An interventional study of LIFT-UP Chatbot in Smoking Cessation, sponsored by University of Utah. Not yet recruiting at 1 site in United States. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-08-06.
Sponsored by University of Utah · Not applicable, Interventional, and Other
This study will test a tailored, multilingual tobacco cessation chatbot called LIFT-UP (LLM Intervention for Tobacco in Underserved Populations), designed to better meet the needs of people living in persistent poverty census tracts.
This study will use 1:1 semi-structured interviews to explore social drivers of health impacting TC, as well as digital access and preferences among those living in PPCTs. This qualitative approach enables guided yet flexible exploration of key domains while capturing unanticipated insights relevant to refining the chatbot.
Tobacco use is a major cause of cancer and is responsible for about half a million deaths in the United States each year. Because of this, helping people stop using tobacco is one of the most important ways to prevent cancer. Although tobacco use has decreased over time, many adults in the U.S. still use tobacco. Many people try to quit each year, but most quit attempts are not successful. One reason is that many people do not use proven, evidence-based quit support, such as counseling or quit medications.
People who live in areas with long-term poverty often face additional barriers that can make quitting harder. These areas may have fewer job and education opportunities, limited access to healthcare and community resources, and higher levels of day-to-day stress (for example, related to financial strain or lack of health insurance). People with lower income are just as likely to try to quit as those with higher income, but they are less likely to quit successfully and are less likely to use evidence-based quitting support. Many persistent poverty areas are also rural and have higher numbers of people who prefer to speak languages other than English, including Spanish, which creates an additional need for bilingual and culturally appropriate quit support.
Digital tools may help increase access to evidence-based tobacco cessation support in these communities. Mobile phone ownership is very common, including among people with lower incomes. However, some smartphone apps require reliable internet access or data plans, which can be a barrier. Text messaging is accessible on nearly all phones, does not require internet access, can be offered in multiple languages, and can be tailored to the needs of the user.
Text-based programs that use artificial intelligence (AI), such as large-language-model chatbots, may be especially useful because they can provide interactive support using natural language and can be delivered at scale. Chatbots have been used successfully in other areas of health, but many existing programs use fixed scripts and may not feel relevant or helpful for all groups. Importantly, most tobacco cessation chatbots have not been designed to address barriers faced by people living in persistent poverty areas.
Exclusion Criteria:
Participants will attend a \~80 minute moderated "think-aloud" session via HIPAA compliant videoconferencing platform.
Behavioral: LIFT-UP Chatbot
LIFT-UP Chatbot will be developed, evaluated, and refined using GARDE-Chat, an open-source chatbot authoring platform that has been used to support the development of chatbot-based interventions tested in large pragmatic clinical trials.
System Usability Scale (SUS)
Usability will be measured using the SUS, a questionnaire assessing the perceived usability of a system, product, website, app, or digital intervention. It consists of ten 5-point Likert items ranging from "Strongly disagree" to "Strongly agree". Scoring follows the standard SUS scoring procedure, for positively worded items, the item score is calculated as response minus 1; for negatively worded items, the item score is calculated as 5 minus the response. The 10 item scores are summed and then multiplied by 2.5 to generate the final SUS score, with higher scores indicating greater perceived usability. Score range: 0-100.
Time frame: up to 1 day
Usability - Chat Bot Usability Scale (BUS-11)
Chatbot usability will be measured using the Chatbot Usability Scale (BUS-11). BUS-11 is a measured that assesses users' experiences after interacting with a chatbot or conversational agent. The BUS-11 consists of eleven 5-point Likert items ranging from "Strongly disagree" to "Strongly agree". Each item is coded from 1 to 5, and item scores are summed to create a total score. Higher scores indicate greater perceived chatbot usability. Score range: 11-55.
Time frame: up to 1 day
Acceptability
Acceptability will be measured using the Acceptability of Intervention Measure (AIM). AIM is an instrument that assesses the perceived acceptability of an intervention. It consists of four 5 point Likert items ranging from "Completely "disagree" to "Strongly agree". Each item is coded from 1 to 5, and the overall score is the mean of the items score. Higher scores indicate greater perceived acceptability of the intervention. Score range: 1-5.
Time frame: up to 1 day
Digital Working Alliance
Working alliance in the digital context will be measured with the Digital Working Alliance inventory (D-WAI). D-WAI is derived from the Working Alliance Inventory and measures the perceived working alliance (e.g., traditionally the collaborative bond between therapist and client) with digital interventions. It includes six 7-point Likert items ranging from "Strongly disagree" to "Strongly agree". Each item is coded from 1 to 7, and item scores are summed to create a total score. Higher scores indicate a stronger perceived digital working alliance. Score range: 7-42.
Time frame: up to 1 day
Perceived cultural fit
Perceived cultural relevance will be measured using the Cultural Relevance Questionnaire (CRQ). CRQ consists of six 5-point Likert items ranging from "Strongly disagree" to "Strongly agree. Higher scores indicate greater perceived cultural appropriateness/relevance of the intervention. Score range: 5-25. An additional 5-point Likert-like question was added to reflect overall cultural fit perceived by the users.
Time frame: up to 1 day
Plan to share: No — De-identified data will be shared with only with investigators that have a data sharing agreement through PIVOT.
No publications or documents are linked to this record.
This study is not yet recruiting, as verified in Jun 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
University of Utah