A5079247989- Complex Network Analysis Techniques
- Mental Health via Writing
- Recommender Systems and Techniques
- Web Data Mining and Analysis
- Health Literacy and Information Accessibility
- Artificial Intelligence in Healthcare and Education
- Machine Learning in Healthcare
- Misinformation and Its Impacts
- Social Media in Health Education
- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Biomedical Text Mining and Ontologies
- Medication Adherence and Compliance
- Privacy-Preserving Technologies in Data
- Data Management and Algorithms
- Data Stream Mining Techniques
- Polynomial and algebraic computation
- Electronic Health Records Systems
- Advanced Graph Neural Networks
- Computational and Text Analysis Methods
- Statistical Methods in Clinical Trials
- Advanced Text Analysis Techniques
- Intergenerational Family Dynamics and Caregiving
- Semantic Web and Ontologies
- COVID-19 diagnosis using AI
Vanderbilt University Medical Center
2017-2025
Vanderbilt University
2015-2025
University of Illinois Urbana-Champaign
2008-2012
University of Cincinnati
2005-2012
As information networks become ubiquitous, extracting knowledge from has an important task. Both ranking and clustering can provide overall views on network data, each been a hot topic by itself. However, objects globally without considering which clusters they belong to often leads dumb results, e.g., database computer architecture conferences together may not make much sense. Similarly, huge number of (e.g., thousands authors) in one cluster distinction is dull as well.
This paper studies the problem of discovering and comparing geographical topics from GPS-associated documents. documents become popular with pervasiveness location-acquisition technologies. For example, in Flickr, geo-tagged photos are associated tags GPS locations. In Twitter, locations tweets can be identified by smart phones. Many interesting concepts, including cultures, scenes, product sales, correspond to specialized distributions. this paper, we interested two questions: (1) how...
Social tagging on online portals has become a trend now. It emerged as one of the best ways associating metadata with web objects. With increase in kinds objects becoming available, collaborative such is also developing along new dimensions. This popularity led to vast literature social tagging. In this survey paper, we would like summarize different techniques employed study various aspects Broadly, discuss about properties tag streams, models, semantics, generating recommendations using...
The phenomenal success of social networking sites, such as Facebook, Twitter and LinkedIn, has revolutionized the way people communicate. This paradigm attracted attention researchers that wish to study corresponding technological problems. Link recommendation is a critical task not only helps increase linkage inside network also improves user experience. In an effective link algorithm it essential identify factors influence creation. paper enumerates several these intuitive criteria...
With the phenomenal success of networking sites (e.g., Facebook, Twitter and LinkedIn), social networks have drawn substantial attention. On online sites, link recommendation is a critical task that not only helps improve user experience but also plays an essential role in network growth. In this paper we propose several criteria, based on both attributes graph structure. To discover candidates satisfy these relevance estimated using random walk algorithm augmented with attribute structure...
This paper studies web object classification problem with the novel exploration of social tags. Automatically classifying objects into manageable semantic categories has long been a fundamental preprocess for indexing, browsing, searching, and mining these objects. The explosive growth heterogeneous objects, especially non-textual such as products, pictures, videos, made increasingly challenging. Such often suffer from lack easy-extractable features information, interconnections between each...
This article studies the problem of latent community topic analysis in text-associated graphs. With development social media, a lot user-generated content is available with user networks. Along rich information networks, graphs can be extended text associated nodes. Topic modeling classic mining and it interesting to discover topics Different from traditional methods considering links, we incorporate discovery into guarantee topical coherence communities so that users same are closely linked...
Previous chapter Next Full AccessProceedings Proceedings of the 2011 SIAM International Conference on Data Mining (SDM)Diversified Trajectory Pattern Ranking in Geo-Tagged Social MediaZhijun Yin, Liangliang Cao, Jiawei Han, Jiebo Luo, and Thomas HuangZhijun Huangpp.980 - 991Chapter DOI:https://doi.org/10.1137/1.9781611972818.84PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract media such as those residing popular photo sharing websites is...
