Objective:

To compare the effectiveness of brief conversations with a chatbot and public health materials on parents' intentions to vaccinate their children against HPV.

Approach:

• Study Design: A randomized clinical trial involving 1,297 parents from the US, Canada, and the UK with at least one HPV vaccine-eligible child.
• Interventions: Participants were assigned to receive no message, government public health materials, a GPT-4o chatbot with a default response style, or a GPT-4o chatbot with a conversational style.
• Outcome Measurement: Parents' self-reported likelihood of vaccinating their child against HPV was measured immediately after the intervention and at 15 and 45 days follow-up.

Key Findings:

• All active interventions increased immediate HPV vaccination intent compared to no message.
• Public health materials produced the largest effect, followed by the default chatbot and the conversational chatbot.
• At 15 days, public health materials and the conversational chatbot maintained modest increases in intent, while the default chatbot did not.
• By 45 days, only public health materials remained statistically significant.
• None of the interventions increased self-reported HPV vaccination uptake at 15 or 45 days.

Interpretation:

Brief chatbot interactions may raise short-term HPV vaccination intentions but do not demonstrate a significant advantage over established public health communication materials.

Limitations:

• ThesamplewaspredominantlyWhiteandfemale,whichmaylimitgeneralizabilitytoabroaderpopulation.

Conclusion:

High-quality public health materials demonstrated greater durability and effectiveness compared to brief chatbot interactions.

Sources:

• JAMA Network Open