracking can help personalize self-management interventionsfor chronic conditions like type 2 diabetes (T2D), but refecting onpersonal data requires motivation and literacy. Machine learning(ML) methods can identify patterns, but a key challenge is making actionable suggestions based on personal health *** introduce GlucoGoalie, which combines ML with an expert system to trans-late ML output into personalized nutrition goal suggestions forindividuals with T2D. In a controlled experiment, participants with T2D found that goal suggestions were understandable and action-able. A 4-week in-the-wild deployment study showed that receiving goal suggestions augmented participants' self-discovery, choosing goals highlighted the multifaceted nature of personal preferences, and the experience of following goals demonstrated the importance of feedback and context. However, we identifed tensions between abstract goals and concrete eating experiences and found static text too ambiguous for complex concepts. We discuss implications for ML-based interventions and the need for systems that ofer more interactivity, feedback, and negotiation. © 2021 ACM.

关键词： Feedback

Enhancing drug and cell line representations via contrastive learning for improved anti-cancer drug prioritization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lawrence, Patrick J. Ning, Xia Biomedical Informatics Department The Ohio State University 1800 Cannon Drive Lincoln Tower 250 ColumbusOH43210 United States Computer Science and Engineering Department The Ohio State University 2015 Neil Avenue ColumbusOH43210 United States Translational Data Analytics Institute The Ohio State University 1760 Neil Avenue ColumbusOH43210 United States

Due to cancer’s complex nature and variable response to therapy, precision oncology informed by omics sequence analysis has become the current standard of care. However, the amount of data produced for each patients makes it difficult to quickly identify the best treatment regimen. Moreover, limited data availability has hindered computational methods’ abilities to learn patterns associated with effective drug-cell line pairs. In this work, we propose the use of contrastive learning to improve learned drug and cell line representations by preserving relationship structures associated with drug mechanism of action and cell line cancer types. In addition to achieving enhanced performance relative to a state-of-the-art method, we find that classifiers using our learned representations exhibit a more balances reliance on drug- and cell line-derived features when making predictions. This facilitates more personalized drug prioritizations that are informed by signals related to drug resistance. © 2023, CC BY.

关键词： Cell culture

Neural Approximation of Graph Topological Features

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yan, Zuoyu Ma, Tengfei Gao, Liangcai Tang, Zhi Wang, Yusu Chen, Chao Wangxuan Institute of Computer Technology Peking University China IBM T. J. Watson Research Center United States Halıcıoglu Data Science Institute University of California United States Department of Biomedical Informatics Stony Brook University United States

Topological features based on persistent homology can capture high-order structural information which can then be used to augment graph neural network methods. However, computing extended persistent homology summaries remains slow for large and dense graphs and can be a serious bottleneck for the learning pipeline. Inspired by recent success in neural algorithmic reasoning, we propose a novel graph neural network to estimate extended persistence diagrams (EPDs) on graphs efficiently. Our model is built on algorithmic insights, and benefits from better supervision and closer alignment with the EPD computation algorithm. We validate our method with convincing empirical results on approximating EPDs and downstream graph representation learning tasks. Our method is also efficient;on large and dense graphs, we accelerate the computation by nearly 100 times. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

Generative AI in Health Economics and Outcomes Research: A Taxonomy of Key Definitions and Emerging Applications – an ISPOR Working Group Report

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fleurence, Rachael L. Wang, Xiaoyan Bian, Jiang Higashi, Mitchell K. Ayer, Turgay Xu, Hua Dawoud, Dalia Chhatwal, Jagpreet Office of the Director National Institutes of Health National Institute of Biomedical Imaging and Bioengineering BethesdaMD United States Tulane University School of Public Health and Tropical Medicine New OrleansLA United States Intelligent Medical Objects RosemontIL United States College of Medicine University of Florida FL United States Biomedical Informatics Clinical and Translational Science Institute University of Florida FL United States Office of Data Science and Research Implementation University of Florida Health GainesvilleFL United States ISPOR The Professional Society for Health Economics and Outcomes Research LawrencevilleNJ United States Center for Health & Humanitarian Systems Georgia Institute of Technology AtlantaGA United States Value Analytics Labs BostonMA United States Institute Department of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States National Institute for Health and Care Excellence London United Kingdom Cairo University Faculty of Pharmacy Cairo Egypt Institute for Technology Assessment Massachusetts General Hospital Harvard Medical School BostonMA United States Center for Health Decision Science Harvard University BostonMA United States

