ICU patients have a 37.158% prevalence of subsyndromal delirium; vasoactive drug use predicts risk.

This prospective cohort study assessed the incidence and influencing factors of subsyndromal delirium within an ICU setting. The sample size was not reported, and the specific intervention or comparator was not reported in the provided data. The primary outcome measured the prevalence of subsyndromal delirium, which was found to be 37.158% among the studied population.

A predictive model utilizing the XGB algorithm demonstrated the best performance with an AUC of 0.84. Feature importance analysis identified several significant predictive factors, including the use of vasoactive drugs (effect size 0.412), monthly household income (effect size 0.306), having undergone surgery (effect size 0.191), and the number of medications (effect size 0.036). No absolute numbers or p-values were reported for these outcomes.

Safety and tolerability data were not reported, and adverse events were not documented. The study limitations note that future multicenter studies should validate these results in larger cohorts. Given the observational nature of the study, causal relationships cannot be established. These findings may enable clinicians to stratify high-risk groups and implement timely and targeted intervention measures, effectively reducing the risk of adverse consequences, but practice relevance remains uncertain without further validation.