Skip to main content
. Author manuscript; available in PMC: 2024 Sep 18.
Published in final edited form as: Eur Arch Otorhinolaryngol. 2024 Feb 28;281(6):3219–3225. doi: 10.1007/s00405-024-08524-0

Table 1.

Average readability and understandability scores of Chat GPT and web search responses to generated patient questions.

ChatGPT Web search Mean difference, 95% CI
FRE 42.3 ± 14.2 56.2 ± 17.4 13.9 (10.6 – 15.3)
FKRL 12.1 ± 2.8 9.4 ±3.3 −2.7 (−3.6 – −1.7)
PEMAT Understandability 93.8 (57.1–100.0) 88.4 (42.9 – 100.0) −5.3 (−1.2 – 9.6)

FRE: Flesch Reading Ease, FKGL: Flesch-Kincaid Grade Level