A5071178113- Biomedical Text Mining and Ontologies
- Topic Modeling
- Natural Language Processing Techniques
- Computational Drug Discovery Methods
- Machine Learning in Healthcare
- Pharmacovigilance and Adverse Drug Reactions
- Semantic Web and Ontologies
- Clinical Reasoning and Diagnostic Skills
- Digital Mental Health Interventions
- Advanced Text Analysis Techniques
- Electronic Health Records Systems
- Mental Health via Writing
- Text Readability and Simplification
- Patient Safety and Medication Errors
- Mental Health Research Topics
- Healthcare Technology and Patient Monitoring
- Bioinformatics and Genomic Networks
- Social Media in Health Education
- Palliative Care and End-of-Life Issues
- Nursing Diagnosis and Documentation
- Impact of Technology on Adolescents
- Social Media and Politics
- Thyroid Cancer Diagnosis and Treatment
- Scientific Computing and Data Management
- Health Literacy and Information Accessibility
University of Washington
2018-2025
University of Washington Medical Center
2019-2023
Seattle University
2020-2023
Hebrew University of Jerusalem
2023
Dartmouth College
2022
Behavioral Tech Research, Inc.
2022
University of British Columbia
2015-2022
Institute for Medical Informatics and Biostatistics
2020
University of Minnesota System
2020
Island Health
2019
Importance Discussions about goals of care are important for high-quality palliative yet often lacking hospitalized older patients with serious illness. Objective To evaluate a communication-priming intervention to promote goals-of-care discussions between clinicians and Design, Setting, Participants A pragmatic, randomized clinical trial clinician-facing vs usual was conducted at 3 US hospitals within 1 health system, including university, county, community hospital. Eligible were aged 55...
In Brief OBJECTIVE: To conduct a cost-effectiveness analysis of opportunistic salpingectomy (elective at hysterectomy or instead tubal ligation). METHODS: A Markov Monte Carlo simulation model estimated the costs and benefits in hypothetical cohort women undergoing for benign gynecologic conditions surgical sterilization. The primary outcome measure was incremental ratio. Effectiveness measured terms life expectancy gain. Sensitivity analyses accounted uncertainty around various parameters....
This article describes the use of continuous vector space models for reasoning with a formal knowledge base. The practical significance these is that they support fast, approximate but robust inference and hypothesis generation, which complementary to slow, exact, sometimes brittle behaviour more traditional deduction engines such as theorem provers. explains way logical connectives can be used in semantic models, summarizes development Predication-based Semantic Indexing, involves Vector...
When it becomes completely possible for one to computationally forecast the impacts of harmful substances on humans, would be easier attempt addressing shortcomings existing safety testing chemicals. In this paper, we relay outcomes a community-facing DREAM contest prognosticate nature environment-based compounds, considering their likelihood have disadvantageous health-related effects human populace. Our research quantified cytotoxicity levels in 156 compounds across 884 lymphoblastic lines...
Importance Many clinical trial outcomes are documented in free-text electronic health records (EHRs), making manual data collection costly and infeasible at scale. Natural language processing (NLP) is a promising approach for measuring such efficiently, but ignoring NLP-related misclassification may lead to underpowered studies. Objective To evaluate the performance, feasibility, power implications of using NLP measure primary outcome EHR-documented goals-of-care discussions pragmatic...
Generative large language models (LLMs) are a subset of transformers-based neural network architecture models. LLMs have successfully leveraged combination an increased number parameters, improvements in computational efficiency, and pre-training datasets to perform wide spectrum natural processing (NLP) tasks. Using few examples (few-shot) or no (zero-shot) for prompt-tuning has enabled achieve state-of-the-art performance broad range NLP applications. This article by the American Medical...
Distributional semantics is the branch of natural language processing that attempts to model meanings words, phrases and documents from distribution usage words in a corpus text. In past three years, research this area has been accelerated by availability Semantic Vectors package, stable, fast, scalable, free software package for creating exploring concepts distributional models. This paper introduces broad field semantics, role vector models within field, describes some results have made...
Abstract Objective Finding relevant datasets is important for promoting data reuse in the biomedical domain, but it challenging given volume and complexity of data. Here we describe development an open source discovery system called DataMed, with goal building additional indexes domain. Materials Methods which can efficiently index search diverse types across repositories, developed through National Institutes Health–funded healthCAre Data Discovery Index Ecosystem (bioCADDIE) consortium. It...
Objectives. We identified content-specific patterns of network diffusion underlying smoking cessation in the context online platforms, with aim generating targeted intervention strategies. Methods. QuitNet is an social for cessation. analyzed 16 492 de-identified peer-to-peer messages from 1423 members, posted between March 1 and April 30, 2007. Our mixed-methods approach comprised qualitative coding, automated text analysis, affiliation analysis to identify, visualize, analyze communication...
Global pandemics call for large and diverse healthcare data to study various risk factors, treatment options, disease progression patterns. Despite the enormous efforts of many consortium initiatives, scientific community still lacks a secure privacy-preserving infrastructure support auditable sharing facilitate automated legally compliant federated analysis on an international scale. Existing health informatics systems do not incorporate latest progress in modern security machine learning...
Behavioral activation (BA) is rooted in the behavioral theory of depression, which states that increased exposure to meaningful, rewarding activities a critical factor treatment depression. Assessing constructs relevant BA currently requires administration standardized instruments, such as Activation for Depression Scale (BADS), places burden on patients and providers, among other potential limitations. Previous work has shown depressed nondepressed individuals may use language differently...
Health literacy has emerged as a crucial factor in making appropriate health decisions and ensuring treatment outcomes. However, medical jargon the complex structure of professional language this domain make information especially hard to interpret. Thus, there is an urgent unmet need for automated methods enhance accessibility biomedical literature general population. This problem can be framed type translation between healthcare professionals, that public. In paper, we introduce novel task...
Low back pain (LBP) is a common condition made up of variety anatomic and clinical subtypes. Lumbar disc herniation (LDH) lumbar spinal stenosis (LSS) are two subtypes highly associated with LBP. Patients LDH/LSS often started non-surgical treatments if those not effective then go on to have decompression surgery. However, recommendation surgery complicated as the outcome may depend patient's health characteristics. We developed deep learning (DL) model predict for patients LDH/LSS.We used...