CLINICAL-EPIDEMIOLOGICAL ANALYSIS OF ACUTE INTESTINAL INFECTIONS OF BACTERIAL AND VIRAL ETIOLOGY AND DIGITAL DECISION-MAKING ALGORITHM

Acute intestinal infections remain an important medical and epidemiological problem worldwide. This study investigated the clinical and epidemiological characteristics of bacterial and viral acute intestinal infections in the Fergana region and evaluated digital predictive models for etiological differentiation. Clinical, epidemiological, and laboratory data of 96 patients treated during 2023-2024 were analyzed. Viral etiology was identified in 50% of cases, bacterial in 35%, and mixed infections in 15%. High fever, prolonged diarrhea, dehydration, leukocytosis, and elevated ESR were more common in bacterial infections. Among the applied digital models, the Random Forest algorithm demonstrated the highest diagnostic performance with 90% accuracy and 88% sensitivity. The findings suggest that digital predictive models can improve early etiological assessment, optimize treatment strategies, and support clinical decision-making in acute intestinal infections.