检索结果-内蒙古大学图书馆

Proceedings of the 17th ACM Web science Conference 2025

作者： Chau Tong School of Journalism University of Missouri Columbia USA and MU Institute for Data Science & Informatics University of Missouri Columbia USA

ISBN: (纸本)9798400714832

Research on search engine algorithmic curation has primarily focused on source diversity in response to general search terms, often overlooking the role of biased user input and its interaction with algorithmic filtering. Given that online users frequently engage in motivated information-seeking, it is crucial to examine how query variation influences search results and potentially reinforces information inequalities. This study employs a user-centered auditing approach through three real-world instances, where self-identified political partisans in the United States conducted Google searches using ideologically slanted queries related to the 2020 U.S. presidential election, abortion, and climate change. Analyzing search results across three topics and timepoints, the study finds that query slant—rather than user ideology—was the primary driver of search result differences. While personalization was observed, search results also exhibited a mainstreaming effect, often surfacing authoritative sources that may counteract polarization. However, slanted queries still led to distinct sets of information, raising concerns about algorithmic amplification of biased search behaviors. These findings contribute to the literature on algorithmic curation and information diversity, highlighting the need for ongoing audits of search engines to assess their role in shaping online political discourse and mitigating information inequalities in an era of heightened polarization.

关键词： Google Search

来源：评论

学校读者我要写书评

暂无评论

Leveraging Language Models for Automated Patient Record Linkage

arXiv

引用

arXiv 2025年

作者： Beheshti, Mohammad Gondara, Lovedeep Zachary, Iris Missouri Cancer Registry and Research Center Department of Public Health College of Health Sciences University of Missouri ColumbiaMO United States MU Institute for Data Science and Informatics University of Missouri ColumbiaMO United States Provincial Health Services Authority Vancouver Canada School of Population and Public Health University of British Columbia Vancouver Canada

Objective: Healthcare data fragmentation presents a major challenge for linking patient data, necessitating robust record linkage to integrate patient records from diverse sources. This study investigates the feasibility of leveraging language models for automated patient record linkage, focusing on two key tasks: blocking and matching. Materials and Methods: We utilized real-world healthcare data from the Missouri Cancer Registry and Research Center, linking patient records from two independent sources using probabilistic linkage as a baseline. A transformer-based model, RoBERTa, was fine-tuned for blocking using sentence embeddings. For matching, several language models were experimented under fine-tuned and zero-shot settings, assessing their performance against ground truth labels. Results: The fine-tuned blocking model achieved a 92% reduction in the number of candidate pairs while maintaining near-perfect recall. In the matching task, fine-tuned Mistral-7B achieved the best performance with only 6 incorrect predictions. Among zero-shot models, Mistral-Small-24B performed best, with a total of 55 incorrect predictions. Discussion: Fine-tuned language models achieved strong performance in patient record blocking and matching with minimal errors. However, they remain less accurate and efficient than a hybrid rule-based and probabilistic approach for blocking. Additionally, reasoning models like DeepSeek-R1 are impractical for large-scale record linkage due to high computational costs. Conclusion: This study highlights the potential of language models for automating patient record linkage, offering improved efficiency by eliminating the manual efforts required to perform patient record linkage. Overall, language models offer a scalable solution that can enhance data integration, reduce manual effort, and support disease surveillance and research. © 2025, CC BY-NC-ND.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Predicting Survivability of Cancer Patients with Metastatic Patterns Using Explainable AI

arXiv

引用

arXiv 2025年

作者： Nalela, Polycarp Rao, Deepthi Rao, Praveen Institute for Data Science and Informatics University of Missouri 22 Heinkel Building ColumbiaMO65201 United States Electrical Engineering and Computer Science University of Missouri 225 Naka Hall ColumbiaMO65201 United States Pathology and Anatomical Sciences MU University Hospital 1 Hospital Dr ColumbiaMO65201 United States

