The SENTINL-1 Study: Evaluating Patient-Reported Outcomes of AI-Inferred Lung Cancer Risk
Purpose
This is a two-cohort (screen naïve vs screen established), prospective, longitudinal, single-center clinical study design that will provide data to comprehensively evaluate patient-reported outcomes of Artificial Intelligence (AI) based prediction of an individual's risk of developing lung cancer over the next 3 years.
Condition
- Lung Cancer
Eligibility
- Eligible Ages
- Between 50 Years and 80 Years
- Eligible Sex
- All
- Accepts Healthy Volunteers
- Yes
Inclusion Criteria
- Participants must be 50-80 years of age, inclusive, at the time of signing the Informed Consent Form (ICF). - Participants must be eligible for LDCT screening as defined by the USPSTF - USPSTF-eligible patients at UI Health and Mile Square FQHC, including primary care and substance use disorder clinics. - Adults who have a 20 pack-year smoking history and currently smoke or have quit within the past 15 years. - Able to provide written informed consent and HIPAA authorization for release of personal health information, via an approved UIC Institutional Review Board (IRB) informed consent form and HIPAA authorization. Consent provided by a legally authorized representative is not permitted in this protocol. - Women of childbearing potential must not be pregnant or breastfeeding. A negative serum or urine pregnancy test is required per institutional practice guidelines. - Ability of the subject to understand and comply with study procedures for the entire length of the study.
Exclusion Criteria
- Adults who have more than 20 pack-years history but who have not smoked for 15 years or more prior to informed consent (i.e., quit smoking for 15 or more years). - Undergoing or referred for diagnostic evaluation due to clinical suspicion for cancer (e.g., referred to a medical or surgical oncologist, or scheduled for biopsy on the basis of a suspicious imaging abnormality). - Personal history of invasive solid tumor or hematologic malignancy, diagnosed within the 5 years prior to the expected enrollment date, or diagnosed greater than 5 years prior to the expected enrollment date and never treated. Individuals with a diagnosis of non-metastatic basal cell carcinoma and squamous cell carcinoma of the skin are not excluded. - Prior/Concurrent Concomitant Therapy (Medications/Treatments): Definitive treatment for invasive solid tumor or hematologic malignancy within the 5 years prior to the expected enrollment date. Adjuvant hormone therapy for cancer (e.g., for breast or prostate cancer) is not an exclusion criterion. - Individuals who will not be able to comply with the protocol procedures. - Individuals who are not currently registered patients at UIH - Current pregnancy (by self-report of pregnancy status)
Study Design
- Phase
- N/A
- Study Type
- Interventional
- Allocation
- Non-Randomized
- Intervention Model
- Parallel Assignment
- Primary Purpose
- Screening
- Masking
- None (Open Label)
Arm Groups
| Arm | Description | Assigned Intervention |
|---|---|---|
|
Other Screen-established cohort |
Screen-established participants are individuals who are currently undergoing or have previously undergone LDCT screening. These participants will receive a research-use-only (RUO) multimodal artificial intelligence risk prediction based on lung screening CT imaging and clinical features. |
|
|
Other Screen-naïve cohort |
In this study, screen-naïve participants are individuals who are eligible for lung cancer screening but have never previously undergone low-dose CT (LDCT) screening. These participants will receive a regulatory cleared laboratory developed test for lung cancer screening, circulating DNA fragmentomics. |
|
Recruiting Locations
Chicago, Illinois 60612
More Details
- Status
- Recruiting
- Sponsor
- University of Illinois at Chicago
Detailed Description
This is a prospective, longitudinal, single-center interventional study of AI lung cancer prediction tests with return of results at the University of Illinois Hospital clinics. The purpose is to evaluate patient-reported outcomes of AI risk inference. The motivation for the study was based on findings that existing AI tests have been designed without including patient populations like those at UI Health. Using newer, more generalizable AI tests, UI Health researchers will evaluate patient perceptions of AI risk and how that impacts their beliefs about their health and lung cancer screening. The study will enroll up to 200 screen-naïve and up to 200 screen-established participants, at least 100 and no more than 400 participants, as defined by the eligibility criteria, over an anticipated enrollment period of approximately 12 months. Recruitment strategies to identify potential participants may include identification of participants through electronic health records, emails, recruitment campaigns, and other outreach strategies. Two cohorts will be studied: A) Individuals eligible for lung cancer screening by the USPSTF who have never undergone lung cancer screening with low-dose CT will receive a regulatory cleared laboratory developed test for lung cancer screening eligible patients. B) For USPSTF-eligible individuals who have already received low-dose CT screening, these individuals will receive a research-use-only (RUO) multimodal AI risk prediction that has been validated on UI Health patients. Multimodal AI risk prediction was developed by UIC researchers to predict long-term lung cancer risk by AI inference of lung screening CT images and clinical characteristics from a diverse patient population.