Cathy Shyr
YOU?
Author Swipe
View article: An optimized variant prioritization process for rare disease diagnostics: recommendations for Exomiser and Genomiser
An optimized variant prioritization process for rare disease diagnostics: recommendations for Exomiser and Genomiser Open
View article: Opportunities, barriers, and remedies for implementing REDCap integration with electronic health records via Fast Healthcare Interoperability Resources (FHIR)
Opportunities, barriers, and remedies for implementing REDCap integration with electronic health records via Fast Healthcare Interoperability Resources (FHIR) Open
Objective Accelerate adoption of clinical research technology that obtains electronic health record (EHR) data through HL7 Fast Healthcare Interoperability Resources (FHIR). Materials and Methods Based on experience helping institutions im…
View article: Large Language Models for Rare Disease Diagnosis at the Undiagnosed Diseases Network
Large Language Models for Rare Disease Diagnosis at the Undiagnosed Diseases Network Open
This cohort study assesses whether large language models (LLMs) can identify the final diagnosis, based on available clinical information, for patients referred to the Undiagnosed Diseases Network.
View article: A statistical framework for evaluating the repeatability and reproducibility of large language models
A statistical framework for evaluating the repeatability and reproducibility of large language models Open
A major concern in applying large language models (LLMs) to medicine is their reliability. Because LLMs generate text by sampling the next token (or word) from a probability distribution, the stochastic nature of this process can lead to d…
View article: O27: Leveraging electronic health records to characterize growth patterns and curves in individuals with genetic disease
O27: Leveraging electronic health records to characterize growth patterns and curves in individuals with genetic disease Open
View article: Sex-Specific Diagnostic Inequality in Fabry Disease: Lessons Learned from Analysis of Newborn Screening and Cascade Testing in Tennessee from 2017 to 2024
Sex-Specific Diagnostic Inequality in Fabry Disease: Lessons Learned from Analysis of Newborn Screening and Cascade Testing in Tennessee from 2017 to 2024 Open
View article: Empowering the biomedical research community: Innovative SAS deployment on the <i>All of Us</i> Researcher Workbench
Empowering the biomedical research community: Innovative SAS deployment on the <i>All of Us</i> Researcher Workbench Open
Objectives The All of Us Research Program is a precision medicine initiative aimed at establishing a vast, diverse biomedical database accessible through a cloud-based data analysis platform, the Researcher Workbench (RW). Our goal was to …
View article: Leveraging artificial intelligence to summarize abstracts in lay language for increasing research accessibility and transparency
Leveraging artificial intelligence to summarize abstracts in lay language for increasing research accessibility and transparency Open
Objective Returning aggregate study results is an important ethical responsibility to promote trust and inform decision making, but the practice of providing results to a lay audience is not widely adopted. Barriers include significant cos…
View article: Illuminating the landscape of high-level clinical trial opportunities in the <i>All of Us</i> Research Program
Illuminating the landscape of high-level clinical trial opportunities in the <i>All of Us</i> Research Program Open
Objective With its size and diversity, the All of Us Research Program has the potential to power and improve representation in clinical trials through ancillary studies like Nutrition for Precision Health. We sought to characterize high-le…
View article: Identifying and Extracting Rare Diseases and Their Phenotypes with Large Language Models
Identifying and Extracting Rare Diseases and Their Phenotypes with Large Language Models Open
Purpose Phenotyping is critical for informing rare disease diagnosis and treatment, but disease phenotypes are often embedded in unstructured text. While natural language processing (NLP) can automate extraction, a major bottleneck is deve…
View article: Impact of financial compensation on enrollment and participation in a remote, mobile-app based research study
Impact of financial compensation on enrollment and participation in a remote, mobile-app based research study Open
Background: There is no consensus on how to determine appropriate financial compensation for research recruitment. Selecting incentive amounts that are reasonable and respectful, without undue inducement, remains challenging. Previously, w…
View article: Expert advice from ResearchMatch volunteers: Recruitment Innovation Center use cases and innovation
Expert advice from ResearchMatch volunteers: Recruitment Innovation Center use cases and innovation Open
Involving participants in the design of clinical trials should improve the overall success of a study. For this to occur, streamlined mechanisms are needed to connect the populations potentially impacted by a given study or health topic wi…
View article: Identifying and Extracting Rare Disease Phenotypes with Large Language Models
Identifying and Extracting Rare Disease Phenotypes with Large Language Models Open
Rare diseases (RDs) are collectively common and affect 300 million people worldwide. Accurate phenotyping is critical for informing diagnosis and treatment, but RD phenotypes are often embedded in unstructured text and time-consuming to ex…
View article: Multi-Study R-Learner for Estimating Heterogeneous Treatment Effects Across Studies Using Statistical Machine Learning
Multi-Study R-Learner for Estimating Heterogeneous Treatment Effects Across Studies Using Statistical Machine Learning Open
Estimating heterogeneous treatment effects (HTEs) is crucial for precision medicine. While multiple studies can improve the generalizability of results, leveraging them for estimation is statistically challenging. Existing approaches often…
View article: A validation of models for prediction of pathogenic variants in mismatch repair genes
A validation of models for prediction of pathogenic variants in mismatch repair genes Open
View article: Multi-Study Boosting: Theoretical Considerations for Merging vs. Ensembling
Multi-Study Boosting: Theoretical Considerations for Merging vs. Ensembling Open
Cross-study replicability is a powerful model evaluation criterion that emphasizes generalizability of predictions. When training cross-study replicable prediction models, it is critical to decide between merging and treating the studies s…