Comparison of different artificial intelligence tools' answers to questions related to early intervention: ChatGPT versus Gemini

Abstract

OBJECTIVE: The aim of this studywasto assess the quality and readability of ChatGPT and Gemini's responses to frequently asked questions about early intervention for individuals with at-risk infants. METHODS: Ten frequently asked questions about early intervention were selected by three researchers (a child development specialist, a physiotherapist, and a midwife) from a list generated byChatGPT and Gemini. Questions were sentto ChatGPTversion4.0 and Gemini 1.5, and initial responses were recorded without follow-up queries. Ten independent experts (two special education specialists, two child development specialists, two physiotherapists, two midwives, and two pediatricians) The quality of ChatGPT and Gemini's responses was assessed using a four-grade rating system. Readability levels were analyzed using the Flesch-Kincaid Grade Level through WordCalc software. RESULTS:Oneofthe answersgiven byChatGPTwasof higherqualitythan Gemini (p=0.025),whileone answergiven byGeminiwasof higherquality than ChatGPT (p=0.033). The answers to the other questions were of similar quality, with Gemini having a lower level. CONCLUSION: This studycomparesthe quality and readabilityof the answers given by artificial intelligence-based language models to demonstrate their potential to appeal todifferent user groups. While the models generally provided answers of similar quality, quantitative differences in readability were observed, suggesting potential suitability for different audiences. These findings contribute to understanding the role of AI tools in health communication.