A5044068445- Topic Modeling
- Biomedical Text Mining and Ontologies
- Natural Language Processing Techniques
- Image Retrieval and Classification Techniques
- Machine Learning in Healthcare
- Neurobiology of Language and Bilingualism
- Text Readability and Simplification
- Speech Recognition and Synthesis
- Advanced Image and Video Retrieval Techniques
- Autism Spectrum Disorder Research
- Radiomics and Machine Learning in Medical Imaging
- Data Quality and Management
- EEG and Brain-Computer Interfaces
- Electronic Health Records Systems
- Language Development and Disorders
- Colorectal Cancer Screening and Detection
- Speech and dialogue systems
- Artificial Intelligence in Healthcare and Education
- Semantic Web and Ontologies
- Gaze Tracking and Assistive Technology
- Heme Oxygenase-1 and Carbon Monoxide
- Folate and B Vitamins Research
- Porphyrin Metabolism and Disorders
- Multimodal Machine Learning Applications
- AI in cancer detection
Oregon Health & Science University
2016-2025
Google (United States)
2022-2023
Harvard University
2022
University of Southern California
2022
Ellipsis
2022
Johns Hopkins University
2022
University of Edinburgh
2021
University of Colorado System
2021
Bar-Ilan University
2021
University of Helsinki
2021
TREC-COVID is an information retrieval (IR) shared task initiated to support clinicians and clinical research during the COVID-19 pandemic. IR for pandemics breaks many normal assumptions, which can be seen by examining 9 important basic questions related pandemic situations. differs from traditional evaluations with special considerations expected users, modality considerations, topic development, participant requirements, assessment process, relevance criteria, evaluation metrics,...
It is standard practice in speech & language technology to rank systems according performance on a test set held out for evaluation. However, few researchers apply statistical tests determine whether differences are likely arise by chance, and examine the stability of system ranking across multiple training-testing splits. We conduct replication reproduction experiments with nine part-of-speech taggers published between 2000 2018, each which reports state-of-the-art widely-used "standard...
TREC-COVID is a community evaluation designed to build test collection that captures the information needs of biomedical researchers using scientific literature during pandemic. One key characteristics pandemic search accelerated rate change: topics interest evolve as progresses and in area explodes. The COVID-19 provides an opportunity capture this progression it happens. TREC-COVID, creating around literature, building infrastructure support new research technologies search.
<h3>Importance</h3> There is widespread concern that clinical notes have grown longer and less informative over the past decade. Addressing these concerns requires a better understanding of magnitude, scope, potential causes increased note length redundancy. <h3>Objective</h3> To measure changes between 2009 2018 in redundancy outpatient progress across multiple medical specialties investigate how measures associate with author experience method entry. <h3>Design, Setting, Participants</h3>...
TREC-COVID is a community evaluation designed to build test collection that captures the information needs of biomedical researchers using scientific literature during pandemic. One key characteristics pandemic search accelerated rate change: topics interest evolve as progresses and in area explodes. The COVID-19 provides an opportunity capture this progression it happens. TREC-COVID, creating around literature, building infrastructure support new research technologies search.
Background With the growing adoption of electronic health record (EHR) worldwide over last decade, new opportunities exist for leveraging EHR data detection rare diseases. Rare diseases are often not diagnosed or delayed in diagnosis by clinicians who encounter them infrequently. One such disease that may be amenable to EHR-based is acute hepatic porphyria (AHP). AHP consists a family rare, metabolic characterized potentially life-threatening attacks and chronic debilitating symptoms. The...
Importance. Data, information and knowledge in health care has expanded exponentially over the last 50 years, leading to significant challenges with overload complex, fragmented plans. Generative AI potential facilitate summarization integration of wisdom through rapid data enable efficient planning. Objective. Our objective was understand value generated short synopses at transition from hospital first outpatient visit. Design. Using a de-identified set recently hospitalized patients...
In dividing Xenopus eggs, furrowing is accompanied by expansion of a new domain plasma membrane in the cleavage plane. The source known to include store oogenetically produced exocytotic vesicles, but site where their exocytosis occurs has not been described. Previous work revealed V-shaped array microtubule bundles at base advancing furrows. Cold shock or exposure nocodazole halted domain, which suggests that these microtubules are involved localized exocytosis. present report, scanning...
Background: Augmentative and alternative communication (AAC) strategies tools developed for individuals with chronic aphasia have been found to facilitate generative language skills. There exists a need identify effective AAC experiencing primary progressive (PPA), neurodegenerative dementia, which compensatory treatment paradigms are yet be systematically evaluated.Aims: To examine the effects of novel compensation tool, CoChat, determine if lexical retrieval skills improve maintained...
Research in clinical information retrieval has long been stymied by the lack of open resources. However, both research innovation and legitimate privacy concerns can be served creation intrainstitutional, fully protected In this article, we provide some principles tools for resource‐building unique problem setting patient‐level retrieval, following tradition Cranfield paradigm. We further include an analysis parallel resources at Oregon Health & Science University Mayo Clinic that were...
Access to communication is critical for individuals with late-stage amyotrophic lateral sclerosis (ALS) and minimal volitional movement, but they sometimes present concomitant visual or ocular motility impairments that affect their performance eye tracking brain-computer interface (BCI) systems. In this study, we explored the use of modified steady state evoked potential (SSVEP) BCI, in combination Shuffle Speller typing interface, population. Two participants ALS, impairments, movement...
Measurement of language atypicalities in Autism Spectrum Disorder (ASD) is cumbersome and costly. Better outcome measures are needed. Using transcripts, we generated Automated Language Measures (ALMs) tested their validity. 169 participants (96 ASD, 28 TD, 45 ADHD) ages 7 to 17 were evaluated with the Diagnostic Observation Schedule. Transcripts one task analyzed generate seven ALMs: mean length utterance morphemes, number different word roots (NDWR), um proportion, content maze...