Work

Can GPT-5 Support Licensing Examination Preparation? Analysis of Accuracy, Reasoning, and Semantic Similarity Across Rehabilitation Disciplines

Year: 2026

Type: article

Abstract: Unlabelled: In this cross-sectional study of 300 board-style questions across physical therapy, occupational therapy, and speech-language pathology, we evaluated reasoning types and found high overall accuracy with variation by discipline and reasoning category; the strongest performance was in deductive and analytical reasoning and the lowest accuracy was in evaluative reasoning.

Source: JMIR Rehabilitation and Assistive Technologies

DOI: 10.2196/91019

Authors: Christy Muasher-Kerwin, M Courtney Hughes, Aida Sanatizadeh

Institutions: North Central College, Northern Illinois University

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $1,750