Navigating the Digital Frontier: AI Strategies for RECOVER’s Long COVID Evidence Synthesis Communication

Le résumé fourni par la source

Introduction Over the last decade, the Artificial Intelligence (AI) revolution has transformed communication. By saving time in content creation, AI can inform and support communication strategies. This study examined the effect of deploying AI-enhanced research summaries on user engagement with the NIH-funded Researching COVID to Enhance Recovery (RECOVER) program’s website. Methods Google Analytics 4 (GA4) data was analyzed from two distinct time periods: December 1, 2023 to September 10, 2024, when all content was human-generated, and September 10, 2024 to January 20, 2025, when NYUChatGPT was deployed to assist with all research summaries. We collected and analyzed page views, active users, and average engagement time per user across three key webpages - Publications, Research Summaries, and Videos - for the two time periods. Lastly, we analyzed the review time and readability scores of the AI-enhanced summaries. Results Between the two time periods, the change in views and active users was not statistically significant. However, there was an average increase in the engagement time of 4.37 seconds (95% CI 0.076s – 8.67s)( P = .0461) per active user between the two time periods. The mean number of changes made to the final product by human reviewers for all AI-enhanced deliverables (n=17) was 19.875 (SD = 15.046, 95% CI [11.858, 27.892]). We analyzed the Flesch-Kincaid Readability (FKR) grade level, ranging from 0 to 18, for the initial AI-generated draft of the content and the final, human-reviewed product. For all AI-enhanced deliverables, the mean FKR level of the initial AI-draft was 12.276 (SD = 1.810, 95% CI [11.346, 13.207]) while the mean FKR level for the final products was 11.56 (SD = 2.129, 95% CI [10.464, 12.654]), indicating a decrease in complexity and increased readability for the end user. Conclusion This study demonstrates the potential and challenges of integrating AI into scientific communication. Our analysis showed a modest increase in user engagement with RECOVER’s AI-drafted content, suggesting that AI can be a valuable tool in generating engaging content. Furthermore, the implementation of AI-tools has reduced the production time needed for deliverables, allowing for more timely dissemination of scientific findings. While AI tools have proven effective in assisting with content creation for public engagement, our findings emphasize the critical role of human oversight in ensuring the accuracy, clarity, and accessibility of information.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.