Search Articles

View query in Help articles search

Search Results (1 to 3 of 3 Results)

Download search results: CSV END BibTex RIS


Sample Size Considerations for Fine-Tuning Large Language Models for Named Entity Recognition Tasks: Methodological Study

Sample Size Considerations for Fine-Tuning Large Language Models for Named Entity Recognition Tasks: Methodological Study

In cases where multiple human-annotated samples were used, we noted the largest reported sample as indicative of the researchers’ sense of the sample necessary to conduct the research in its entirety. Additionally, for each paper that made use of a human-annotated training set, we sought to identify any possible justifications for the chosen sample size.

Zoltan P Majdik, S Scott Graham, Jade C Shiva Edward, Sabrina N Rodriguez, Martha S Karnes, Jared T Jensen, Joshua B Barbour, Justin F Rousseau

JMIR AI 2024;3:e52095

Predictors of Online Patient Portal Use Among a Diverse Sample of Emerging Adults: Cross-sectional Survey

Predictors of Online Patient Portal Use Among a Diverse Sample of Emerging Adults: Cross-sectional Survey

The sample was defined by only those who self-reported 1 or more health care visits on the Lorig healthcare utilization questionnaire. The sample was further categorized by their use of the portal (nonuser versus user). Users were defined as those who reported using at least one of 8 portal features. Pearson chi-square analyses or independent t tests were used to examine differences by user status. A Levene test for equality of variances was run to determine the t statistic used to evaluate significance.

Julie A Wright, Julie E Volkman, Suzanne G Leveille, Daniel J Amante

JMIR Form Res 2022;6(2):e33356