Obesity and its impact on health is a multifaceted phenomenon encompassing many factors, including demographics, environment, lifestyle, and psychosocial functioning. A systems science approach, investigating these many influences, is needed to capture the complexity and multidimensionality of obesity prevention to improve health. Leveraging baseline data from a unique clinical cohort comprising 333 postmenopausal overweight or obese breast cancer survivors participating in a weight-loss trial, we applied Bayesian networks, a machine learning approach, to infer interrelationships between lifestyle factors (e.g., sleep, physical activity), body mass index (BMI), and health outcomes (biomarkers and self-reported quality of life metrics). We used bootstrap resampling to assess network stability and accuracy, and Bayesian information criteria (BIC) to compare networks. Our results identified important behavioral subnetworks. BMI was the primary pathway linking behavioral factors to glucose regulation and inflammatory markers; the BMI-biomarker link was reproduced in 100% of resampled networks. Sleep quality was a hub impacting mental quality of life and physical health with > 95% resampling reproducibility. Omission of the BMI or sleep links significantly degraded the fit of the networks. Our findings suggest potential mechanistic pathways and useful intervention targets for future trials. Using our models, we can make quantitative predictions about health impacts that would result from targeted, weight loss and/or sleep improvement interventions. Importantly, this work highlights the utility of Bayesian networks in health behaviors research.

No abstract

e15018 Background: There are known risk factors for pancreatic cancer like diabetes mellitus; cigarette smoking; poverty, and alcoholism; all of which are more common in African American patients than the general population. The purpose was to determine if these established risk factors were more associated within African American pancreatic cancer patients to explain their 50 – 90% increased incidence in the U.S. population. Methods: This retrospective study reviewed 172 biopsy-proven pancreatic cancer patients diagnosed over ten years at University of Florida Jacksonville. We employed linear regression models to determine statistical significance of established risk factors with prevalence of pancreatic cancer among cohorts. Results: Our data showed no increased association of diabetes, tobacco use, alcohol use between African Americans and Caucasians. However, Africans Americans as a group were twice as likely to be found at stage III or IV upon diagnosis, conferring an increased mortality risk (OR = 2.2, (95% CI 1.1 – 4.39)). Among these African Americans at advanced stage of diagnosis, females were at triple risk by odds ratio to be underinsured compared to Caucasian males (OR = 3.1, (95% CI 1.29 – 7.49, p = 0.015)). African American females were almost twice as likely to be underinsured compared to Caucasian females (OR = 1.72, (95% CI 0.646, 4.558)). The lack of healthcare access maybe related to advanced stage at diagnosis and its increased mortality risk. Conclusions: Our data suggests that the risk factors of smoking, alcoholism, and diabetes mellitus alone do not explain African Americans’ propensity for pancreatic cancer. However, lack of health insurance does confer an advanced stage at diagnosis and increased mortality risk among African American females. Our data also suggests that other etiological factors such as genetics maybe be associated with the increased risk amongst African Americans. A further investigation is warranted into genetic etiologies since African American patients have higher incidence of K-ras mutations than Caucasians; and mutated K-ras has been associated with pancreatic cancer, which is a target for therapy.