Artykuł źródłowy pochodzi z portalu PubMed. Oryginalny tytuł to:
Artykuł naukowy porównuje jakość i czytelność materiałów edukacyjnych dla pacjentów na temat rurek myringotomijnych, uzyskanych za pomocą sztucznej inteligencji oraz wyszukiwarki Google. Wykorzystano narzędzia takie jak skala DISCERN oraz testy czytelności Flesch-Kincaid i Fry, aby ocenić materiały. Wyniki pokazują, że materiały te mają średnią jakość, ale poziom ich czytelności przekracza zalecany szósty poziom nauczania. Wyszukiwarka…
Zobacz Abstrakt
Eur Arch Otorhinolaryngol. 2024 Dec 12. doi: 10.1007/s00405-024-09148-0. Online ahead of print.
ABSTRACT
PURPOSE: To compare the quality and readability of patient education materials on myringotomy tubes from artificial intelligence and Google search.
METHODS: Three questions were posed to ChatGPT and Google Gemini addressing „Condition,” „Investigation,” and „Treatment” domains. Google was queried for „Ear tubes,” „Myringotomy and tubes,” and „Tympanostomy tubes.” Text quality was assessed using the DISCERN instrument. Readability was assessed using the Flesch-Kincaid Grade Level, Flesch-Kincaid Reading Ease scores, and the Fry Readability Graph.
RESULTS: The average DISCERN score for websites was 52 (SD = 13.1, Median = 55.5), out of 80. The mean Flesch-Kincaid Reading Grade Level was 8 (SD = 3, Median = 7.1), and the mean Flesch-Kincaid Reading Ease score was 55 (SD = 12.3, Median = 57.7). ChatGPT and Google Gemini’s „Condition” responses each had DISCERN scores of 46, Flesch-Kincaid Grade Levels of 13.1 and 9.5, and Reading Ease scores of 41 and 61. For „Investigation,” DISCERN scores were 46 (ChatGPT) and 66 (Google Gemini), Grade Levels were 13.9 and 12.4, and Reading Ease scores were 38.9 and 34.9. For „Treatment,” ChatGPT and Google Gemini had DISCERN scores of 45 and 34, Grade Levels of 15.7 and 9.8, and Reading Ease scores of 36.2 and 53.9.
CONCLUSION: Sites and artificial intelligence providing patient education material regarding myringotomy tubes are of „fair” quality but have readability levels above the recommended 6th grade level. Google search results were superior to artificial intelligence in readability.
PMID:39668220 [https://pubmed.ncbi.nlm.nih.gov/39668220/?utm_source=Other&utm_medium=rss&utm_campaign=pubmed-2&utm_content=18Cx71VHHP3XUFm_UtwWKCRHiwab6gnVsoJL5Op9oVpDIYQURc&fc=20241127081157&ff=20241213020332&v=2.18.0.post9+e462414] | DOI:10.1007/s00405-024-09148-0 [https://doi.org/10.1007/s00405-024-09148-0]
Poniższy komentarz stanowi jedynie kontekst wiadomości i NIE jest analizą przedstawianych badań naukowych, więc po dokładne informacje sięgnij do źródła PubMed.