Comparative analysis of the effectiveness of microsoft copilot artificial intelligence chatbot and google search in answering patient inquiries about infertility: evaluating readability, understandability, and actionability

Failure to achieve spontaneous pregnancy within 12 months despite unprotected intercourse is called infertility. The rapid development of digital health data has led more people to search for healthcare-related topics on the Internet. Many infertile individuals and couples use the Internet as their primary source for information on infertility diagnosis and treatment. However, it is important to assess the readability, understandability, and actionability of the information provided by these sources for patients. There is a gap in the literature addressing this aspect. This study aims to compare the readability, understandability, and actionability of responses generated by Microsoft Copilot (MC), an AI chatbot, and Google Search (GS), an internet search engine, for infertility-related queries. Prospectively a Google Trends analysis was conducted to identify the top 20 queries related to infertility in February, 2024. Then these queries were entered into GS and MC in May 2024. Answers from both platforms were recorded for further analysis. Outputs were assessed using automated readability tools, and readability scores were calculated. Understandability and actionability of answers were evaluated using the Patient Education Materials Assessment Tool for Printable Materials (PEMAT-P) tool. GS was found to have significantly higher Automated Readability Index (ARI) and Flesch-Kincaid Grade Level (FKGL) scores than MC (p = 0.044), while no significant differences were observed in the Flesch Reading Ease, Gunning Fog Index, Simplified Measure of Gobbledygook (SMOG), and Coleman-Liau Index scores. Both GS and MC outputs had readability scores above the 8th-grade level, indicating advanced reading levels. According to PEMAT-P, MC outperformed GS in terms of understandability (68.65 ± 11.99 vs. 54.50 ± 15.09, p = 0.001) and actionability (29.85 ± 17.8 vs. 1 ± 4.47, p = 0.000). MC provides more understandable and actionable responses to infertility related queries, that it might have great potential for patient education.