Cancer remains a leading global health challenge and a major cause of mortality. This study leverages machine learning (ML) to predict the survivability of cancer patients with metastatic patterns using the comprehensive MSK-MET dataset, which includes genomic and clinical data from 25,775 patients across 27 cancer types. We evaluated five ML models-XGBoost, Naïve Bayes, Decision Tree, Logistic Regression, and Random Fores using hyperparameter tuning and grid search. XGBoost emerged as the best performer with an area under the curve (AUC) of 0.82. To enhance model interpretability, SHapley Additive exPlanations (SHAP) were applied, revealing key predictors such as metastatic site count, tumor mutation burden, fraction of genome altered, and organ-specific metastases. Further survival analysis using Kaplan-Meier curves, Cox Proportional Hazards models, and XGBoost Survival Analysis identified significant predictors of patient outcomes, offering actionable insights for clinicians. These findings could aid in personalized prognosis and treatment planning, ultimately improving patient care. © 2025, CC BY.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Digital Methodology for Mobile Clinical Decision Support Development in Long-Term Care 18

Digital Methodology for Mobile Clinical Decision Support Dev...

引用

18th World Congress on Medical and Health informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021

作者： Gallimore, Malaika R. Howland, Chelsea Chase, Jo-Ana D. Grimsley, Amy Emezue, Chuka Boles, Katrina Anbari, Allison B. Sherwin, LeeAnne B. Vogelsmeier, Amy Popejoy, Lori Rantz, Marilyn J. Reeder, Blaine Sinclair School of Nursing University of Missouri ColumbiaMO United States Mu Institute for Data Science and Informatics University of Missouri ColumbiaMO United States

ISBN: (纸本)9781643682648

The global COVID-19 pandemic has driven innovations in methods to sustain initiatives for the design, development, evaluation, and implementation of clinical support technology in long-term care settings while removing risk of infection for residents, family members, health care workers, researchers and technical professionals. We adapted traditional design and evaluation methodology for a mobile clinical decision support app-designated Mobile Application Information System for Integrated Evidence ('MAISIE')-to a completely digital design methodology that removes in-person contacts between the research team, developer, and nursing home staff and residents. We have successfully maintained project continuity for MAISIE app development with only minor challenges while working remotely. This digital design methodology can be implemented in projects where software can be installed without in-person technical support and remote work is feasible. Team skills, experience, and relationships are key considerations for adapting to digital environments and maintaining project momentum. © 2022 International Medical informatics Association (IMIA) and IOS Press.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Remote Usability Testing to Facilitate the Continuation of Research 18

Remote Usability Testing to Facilitate the Continuation of R...

引用

18th World Congress on Medical and Health informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021

作者： Sherwin, LeeAnne B. Yevu-Johnson, Justina Matteson-Kome, Michelle Bechtold, Mathew Reeder, Blaine Sinclair School of Nursing University of Missouri ColumbiaMO United States Department of Gastroenterology Mu Health Care ColumbiaMO United States Mu Institute for Data Science and Informatics University of Missouri ColumbiaMO United States

ISBN: (纸本)9781643682648

Usability testing has historically been an in-person activity where test participants and evaluation researchers are co-located. Recruiting participants into usability studies can be a challenging endeavor especially when potential participants are concerned about time commitments and social distancing. The global COVID-19 pandemic has driven the development of remote usability testing methods. In this paper, we describe remote usability testing as it evolved during a pre-pandemic research study. We adapted our in-person usability evaluation methodology for a commercially available mHealth app to a remote usability testing methodology to accommodate potential participants during a more convenient participant-identified time. In doing so we met the needs, preferences, and availability of our participants and maintained research progress. Adapting to patient-centered needs through remote usability testing has the potential to facilitate continued research and engage potential participants due to its convenience, flexibility, and decrease constraints presented by geographic limits. © 2022 International Medical informatics Association (IMIA) and IOS Press.

关键词： Testing

来源：评论

学校读者我要写书评

暂无评论

Who Influences Cancer Conversations on Twitter?: A Comparative Surveillance of Cancer Communications 18

Who Influences Cancer Conversations on Twitter?: A Comparati...

