Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
The goal of this clinical trial is to test whether short conversations with large language model (LLM) chatbots can persuade vaccine-hesitant parents to vaccinate their children against human papillomavirus (HPV). The study compares two chatbot styles to official public health information and to a no-message control. Parents of HPV-eligible children first complete a survey about their attitudes toward the HPV vaccine and their main concerns. They are then randomly assigned to read public health materials, have a three-minute conversation with either a default-style chatbot or a conversational-style chatbot tailored to their concern, or receive no message. The main outcome is change in intent to vaccinate immediately after the intervention, with follow-up surveys at 15 and 45 days.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Default-style LLM chatbot | Experimental | A large language model chatbot (GPT-4o) that delivers tailored persuasive messages to parents about HPV vaccination, using the model's default style with longer, structured responses. Participants engage in a three-minute, multi-turn conversation, with responses personalized to their top-rated vaccine concern identified in a pre-intervention survey. |
|
| Conversational-style LLM chatbot | Experimental | A large language model chatbot (GPT-4o) that delivers tailored persuasive messages to parents about HPV vaccination in a conversational style, with short responses. Participants engage in a three-minute, multi-turn conversation, with responses personalized to their top-rated vaccine concern identified in a pre-intervention survey. |
|
| Public health informational materials | Active Comparator | Official public health informational materials on HPV vaccination from the Centers for Disease Control and Prevention (U.S.), National Health Service (U.K.), or Public Health Agency of Canada, matched to the participant's country of residence. Materials are 589-680 words in length, cover HPV risks and benefits of vaccination, and are presented for three minutes before participants proceed. |
|
| No Message | No Intervention | No Intervention |
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Default-style LLM chatbot | Behavioral | A large language model chatbot (GPT-4o) that delivers tailored persuasive messages to parents about HPV vaccination, using the model's default style with longer, structured responses. Participants engage in a three-minute, multi-turn conversation, with responses personalized to their top-rated vaccine concern identified in a pre-intervention survey. |
| Measure | Description | Time Frame |
|---|---|---|
| Change in intent to vaccinate child against HPV within the next 12 months | Self-reported likelihood, on a 0-100 scale, of vaccinating the participant's youngest HPV vaccine-eligible child (identified in pre-survey) within the next 12 months. Measured before and immediately after the intervention to assess short-term changes in vaccination intent. | Baseline to immediately post-intervention |
| Measure | Description | Time Frame |
|---|---|---|
| Change in intent to vaccinate child against HPV at 15-day follow-up | Self-reported likelihood, on a 0-100 scale, of vaccinating the participant's youngest HPV vaccine-eligible child within the next 12 months. Measured at baseline and 15 days after the intervention to assess durability of effects. | Baseline to 15 days post-intervention |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Participants are recruited online via Prolific | Philadelphia | Pennsylvania | 19104 | United States |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 42258213 | Derived | Sehgal NKR, Rai S, Tonneau M, Agarwal AK, Cappella J, Kornides ML, Ungar L, Buttenheim A, Guntuku SC. Large Language Model Chatbot Conversations vs Public Health Materials and Parental HPV Vaccination Intentions: A Randomized Clinical Trial. JAMA Netw Open. 2026 Jun 1;9(6):e2616822. doi: 10.1001/jamanetworkopen.2026.16822. |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
|
| Conversational-style LLM chatbot | Behavioral | A large language model chatbot (GPT-4o) that delivers tailored persuasive messages to parents about HPV vaccination in a conversational style, with short responses. Participants engage in a three-minute, multi-turn conversation, with responses personalized to their top-rated vaccine concern identified in a pre-intervention survey. |
|
| Public health informational materials | Behavioral | Official public health informational materials on HPV vaccination from the Centers for Disease Control and Prevention (U.S.), National Health Service (U.K.), or Public Health Agency of Canada, matched to the participant's country of residence. Materials are 589-680 words in length, cover HPV risks and benefits of vaccination, and are presented for three minutes before participants proceed. |
|
| Change in intent to vaccinate child against HPV at 45-day follow-up |
Self-reported likelihood, on a 0-100 scale, of vaccinating the participant's youngest HPV vaccine-eligible child within the next 12 months. Measured at baseline and 45 days after the intervention to assess durability of effects. |
| Baseline to 45 days post-intervention |
| Change in general parental vaccine hesitancy (PACV-5) | Change in scores on the 5-item Parent Attitudes about Childhood Vaccines (PACV-5) scale. Measured at baseline and immediately after the intervention. | Baseline to immediately post-intervention |
| Change in intent to vaccinate child for influenza and COVID-19 | Self-reported likelihood, on a 0-100 scale, of vaccinating the participant's youngest eligible child for influenza or COVID-19 within the next 12 months. | Measured at baseline and immediately post-intervention. |
| Change in importance ratings of HPV vaccine concerns | Change in participant ratings (0-100 scale) of importance for each HPV vaccine concern (list derived from National Immunization Surveys) between baseline and immediately post-intervention. | Baseline to immediately post-intervention |
| Clicks on HPV vaccine appointment scheduling link | Whether participants click a provided link to schedule an HPV vaccine appointment through CVS during the post-intervention survey. | Immediately post-intervention |
| Willingness to donate payment to vaccine education charity | Percentage of survey payment participants choose to donate (0%, 10%, 30%, or 50%) to an immunization-related charity during the post-intervention survey. | Immediately post-intervention |
| Willingness to be recontacted for future research | Participant self-reported willingness (yes/no) to be contacted for future studies | Immediately post-intervention |
| Ratings of empathy, usefulness, and relevance of intervention content | Participant ratings (1-5 scale) of how empathetic, useful, and relevant they found the assigned chatbot conversation or public health reading material. | Immediately post-intervention |