A trial comparing AI chatbots to standard health materials found no clear advantage for the conversational tool in boosting HPV vaccine intentions.
Key Details
- The Study: A randomized controlled trial conducted by Penn researchers examined whether AI-powered chatbots could increase HPV vaccine intention among vaccine-hesitant parents.
- Participants: Nearly 1,300 individuals from the US, UK, and Canada took part.
- Methodology: Participants were assigned to one of three groups: interaction with a chatbot, reading written materials from health agencies like the CDC, or receiving no intervention. Each exposure lasted a minimum of 3 minutes.
Findings
Both the chatbot and written materials successfully increased intention to vaccinate compared to the no-intervention group. However, a critical difference emerged over time.
The written materials showed a sustained effect at 45 days, while the chatbot's effect did not persist.
Notably, no intervention led to actual vaccination within the 45-day study window.
Expert Statements
Senior author Sharath Chandra Guntuku highlighted the importance of fair comparisons:
"Comparing a chatbot to nothing isn't really a fair test. The interesting question is whether it does better than what public health agencies already have out there. In our study, it didn't."
First author Neil Sehgal reinforced the study's core purpose:
"We wanted to know whether the chatbot added value beyond what public health agencies already provide."
Co-author Alison Buttenheim emphasized the study's design strength:
"What is new here is the comparison against a strong, realistic control."
Implications for Public Health
The researchers stress that AI tools must be evaluated against realistic alternatives, not simply against doing nothing.
- Chatbots may prove more useful when combined with scheduling reminders or other practical functions.
- Further studies in global health settings are already planned to explore these tools' potential in different contexts.