引用

18th World Congress on Medical and Health informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021

作者： Jain, Nishant Zachary, Iris Boren, Suzanne Mu Institute of Data Science and Informatics University of Missouri ColumbiaMO United States Department of Health Management and Informatics University of Missouri ColumbiaMO United States Missouri Cancer Registry & Research Center University of Missouri ColumbiaMO United States

ISBN: (纸本)9781643682648

In this study, we used social network analysis to compare the Twitter social networks of top five cancers in the United States (as ranked by the CDC) to determine the key influencers in cancer-related conversations. We find that organizations and groups geared toward patients that provide patient support, promote cancer awareness, cancer prevention and cancer management comprised up to 40% of influencers. Researchers (24%) and physicians (14%) were also found to be influential participants;the extent of influence varying by each cancer, being as high as 40% research influence for colorectal cancer. Notably, scientific organizations (JAMA, CDC_cancer, AACR) played a key role in conversations about colorectal cancer whereas patient-focused organizations played a greater influencing role in conversations about prostate cancer and skin cancer. This study shows that Twitter data can be a valuable source of cancer surveillance data, and has potential to influence policies, strategies, and research directions around each cancer. © 2022 International Medical informatics Association (IMIA) and IOS Press.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

IRnet: Immunotherapy response prediction using pathway knowledge-informed graph neural network

引用

Journal of Advanced Research 2024年 72卷 319-331页

作者： Jiang, Yuexu Immadi, Manish Sridhar Wang, Duolin Zeng, Shuai On Chan, Yen Zhou, Jing Xu, Dong Joshi, Trupti Department of Electrical Engineering and Computer Science University of Missouri-Columbia Columbia MO United States Christopher S. Bond Life Sciences Center University of Missouri-Columbia Columbia MO United States MU Institute for Data Science and Informatics University of Missouri-Columbia Columbia MO United States Department of Surgery University of Missouri-Columbia Columbia MO United States Department of Biomedical Informatics Biostatistics and Medical Epidemiology University of Missouri-Columbia Columbia MO United States

Introduction: Immune checkpoint inhibitors (ICIs) are potent and precise therapies for various cancer types, significantly improving survival rates in patients who respond positively to them. However, only a minority of patients benefit from ICI treatments. Objectives: Identifying ICI responders before treatment could greatly conserve medical resources, minimize potential drug side effects, and expedite the search for alternative therapies. Our goal is to introduce a novel deep-learning method to predict ICI treatment responses in cancer patients. Methods: The proposed deep-learning framework leverages graph neural network and biological pathway knowledge. We trained and tested our method using ICI-treated patients’ data from several clinical trials covering melanoma, gastric cancer, and bladder cancer. Results: Our results demonstrate that this predictive model outperforms current state-of-the-art methods and tumor microenvironment-based predictors. Additionally, the model quantifies the importance of pathways, pathway interactions, and genes in its predictions. A web server for IRnet has been developed and deployed, providing broad accessibility to users at https://***. Conclusion: IRnet is a competitive tool for predicting patient responses to immunotherapy, specifically ICIs. Its interpretability also offers valuable insights into the mechanisms underlying ICI treatments. © 2024

关键词： Biological pathway Checkpoint inhibitors Graph neural network Immunotherapy response Machine learning Model interpretability

来源：评论

学校读者我要写书评

暂无评论

Technical Function Evaluation of Two Smart Wearables and data Analysis Methods for Step Counts

SSRN

引用

SSRN 2022年

作者： Boles, Katrina K. Gallimore, Malaika R. Howland, Chelsea Emezue, Chuka Reeder, Blaine MU Institute for Data Science & Informatics University of Missouri ColumbiaMO United States Sinclair School of Nursing University of Missouri ColumbiaMO United States

Background and Objective: The use of smart wearable technologies to study physical activity for health interventions and wellness research shows great promise. However, most commercial devices are not tested against a 'gold standard' before market release and no standard methodology exists for analyzing step count data captured by these devices. Our objective is to describe data analytic method selection and application during a smart watch technical function evaluation ***: We completed a technical function evaluation of two consumer-grade devices (Fitbit Versa 3 and generation 2 Oura Ring) against research-grade gold standard ActiGraph devices (wGT3X-BT and GT9X-Link) and reviewed prior wearable device studies to identify methods for data analysis. We determined that only analysis methods comparing devices in matched pairs with non-normal distribution would be considered due to the variability in step counts among individual evaluators. Identified methods included: Spearman’s Rho, Mean Absolute Percent Error (MAPE), and Bland-Altman ***: After comparing methods, we also calculated Median Absolute Percent Difference (MdAPD) because it uses matched pairs, has a distinct scale from 0 to 200, assumes neither device is exact, and the median is less susceptible to skewed data. Analysis of daily step count data showed high correlation among all devices, with the highest between the Fitbit Versa 3 and Oura Ring (rho = 0.88, pConclusions: Smart wearable devices that capture physical activity data are increasingly used for health research. However, these devices must be tested to understand their function before use in research and there are few standards for the analysis of step counts. We compared data analysis methods to select ones that fit the needs of our study of evaluating smart wearable physical activity data. We recommend the development of standards and guidance for data analysis for wearable devices in research and suggest inclusion of MdAPD

