RESEARCH LIBRARY
RESEARCH LIBRARY
View the latest publications from members of the NBME research team
Behavior & Information Technology
This study builds upon prior work in this area that focused on developing a machine-learning classifier trained on gaze data from web-related tasks to detect ASD in adults. Using the same data, we show that a new data pre-processing approach, combined with an exploration of the performance of different classification algorithms, leads to an increased classification accuracy compared to prior work.
Academic Medicine: Volume 97 - Issue 8 - Pages 1219-1225
Since 2012, the United States Medical Licensing Examination (USMLE) has maintained a policy of ≤ 6 attempts on any examination component. The purpose of this study was to empirically examine the appropriateness of existing USMLE retake policy.
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - p 2880–2886
This paper presents a corpus of 43,985 clinical patient notes (PNs) written by 35,156 examinees during the high-stakes USMLE® Step 2 Clinical Skills examination.
Academic Medicine: June 2022
This study examines the associations between Step 3 scores and subsequent receipt of disciplinary action taken by state medical boards for problematic behavior in practice. It analyzes Step 3 total, Step 3 computer-based case simulation (CCS), and Step 3multiple-choice question (MCQ) scores.
Journal of Graduate Medical Education: Volume 14, Issue 3, Pages 353-354
Letter to the editor.
JMIR Medical Education: Volume 8 - Issue 2 - e30988
This article aims to compare the reliability of two assessment groups (crowdsourced laypeople and patient advocates) in rating physician error disclosure communication skills using the Video-Based Communication Assessment app.
Academic Medicine: Volume 97 - Issue 5 - Pages 718-722
The purpose of this 2019–2020 study was to statistically identify and qualitatively review USMLE Step 1 exam questions (items) using differential item functioning (DIF) methodology.
Academic Medicine: Volume 97 - Issue 4 - Pages 476-477
Response to to emphasize that although findings support a relationship between multiple USMLE attempts and increased likelihood of receiving disciplinary actions, the findings in isolation are not sufficient for proposing new policy on how many attempts should be allowed.
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.
Journal of Educational Measurement: Volume 58, Issue 4, Pages 515-537
In this paper, the NBME team reports the results an eye-tracking study designed to evaluate how the presence of the options in multiple-choice questions impacts the way medical students responded to questions designed to evaluate clinical reasoning. Examples of the types of data that can be extracted are presented. We then discuss the implications of these results for evaluating the validity of inferences made based on the type of items used in this study.