Artificial Intelligence- and Physician-Interpreted Stool Image Characteristics Correlate With C-Reactive Protein Among Inpatients With Acute Severe Ulcerative Colitis: A Pilot Study (2024 Oxford University Press)

This study explores the correlation between stool characteristics measured by AI and physicians with inflammation in patients hospitalized with acute severe ulcerative colitis (ASUC). Using AI and manual scoring, the study found that certain stool characteristics, like the Bristol stool scale and stool consistency, significantly correlated with C-reactive protein (CRP) levels, a marker of inflammation. The findings suggest that smartphone-based AI tools could serve as noninvasive methods for monitoring UC disease activity in clinical settings, potentially improving patient care through more precise monitoring.