Anish K. Agarwal | Searcharxiv

arXiv2026

Effects of Static and Conversational AI-Generated Messages on Colorectal Cancer Screening Intent: a Randomized Clinical Trial

Large language model chatbots show increasing promise in persuasive communication, but their clinical utility remains uncertain, particularly in settings where sustained conversations are difficult to scale. In a randomized clinical trial, 915 U.S. adults (ages 45-75) who had never completed colorectal cancer (CRC) screening were randomized to no-message control, expert-written patient materials, single AI-generated message, or motivational interviewing (MI) chatbot. Both AI interventions significantly increased stool-test intentions by over 12 points (12.9-13.8/100), compared to a 7.5 gain for expert materials (p<.001). While AI interventions outperformed the no-message control for colonoscopy intent, neither showed improvement over expert materials. Notably, we did not detect a statistically significant difference between the longer, interactive chatbot and the simpler single AI message, despite participants spending 3 minutes more on average engaging with it. These findings suggest concise, demographically tailored AI messages may offer a scalable approach to increasing CRC screening intentions, although effects on completed screening remain unknown.

cs.CY↗

arXiv2026

Large Language Model Chatbot Conversations vs Public Health Materials and Parental HPV Vaccination Intentions: A Randomized Clinical Trial

Health care systems are increasingly considering large language model (LLM)-based chatbots for vaccine communication, but evidence that they improve durable, behaviorally relevant outcomes beyond existing health materials is limited. This randomized clinical trial tested whether brief, multiturn LLM chatbot interactions increased parental intention to vaccinate children against human papillomavirus (HPV) compared with no intervention and government public health materials, and whether effects persisted. Parents in the US, Canada, and UK were recruited online from March 3 to May 25, 2025, with follow-up at 15 and 45 days. Eligible participants were adults with at least one HPV vaccine-eligible child who was unvaccinated or whose vaccination status was unknown. Participants were randomized to no-message control, country-matched government materials with at least 3 minutes of exposure, or a 3-minute GPT-4o chatbot interaction using either a default persuasive style or a shorter conversational style. The primary outcome was self-reported likelihood of vaccinating the child against HPV within 12 months, measured immediately after intervention on a 0-100 scale. Follow-up outcomes included vaccination intent and self-reported vaccination at 15 and 45 days. In total, 1297 participants were randomized (mean age 42.84 years; 72.1% female). Compared with no intervention, public health materials increased immediate vaccination intent (Cohen d = 0.53; 95% CI, 0.36-0.70), as did the default chatbot (d = 0.48; 95% CI, 0.30-0.65) and conversational chatbot (d = 0.33; 95% CI, 0.17-0.49). At 45 days, neither chatbot increased intent relative to controls, whereas public health materials maintained modest effects. No intervention increased self-reported vaccination uptake. Findings suggest well-designed public health materials may match or exceed short LLM chatbot conversations for HPV vaccine promotion.

cs.CY↗