LLM Intervention for Tobacco in Underserved Populations (LIFT-UP)
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 入组人数
- 22
- 试验地点
- 1
- 主要终点
- System Usability Scale (SUS)
研究概览
简要总结
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.
详细描述
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.
研究设计
- 研究类型
- Interventional
- 分配方式
- Na
- 干预模型
- Single Group
- 主要目的
- Other
- 盲法
- None
入排标准
- 年龄范围
- 18 Years 至 —(Adult, Older Adult)
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •18+ years old
- •Use ≥3 cigarettes/day on average
- •Motivated to quit in the next 30 days
- •Have a computer or tablet with internet access for 1:1 interviews
- •Speak English or Spanish
- •Home address is in an area characterized by persistent poverty
排除标准
- 未提供
研究组 & 干预措施
Moderated Session
Participants will attend a ~80 minute moderated "think-aloud" session via HIPAA compliant videoconferencing platform.
干预措施: LIFT-UP Chatbot (Behavioral)
结局指标
主要结局
System Usability Scale (SUS)
时间窗: up to 1 day
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.
次要结局
- Usability - Chat Bot Usability Scale (BUS-11)(up to 1 day)
- Acceptability(up to 1 day)
- Digital Working Alliance(up to 1 day)
- Perceived cultural fit(up to 1 day)
