Imaging-based risk assessment of intestinal obstruction: The impact mechanisms of clozapine-class drugs and nutritional elements

Intestinal obstruction is a common and serious condition within the digestive system, with a higher incidence observed in the elderly population. This condition can lead to a series of significant complications. In recent years, there has been growing attention on the adverse gastrointestinal effects associated with antipsychotic medications such as clozapine, yet the relationship between these drugs and intestinal obstruction requires systematic investigation. This study is based on the U.S. National Health and Nutrition Examination Survey (NHANES) database, integrating participant health status, nutritional intake, medication use, and imaging diagnostic information. Weighted analysis, forest plots, and neural network models were employed to explore the risk factors associated with intestinal obstruction. A total of 5226 participants were included in the study. Statistically significant differences were observed in age, gender, marital status, income, and nutritional intake between the intestinal obstruction group and the control group. Individuals aged over 60 years, females, and those with low income exhibited a higher risk of developing the condition. The risk of intestinal obstruction increased by 78% among users of clozapine, and high protein and low fiber intake were also identified as risk factors. The predictive performance of the neural network model was moderate, with energy intake being the most important variable. In the intestinal obstruction group, levels of potassium and magnesium were significantly elevated, which may suggest their role in the pathophysiology of the condition. This study identified several important risk factors associated with intestinal obstruction, particularly highlighting the effects of clozapine use and nutritional elements. The findings provide a basis for the identification of high-risk populations and early interventions, as well as directions for future intelligent predictions that incorporate imaging characteristics.