Objective: This article offers a taxonomy of generative artificial intelligence (AI) for health economics and outcomes research (HEOR), explores its emerging applications, and outlines methods to enhance the accuracy and reliability of AI-generated outputs. Methods: The review defines foundational generative AI concepts and highlights current HEOR applications, including systematic literature reviews, health economic modeling, real-world evidence generation, and dossier development. Approaches such as prompt engineering (zero-shot, few-shot, chain-of-thought, persona pattern prompting), retrieval-augmented generation, model fine-tuning, and the use of domain-specific models are introduced to improve AI accuracy and reliability. Results: Generative AI shows significant potential in HEOR, enhancing efficiency, productivity, and offering novel solutions to complex challenges. Foundation models are promising in automating complex tasks, though challenges remain in scientific reliability, bias, interpretability, and workflow integration. The article discusses strategies to improve the accuracy of these AI tools. Conclusion: Generative AI could transform HEOR by increasing efficiency and accuracy across various applications. However, its full potential can only be realized by building HEOR expertise and addressing the limitations of current AI technologies. As AI evolves, ongoing research and innovation will shape its future role in the field. © 2024, CC BY.

关键词： Generative adversarial networks

Moving From PQRST to AI: Advancing Transparency, Reliability, and Clinical Translation in ECG Deep Learning

学校读者我要写书评

暂无评论

JACC: Advances

JACC: Advances 2023年第10期2卷 100682-100682页

作者： Haggerty, Christopher M. Poterucha, Timothy J. IT Data Science NewYork-Presbyterian Hospital New York NY United States Department of Biomedical Informatics Columbia University New York NY United States Seymour Paul and Gloria Milstein Division of Cardiology Department of Medicine Columbia University Irving Medical Center and NewYork-Presbyterian Hospital New York NY United States

Corresponding author

关键词： artificial intelligence deep learning electrocardiography (ECG) neural networks risk prediction

Resource Utilization in Adolescent and Adult Cardiomyopathy and Heart Failure

学校读者我要写书评

暂无评论

The Journal of Heart and Lung Transplantation 2025年第4期44卷 S637-S637页

作者： A.B. Ludomirsky W. Russell K. Lin M. O'Connor C. Wittlieb-Weber H. Ahmed N. Reza T. Bittermann A. Dewitt H. Griffis X. Zhang Y. Huang J. Rossano J. Edelson Department of Pediatrics Children's Hospital of Philadelphia Philadelphia PA Department of Internal Medicine Hospital of the University of Pennsylvania Philadelphia PA Department of Anesthesiology and Critical Care Medicine Children's Hospital of Philadelphia Philadelphia PA Department of Biomedical Health Informatics Data Science and Biostatistics Unit University of Pennsylvania Philadelphia PA Department of Biomedical Health Informatics Data Science and Biostatistics Unit Children's Hospital of Philadelphia Philadelphia PA

Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic data Generation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lopez, Ivan Haredasht, Fateme Nateghi Caoili, Kaitlin Chen, Jonathan H. Chaudhari, Akshay Stanford University School of Medicine StanfordCA United States Department of Biomedical Data Science StanfordCA United States Center for Biomedical Informatics Research StanfordCA United States The Ohio State University College of Medicine ColumbusOH United States Division of Hospital Medicine Stanford University School of Medicine StanfordCA United States Clinical Excellence Research Center Stanford School of Medicine StanfordCA United States Department of Medicine StanfordCA United States Department of Radiology StanfordCA United States Cardiovascular Institute StanfordCA United States

Accurate classification of clinical text often requires fine-tuning pre-trained language models, a process that is costly and time-consuming due to the need for high-quality data and expert annotators. Synthetic data generation offers an alternative, though pre-trained models may not capture the syntactic diversity of clinical notes. We propose an embedding-driven approach that uses diversity sampling from a small set of real clinical notes to guide large language models in few-shot prompting, generating synthetic text that better reflects clinical syntax. We evaluated this method using the CheXpert dataset on a classification task, comparing it to random few-shot and zero-shot approaches. Using cosine similarity and a Turing test, our approach produced synthetic notes that more closely align with real clinical text. Our pipeline reduced the data needed to reach the 0.85 AUC cutoff by 40% for AUROC and 30% for AUPRC, while augmenting models with synthetic data improved AUROC by 57% and AUPRC by 68%. Additionally, our synthetic data was 0.9 times as effective as real data, a 60% improvement in value. © 2025, CC BY.

关键词： data assimilation