Colorectal Cancer Control and Prevention
Conditions
Keywords
chatbot, Artificial Intelligence, large language models, colorectal cancer screening
Brief summary
The goal of this clinical trial is to assess whether messages generated by a large language model (LLM), including both static and conversational formats, can increase colorectal cancer (CRC) screening intentions among U.S. adults aged 45-75 who have never completed CRC screening. The main questions it aims to answer are: Do personalized, AI-generated messages increase the self-reported likelihood of completing a stool-based CRC screening test within 12 months? Do they also increase intent to undergo colonoscopy screening within 12 months? Researchers will compare four groups: (1) no message control, (2) expert-written patient education materials, (3) a single AI-generated persuasive message, and (4) a motivational interviewing-style AI chatbot. These comparisons will help assess whether a conversational format offers added benefit over static AI or expert-generated content. Participants will: Be randomly assigned to one of the four study arms Spend at least 3 minutes reading or interacting with their assigned material Complete pre- and post-intervention surveys assessing intent to receive CRC screening Receive messages tailored to their self-reported demographics, including age, political ideology, gender, education, community setting (urban, rural, suburb), self-reported health, and the last time they saw their PCP
Interventions
BEHAVIORALsingle GPT generated message
Participants receive a single \ 640-word message generated by GPT-4.1. The message is tailored to participants' self-reported demographics (age, gender, political ideology, education, urbanicity, health status, and last PCP visit). The message provides persuasive content encouraging colorectal cancer screening, emphasizing stool and colonoscopy screening options. Participants are required to read the message for a minimum of 3 minutes.
BEHAVIORALAI Chatbot
Participants engage in a multi-turn conversation with a GPT-4.1 chatbot trained to emulate motivational interviewing techniques. The chatbot personalizes its conversation based on each participant's demographics (age, gender, political ideology, education, urbanicity, health status, and last PCP visit). Conversations last at least 3 minutes and aim to increase participant motivation to complete colorectal cancer screening.
BEHAVIORALExpert-Written Patient Materials
Participants read a 642-word expert-written educational summary from the Journal of the American Medical Association's Patient Page on colorectal cancer screening. The material is designed to provide objective information about screening options and guidelines recommended by the US Preventive Services Task Force. Participants are required to read the material for at least 3 minutes.
Sponsors
University of Pennsylvania
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
SCREENING
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
45 Years to 75 Years
Healthy volunteers
Yes
Inclusion criteria
* Adults aged 45 to 75 years * Currently residing in the United States * Self-reported no prior colorectal cancer screening (or unsure if screened) * Able to read and understand English * Consent to participate in a behavioral research study
Exclusion criteria
* Previous colonoscopy, stool test, sigmoidoscopy, or CT colonography * Failure to pass pre- or post-intervention attention checks * Identified as non-human respondents by reCAPTCHA or other automated bot detection * Completion time significantly shorter than the median, indicating inattentiveness
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Change in Self-Reported Likelihood of Completing Stool Test Screening for Colorectal Cancer | Immediately before and after the intervention (single session; same day) | Measured on a 0-100 scale, where 0 = Extremely unlikely and 100 = Extremely likely. Assessed before and after the intervention. Change in score indicates difference in participant intention to complete a stool-based CRC screening test. |
| Change in Self-Reported Likelihood of Completing Colonoscopy Screening for Colorectal Cancer | Immediately before and after the intervention (single session; same day) | Measured on a 0-100 scale, where 0 = Extremely unlikely and 100 = Extremely likely. Assessed before and after the intervention. Change in score reflects shift in participant intention to complete a colonoscopy within the next 12 months. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Perceived Empathy of the Intervention | Immediately after the intervention (single session) | Participants rate how empathetic they found the assigned message or chatbot interaction using a 5-point Likert scale. Higher values indicate greater perceived empathy. |
| Comfort Discussing CRC Screening with a Provider | Immediately before and after the intervention (single session; same day) | Measured on a 0-100 scale where 0 = Not at all comfortable and 100 = Extremely comfortable. Assessed pre- and post-intervention to detect changes in self-reported comfort discussing colorectal cancer screening with a primary care provider. |
| Perceived Message Effectiveness | Immediately after the intervention (single session) | Participants rate the persuasive effectiveness of the assigned content using a previously developed public health message effectiveness scale. |
| Change in Reasons for CRC Screening Hesitancy | Immediately before and after the intervention (single session) | Participants rate the importance of 13 pre-defined concerns about CRC screening on a 0-100 scale (e.g., cost, discomfort, necessity). Changes in ratings pre- to post-intervention reflect shifts in perceived barriers. |
Countries
United States
Outcome results
None listed