Development of a Clinical Reasoning Documentation Assessment Tool for Resident and Fellow Admission Notes: a Shared Mental Model for Feedback

Abstract

BACKGROUND: Residents and fellows receive little feedback on their clinical reasoning documentation. Barriers include lack of a shared mental model and variability in the reliability and validity of existing assessment tools. Of the existing tools, the IDEA assessment tool includes a robust assessment of clinical reasoning documentation focusing on four elements (interpretive summary, differential diagnosis, explanation of reasoning for lead and alternative diagnoses) but lacks descriptive anchors threatening its reliability. OBJECTIVE: Our goal was to develop a valid and reliable assessment tool for clinical reasoning documentation building off the IDEA assessment tool. DESIGN, PARTICIPANTS, AND MAIN MEASURES: The Revised-IDEA assessment tool was developed by four clinician educators through iterative review of admission notes written by medicine residents and fellows and subsequently piloted with additional faculty to ensure response process validity. A random sample of 252 notes from July 2014 to June 2017 written by 30 trainees across several chief complaints was rated. Three raters rated 20% of the notes to demonstrate internal structure validity. A quality cut-off score was determined using Hofstee standard setting. KEY RESULTS: The Revised-IDEA assessment tool includes the same four domains as the IDEA assessment tool with more detailed descriptive prompts, new Likert scale anchors, and a score range of 0-10. Intraclass correlation was high for the notes rated by three raters, 0.84 (95% CI 0.74-0.90). Scores ≥6 were determined to demonstrate high-quality clinical reasoning documentation. Only 53% of notes (134/252) were high-quality. CONCLUSIONS: The Revised-IDEA assessment tool is reliable and easy to use for feedback on clinical reasoning documentation in resident and fellow admission notes with descriptive anchors that facilitate a shared mental model for feedback.

Clinical Reasoning of a Generative Artificial Intelligence Model Compared With Physicians

“…Physicians' vignette responses may differ from clinical practice; however, physician R-IDEA scores in clinical documentation were lower than physician scores in this study. 6 We also used a zero-shot approach for chatbot's prompt.…”

“…Primary outcome was the Revised-IDEA (R-IDEA) score, a validated 10-point scale evaluating 4 core domains of clinical reasoning documentation (eTable 3 in Supplement 1). 6 To establish reliability, we (D.R., Z.K., A.R.) independently scored 29 section responses from 8 nonparticipants, showing substantial scoring agreement (mean Cohen weighted κ = 0.61).…”

“…Physicians' vignette responses may differ from clinical practice; however, physician R-IDEA scores in clinical documentation were lower than physician scores in this study. 6 We also used a zero-shot approach for chatbot's prompt. Iterative training could enhance LLM performance, suggesting that the results may have underestimated its capabilities.…”

Demystifying AI: Current State and Future Role in Medical Education Assessment

“…23 For instance, models like Schaye et al's ML model for automated assessment of resident clinical reasoning documentation are examples of supervised ML that use text-based labeled datasets. 24 Such models help overcome traditional barriers in medical education assessment by providing a sufficient number of assessment inputs and consistency in standards of assessment. 25 This automated assessment of clinical reasoning documentation helps overcome the barriers in medical education assessment of obtaining sufficient number of assessment inputs and consistency in standards of assessment.…”

“…AI is increasingly being used in the assessment of physician competence across various levels of learners (undergraduate medical education [UME], graduate medical education [GME], and continuing medical education [CME]), competency domains (e.g., medical knowledge and patient care), and different types of data input (e.g., text vs video) and AI technologies (e.g., supervised vs unsupervised ML) 23 . For instance, models like Schaye et al’s ML model for automated assessment of resident clinical reasoning documentation are examples of supervised ML that use text-based labeled datasets 24 . Such models help overcome traditional barriers in medical education assessment by providing a sufficient number of assessment inputs and consistency in standards of assessment 25 .…”