Deep neural networks reveal organic pollutants’ dominance in global inflammatory bowel disease

Abstract

Inflammatory bowel disease (IBD) is increasing globally, with risk factors still poorly understood and influenced by both genetic and environmental factors. The role of atmospheric pollutants, particularly precursor organic pollutants contributing to < 2.5 µm size particulate matter (PM_2.5), remains unclear. In this multi-decadal global study, we investigated their contribution to IBD prevalence using data from the Global Burden of Disease (GBD, 1990–2019), NASA’s MERRA-2, and AERONET datasets. A graph neural network (GNN) modeled spatio-temporal dependencies and incorporated immune dysfunction and socio-economic disparities. The dataset was split into 75 % training and 25 % testing, achieving mean squared errors of 4.3 % and 4.6 % respectively, with strong predictive validity (R² = 0.87). A 10 % global increase in organics was associated with a rise in odds ratio (OR) by 0.21 (95 % CI: 0.12–0.29, p < 0.001), compared to a smaller OR increase of 0.04 (95 % CI: 0.01–0.09, p < 0.001) for PM_2.5. Regional disparities were evident, with Sub-Saharan Africa exhibiting higher odds ratios (OR = 1.25; 95 % CI: 1.09–1.43, p < 0.01) than North America (OR = 1.08; 95 % CI: 1.03–1.24, p < 0.05) at an organic burden of 5 µg/m³. However, this trend reversed at higher exposure (25 µg/m³), where the OR for North America approaches 2, while Sub-Saharan Africa plateaued near 1.5. Notably, particles under 100 nm posed the greatest risk. Concluding, organic pollutants play a disproportionate and size-dependent role in IBD prevalence, with significant regional variability. This underscores the need to consider organics as a distinct environmental risk factor in IBD epidemiology.