Currently submitted to: Journal of Medical Internet Research
Date Submitted: Jul 15, 2026
Open Peer Review Period: Jul 16, 2026 - Sep 10, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
The Utility of Google's AI Overview in Answering Anatomy-related Search Queries: Cross-sectional Quantitative Analysis
ABSTRACT
Background:
This study provides an understanding of Google’s new search engine feature AI (Artificial Intelligence) Overview and its usefulness in answering anatomy search queries. The study outlines the function, utility and limitations of AI Overview in this context.
Objective:
The study aims to evaluate the utility of the tool by investigating the appearance rate, readability and substantiation of AI Overview responses to anatomical queries.
Methods:
A list of 120 anatomical prompts of different obscurities, anatomical regions, and sex were curated from a standard anatomy textbook. The prompts were then entered into Google’s search engine in two separate rounds of searching. Search results were analysed in Python for readability and recency of cited literature.
Results:
The preliminary search found that AI Overview responses were returned for 70.8% of all anatomical queries searched. The secondary search found that for 120 AI Overview responses, 2731 citations across 1327 sources were returned. Flesch-Kincaid readability analysis of AI Overview responses found the readability of AI Overview to be at a level equivalent to that obtained at college (US). AI Overviews were strongly substantiated with most cited sources being recently published and of reputable background. AI Overviews favoured highly ranked sources, with the top 5 AI Overview sources accounting for more than 46% of all citations.
Conclusions:
Overall, the functional capabilities of AI Overview make it suitable for use in self-study of anatomy. However, users should be aware of the functional pitfalls of AI Overview. Selective presentation of corroborating sources and biases in training data were considered limitations of AI Overview. Future research should investigate potential algorithmic biases.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.