关键词： Function evaluation

来源：评论

学校读者我要写书评

暂无评论

Identifying patient-specific flow of signal transduction perturbed by multiple single-nucleotide alterations

引用

Quantitative Biology 2020年第4期8卷 336-346页

作者： Olha Kholod Chi-Ren Shyu Jonathan Mitchem Jussuf Kaifi Dmitriy Shin MU Institute for Data Science and Informatics University of MissouriColumbiaMO 65201USA Department Pathology and Anatomical Sciences School of MedicineUniversity of MissouriColumbiaMO 65212USA Department of Surgery School of MedicineUniversity of MissouriColumbiaMO 65212USA Harry S.Truman Memorial Veterans'Hospital ColumbiaMO 65201USA Department of Electrical Engineering&Computer Science University of MissouriColumbiaMO 65212USA

Background:Identifying patient-specific flow of signal transduction perturbed by multiple single-nucleotide alterations is critical for improving patient outcomes in cancer ***,accurate estimation of mutational effects at the pathway level for such patients remains an open *** probabilistic pathway topology methods are gaining interest among the scientific community,the overwhelming majority do not account for network perturbation effects from multiple single-nucleotide ***:Here we present an improvement of the mutational forks formalism to infer the patient-specific flow of signal transduction based on multiple single-nucleotide alterations,including non-synonymous and synonymous *** lung adenocarcinoma and skin cutaneous melanoma datasets from TCGA Pan-Cancer Atlas have been employed to show the utility of the proposed ***:We have comprehensively characterized six mutational *** number of mutated nodes ranged from one to four depending on the topological characteristics of a *** confidences(TCs)have been computed for every possible combination of single-nucleotide alterations in the *** performed analysis demonstrated the capacity of the mutational forks formalism to follow a biologically explainable logic in the identification of high-likelihood signaling routes in lung adenocarcinoma and skin cutaneous melanoma *** findings have been largely supported by the evidence from the biomedical ***:We conclude that the formalism has a great chance to enable an assessment of patient-specific flow by leveraging information from multiple single-nucleotide alterations to adjust the transitional likelihoods that are solely based on the canonical view of a disease.

关键词： mutational forks signaling pathways cancer single-nucleotide alterations

来源：评论

学校读者我要写书评

暂无评论

Designing a Cloud-Based System for Affordable Cyberinfrastructure to Support Software-Based Research 18

Designing a Cloud-Based System for Affordable Cyberinfrastru...

引用

18th World Congress on Medical and Health informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021

作者： Anderson, Blake Cameron, Jason Jefferson, Urmeka Reeder, Blaine Hekademeia Research Solutions 2601 Northridge Dr. ColumbiaMO65202 United States College of Nursing Rush University ChicagoIL United States Sinclair School of Nursing University of Missouri ColumbiaMO United States Mu Institute for Data Science and Informatics University of Missouri ColumbiaMO United States

ISBN: (纸本)9781643682648

Interest in cloud-based cyberinfrastructure among higher-education institutions is growing rapidly, driven by needs to realize cost savings and access enhanced computing resources. Through a nonprofit entity, we have created a platform that provides hosting and software support services enabling researchers to responsibly build on cloud technologies. However, there are technical, logistic, and administrative challenges if this platform is to support all types of research. Software-enhanced research is distinctly different from industry applications, typically characterized by needs for lower reduced availability, greater flexibility, and fewer resources for upkeep costs. We describe a swarm environment specifically designed for research in academic settings and our experience developing an operating model for sustainable cyberinfrastructure. We also present three case studies illustrating the types of applications supported by the cyberinfrastructure and explore techniques that address specific application needs. Our findings demonstrate safer, faster, cheaper cloud services by recognizing the intrinsic properties of academic research environments. © 2022 International Medical informatics Association (IMIA) and IOS Press.

关键词： Application programs

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：