- Topic Modeling
- Biomedical Text Mining and Ontologies
- Data Visualization and Analytics
- Advanced Text Analysis Techniques
- Data Quality and Management
- Semantic Web and Ontologies
- Breast Lesions and Carcinomas
- scientometrics and bibliometrics research
- Data-Driven Disease Surveillance
- Breast Cancer Treatment Studies
- Research Data Management Practices
- Big Data and Business Intelligence
- Library Science and Information Systems
- Misinformation and Its Impacts
- Distributed and Parallel Computing Systems
- Pain Mechanisms and Treatments
- Academic Publishing and Open Access
- Data Mining Algorithms and Applications
- Family and Patient Care in Intensive Care Units
- Pain Management and Opioid Use
- Innovative Human-Technology Interaction
- Grief, Bereavement, and Mental Health
- Big Data Technologies and Applications
- Museums and Cultural Heritage
- Aesthetic Perception and Analysis
OurResearch
2023
University of Washington
2015-2022
Allen Institute for Artificial Intelligence
2020
Beth Israel Deaconess Medical Center
2012
Mount Sinai Beth Israel
2008-2011
John Brown University
2007
To evaluate the prevalence, characteristics, and correlates of chronic pain in a population predominantly employed, alcoholic patients attending an outpatient drug alcohol treatment program.A survey was administered to 79 program situated suburban community outside New York City. Chronic severe defined as that 1) had persisted for at least 6 months; 2) either moderate intensity or significantly interfered with daily activities.Seventy-six percent experienced during past week. by 29.1%...
Isolated silos of scientific research and the growing challenge information overload limit awareness across literature hinder innovation. Algorithmic curation recommendation, which often prioritize relevance, can further reinforce these informational "filter bubbles." In response, we describe Bridger, a system for facilitating discovery scholars their work. We construct faceted representation authors with gleaned from papers inferred author personas, use it to develop an approach that...
Abstract Journals play a critical role in the scientific process because they evaluate quality of incoming papers and offer an organizing filter for search. However, journals has been called into question new preprint archives academic search engines make it easier to find articles independent that publish them. Research on this issue is complicated by deeply confounded relationship between article journal reputation. We present innovative proxy individual divorced from journal's reputation...
Background . DCIS treated by mastectomy ensures high local control rates. There is limited data on risk for relapse and lack of clear indication adjuvant radiation therapy (RT). We report a retrospective review population patients with mastectomy. The objective was to identify the overall incidence relapse, factors recurrence, accordingly whom postmastectomy RT may be considered. Methods This an IRB-approved study prospective breast cancer database. From 1997 2007, we identified 969...
Tom Hope, Jason Portenoy, Kishore Vasan, Jonathan Borchardt, Eric Horvitz, Daniel Weld, Marti Hearst, Jevin West. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2020.
Abstract The COVID-19 pandemic has sparked unprecedented mobilization of scientists, generating a deluge papers that makes it hard for researchers to keep track and explore new directions. Search engines are designed targeted queries, not discovery connections across corpus. In this paper, we present SciSight, system exploratory search research integrating two key capabilities: first, exploring associations between biomedical facets automatically extracted from (e.g., genes, drugs, diseases,...
Assessing the influence of a scholar's work is an important task for funding organizations, academic departments, and researchers. Common methods, such as measures citation counts, can ignore much nuance multidimensionality scholarly influence. We present approach generating dynamic visualizations scholars' careers. This uses animated node-link diagram showing network accumulated around researcher over course career in concert with key indicators, highlighting both within across fields....
Scopus and the Web of Science have been foundation for research in science even though these traditional databases systematically underrepresent certain disciplines world regions. In response, new inclusive databases, notably OpenAlex, emerged. While many studies begun using OpenAlex as a data source, few critically assess its limitations. This study, conducted collaboration with team, addresses this gap by comparing to across number dimensions. The analysis concludes that is superset can be...
With data on scholarly publications becoming more abundant and accessible, there exist new opportunities for using this information to provide rich author profiles display explore work. We present a pair of linked visualizations connected the Microsoft Academic Graph that can be used citations individual authors. an online application with which user manage collections papers generate these visualizations.
The Big Data movement is sweeping across all sectors in society including museums. These organizations are being encouraged to explore new ways generate, track, link, and analyze data better understand their visitors refine business practices. While tapping into Data's potential seems promising for museums, little known about how museum professionals -- that is, those who responsible building the museum-to-Big-Data bridge speak of this trend context work. To begin address problem, we...
93 Background: The efficacy of accelerated radiation therapy (RT) for treating early stage invasive breast cancer has been established (Whelan T et al: NEJM, February 2010). But the role schedules in patients with DCIS still needs to be defined. We have previously described feasibility and low toxicity when using ARTB after lumpectomy (Chadha M Int J Radiat Oncol Biol Phys 2007; 69). objective this study is evaluate outcomes treated ARTB, compare local recurrence rates conventional fraction...
The COVID-19 pandemic has sparked unprecedented mobilization of scientists, generating a deluge papers that makes it hard for researchers to keep track and explore new directions. Search engines are designed targeted queries, not discovery connections across corpus. In this paper, we present SciSight, system exploratory search research integrating two key capabilities: first, exploring associations between biomedical facets automatically extracted from (e.g., genes, drugs, diseases, patient...
Isolated silos of scientific research and the growing challenge information overload limit awareness across literature hinder innovation. Algorithmic curation recommendation, which often prioritize relevance, can further reinforce these informational "filter bubbles." In response, we describe Bridger, a system for facilitating discovery scholars their work. We construct faceted representation authors with gleaned from papers inferred author personas, use it to develop an approach that...