Assessment of the Readability of Google Gemini-Generated Versus UpToDate Clinical Contents for Ventricular Tachycardia Management

Introduction Ventricular tachycardia (VT) is a life-threatening arrhythmia requiring complex management. Google Gemini is increasingly used to generate medical content, while UpToDate remains a leading expert-authored clinical reference. This study compared the "readability," not the "clinical accuracy," of VT-related content generated by Google Gemini and UpToDate. Aims This study aims to objectively compare the readability of Google Gemini-generated medical content and UpToDate expert-authored material on VT using standardized readability indices. Methods A cross-sectional study analyzed 12 textual responses on VT management: six from Google Gemini and six from UpToDate. Readability was assessed using the WebFX Readability Test Tool, which calculates Flesch Reading Ease (FRE), Flesch-Kincaid Grade Level (FKGL), Simple Measure of Gobbledygook (SMOG) Index, and Difficult Word Percentage. As the data were non-normally distributed, the Mann-Whitney U test was applied. The analysis was limited to quantitative readability metrics and did not assess clinical accuracy or human comprehension. Results The median FKGL score was 16.5 for UpToDate and 13.5 for Google Gemini (p = 0.017), indicating that UpToDate text required a more advanced reading level. The median Difficult Word Percentage was 32.0% for Google Gemini and 28.6% for UpToDate (p = 0.026), suggesting that Google Gemini content contained a higher proportion of multisyllabic or specialized words. No significant differences were observed in FRE or SMOG Index values (p > 0.05). Conclusion Google Gemini-generated content demonstrated a simpler sentence structure but greater lexical density compared to UpToDate. This highlights a distinct linguistic pattern: syntactic simplicity combined with concentrated technical vocabulary. These findings emphasize the importance of expert review when using Google Gemini-generated material in medical education and communication.

Authors

Institutions

Publication Details

Journal
Cureus
Published
2025-11-28
DOI
https://doi.org/10.7759/cureus.97997
Primary Topic
Health Literacy and Information Accessibility
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Assessment of the Readability of Google Gemini-Generated Versus UpToDate Clinical Contents for Ventricular Tachycardia Management

Veena Ramanathan, Mohammad Danish, Puru Panchal, M Chaudhari et al.
Cureus
Health Literacy and Information Accessibility
article

Assessment of the Readability of Google Gemini-Generated Versus UpToDate Clinical Contents for Ventricular Tachycardia Management

Veena Ramanathan, Mohammad Danish, Puru Panchal, M Chaudhari, Akash Ranganatha, Nikhil Vamsi Chitte
article en

Abstract

Introduction Ventricular tachycardia (VT) is a life-threatening arrhythmia requiring complex management. Google Gemini is increasingly used to generate medical content, while UpToDate remains a leading expert-authored clinical reference. This study compared the "readability," not the "clinical accuracy," of VT-related content generated by Google Gemini and UpToDate. Aims This study aims to objectively compare the readability of Google Gemini-generated medical content and UpToDate expert-authored material on VT using standardized readability indices. Methods A cross-sectional study analyzed 12 textual responses on VT management: six from Google Gemini and six from UpToDate. Readability was assessed using the WebFX Readability Test Tool, which calculates Flesch Reading Ease (FRE), Flesch-Kincaid Grade Level (FKGL), Simple Measure of Gobbledygook (SMOG) Index, and Difficult Word Percentage. As the data were non-normally distributed, the Mann-Whitney U test was applied. The analysis was limited to quantitative readability metrics and did not assess clinical accuracy or human comprehension. Results The median FKGL score was 16.5 for UpToDate and 13.5 for Google Gemini (p = 0.017), indicating that UpToDate text required a more advanced reading level. The median Difficult Word Percentage was 32.0% for Google Gemini and 28.6% for UpToDate (p = 0.026), suggesting that Google Gemini content contained a higher proportion of multisyllabic or specialized words. No significant differences were observed in FRE or SMOG Index values (p > 0.05). Conclusion Google Gemini-generated content demonstrated a simpler sentence structure but greater lexical density compared to UpToDate. This highlights a distinct linguistic pattern: syntactic simplicity combined with concentrated technical vocabulary. These findings emphasize the importance of expert review when using Google Gemini-generated material in medical education and communication.

CureusVol. 17(11)
Swansea Bay University Health Board (GB), Midas Multispeciality Hospital (IN), Davao Medical School Foundation (PH), B.J. Medical College (IN), JSS Dental College and Hospital (IN), Kamineni Institute of Dental Sciences (IN)
Openalex Percentile: Top 46%
Health Literacy and Information Accessibility
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.