Background: Biomedical research has traditionally been conducted via surveys and the analysis of medical records. However, these resources are limited in their content, such that non-traditional domains (eg, online forums social media) have an opportunity to supplement view individual's health. Objective: The objective this study was develop a scalable framework detect personal health status mentions on Twitter assess extent which information is disclosed. Methods: We collected more than 250...
Artificial intelligence (AI) and machine learning (ML) technology design development continues to be rapid, despite major limitations in its current form as a practice discipline address all sociohumanitarian issues complexities. From these emerges an imperative strengthen AI ML literacy underserved communities build more diverse workforce engaged health research. has the potential account for assess variety of factors that contribute disease improve prevention, diagnosis, therapy. Here, we...
Topic modeling utilizes unsupervised machine learning to detect underlying themes within texts and has been deployed routinely analyze social media for insights into healthcare issues. However, the inherent messiness of hinders full realization this technique’s potential. As such, we hypothesized that restricting medical concepts in specific related semantic types applying topic these could be a feasible approach overcome challenge traditional texts. Therefore, developed semantic-type-based...
<sec> <title>UNSTRUCTURED</title> The role and use of race within health-related artificial intelligence machine learning (AI/ML) models has sparked increasing attention controversy. Despite the complexity breadth related issues, a robust holistic framework to guide stakeholders in their examination resolution remains lacking. This perspective provides broad-based, systematic, cross-cutting landscape analysis race-related challenges, structured around AI/ML lifecycle framed through “points...
Background: Several health conditions are known to increase the risk of Alzheimer's disease (AD). We aim systematically identify medical that associated with subsequent development AD by leveraging growing resources electronic records (EHRs). Methods: This retrospective cohort study used de-identified EHRs from two independent databases (MarketScan and VUMC) 153 million individuals cases age- gender-matched controls. By tracking their over a 10-year window before diagnosis comparing between...
The rank of a university has been widely perceived as reputation measure that is often determined based on the comprehensive overview various factors. Among factors, publication imperative and carries significant weight in almost every ranking system around globe. To reveal how may influence ranking, we investigated 2020 US News Best Global Universities Ranking results analyzed different related criteria, including discipline coverage, productivity, research impact, level interdisciplinary...
Background By the end of 2022, more than 100 million people were infected with COVID-19 in United States, and cumulative death rate rural areas (383.5/100,000) was much higher urban (280.1/100,000). As pandemic spread, used social media platforms to express their opinions concerns about COVID-19–related topics. Objective This study aimed (1) identify primary topics contiguous States communicated over Twitter (2) compare sentiments users expressed these Methods We collected tweets containing...
Online platforms have created a variety of opportunities for breast patients to discuss their hormonal therapy, long-term adjuvant treatment reduce the chance cancer occurrence and mortality. The goal this investigation is ascertain extent which messages communicated through an online portal can indicate potential discontinuing therapy.We studied de-identified electronic medical records 1106 who were prescribed therapy at Vanderbilt University Medical Center over 12-year period. We designed...
NAD(P)H:quinone oxidoreductase 1 (NQO1) is overexpressed in most solid cancers, emerging as a promising target for tumor-selective killing. β-Lapachone (β-Lap), an NQO1 bioactivatable drug, exhibits significant antitumor effects on NQO1-positive cancer cells by inducing immunogenic cell death (ICD) and enhancing tumor immunogenicity. However, the interaction between β-Lap-mediated immune responses neutrophils, novel antigen-presenting (APCs), remains unknown. This study demonstrates that...
Abstract Objectives Artificial intelligence (AI) proceeds through an iterative and evaluative process of development, use, refinement which may be characterized as a lifecycle. Within this context, stakeholders can vary in their interests perceptions the ethical issues associated with rapidly evolving technology ways that fail to identify avert adverse outcomes. Identifying throughout AI lifecycle systematic manner facilitate better-informed deliberation. Materials Methods We analyzed...