Showing 1 - 2 of 2 Research Library Publications

Similarities Between Clinically Matched and Unmatched Analogue Patient Raters: A Mixed Methods Study

Posted: | Ann King, Kathleen Mazor, Andrew Houriet, Thea Musselman, Ruth Hoppe, Angelo D’Addario

Patient Education and Counseling: Volume 109, Supplement, April 2023, Page 2

 

Physicians' responses to patient communication were assessed by both clinically matched and unmatched analogue patients (APs). Significant correlations between their ratings indicated consistency in evaluating physician communication skills. Thematic analysis identified twenty-one common themes in both clinically matched and unmatched AP responses, suggesting similar assessments of important behaviors. These findings imply that clinically unmatched APs can effectively substitute for clinically matched ones in evaluating physician communication and offering feedback when the latter are unavailable.

Category:Assessment-Oriented Research, Applications of Technology, Links to Outcomes

Leveraging Machine Learning Technology to Improve Accuracy and Efficiency of Identification of Enemy Item Pairs

Posted: | Ian Micir, Kimberly Swygert, Jean D'Angelo

Journal of Applied Technology: Volume 23 - Special Issue 1 - Pages 30-40

 

The interpretations of test scores in secure, high-stakes environments are dependent on several assumptions, one of which is that examinee responses to items are independent and no enemy items are included on the same forms. This paper documents the development and implementation of a C#-based application that uses Natural Language Processing (NLP) and Machine Learning (ML) techniques to produce prioritized predictions of item enemy statuses within a large item bank.

Category:Assessment-Oriented Research, Scoring, Applications of Technology