1529 Background: In patients with cancer, those with lower income are 30% less likely to participate in clinical trials. Lower income individuals face direct and indirect costs that can make participation in a clinical trial prohibitive. However, a broader evaluation of specific behavioral, information, insurance, and area-level variables that could contribute to this disparity has not been conducted. We aimed to develop and validate a model to identify socioeconomically vulnerable patients at high risk of non-participation in clinical trials. Methods: We used data from the Health Information National Trends Survey (HINTS), a national cross-sectional survey about knowledge of, attitudes toward, and use of health-related information. We analyzed HINTS survey databases that included questions about whether patients with cancer participated in a clinical trial (survey years 2014, 2017, and 2020). We examined 21 different demographic, socioeconomic, behavioral, geographic, and health information questions. We derived a risk model to predict clinical trial participation in a random set of 60% of participants using best subset selection with k-fold cross validation. The derived model was validated in the remaining 40% of participants. Logistic regression was used. Results: We examined N=1,023 participants with household income <$75,000, the current median in the U.S. In the training dataset of n=614 participants, a model with 5 variables was identified. Non-Hispanic White patients and patients without a college education, with high levels of distrust, with high levels of anxiety or depression, and from non-urban areas were all at lower risk of trial participation. We summed the adverse risk factors for all individuals; a risk score with 4 levels was constructed based on distribution quartiles. In the independent validation cohort (n=409), each increase in level of adverse risk factors was associated with a 42% reduction in the odds of trial participation (OR=0.58, 95%-CI, 0.40-0.84, p=.004), indicating successful model validation. Among all individuals, trial participation rates decreased from 18.6% to 7.5% to 4.6% to 2.8%, respectively, as the number of adverse risk factors increased (in quartiles) from 0-1 to 2 to 3 to 4-5. Individuals with 4 or 5 risk factors (vs. those with 0-1 factors) were 87% less likely to participate (OR=0.13, 95% CI, 0.05-0.31, p<.0001). Conclusions: We developed and validated a 5-variable risk model that identified a large set of lower income individuals at lower risk of trial participation. In a first-time observation, psychosocial variables were shown to be meaningful predictors of lower trial participation. These findings could aide in the early identification of patients who may benefit from additional support to navigate the treatment trial decision making process, in the name of more equitable participation in trials for all patients.