Interpretable machine learning-derived nomogram model for early detection of persistent diarrhea in Salmonella typhimurium enteritis: a propensity score matching based case-control study

• DOI: 10.1186/s12879-025-10587-1
• Publication Date: 2025-02-10T15:52:16Z
• Authors: Longteng Jin; Yucheng Huang; Jianan Xi; Lu Zhan; Haojie Jin; Yiping Chen; Maoping Chu
• Keywords: Salmonella typhimurium enteritis; Persistent diarrhea; Machine learning; Infectious and parasitic diseases; RC109-216; Nomogram model; Pediatrics

Abstract Salmonella typhimuriuminfection is a considerable global health concern, particularly in children, where it often leads to persistent diarrhea. This condition can result in severe health complicationsincluding malnutrition and cognitive impairment. A retrospective case-control study was carried out involving 627 children diagnosed with S. typhimuriumenteritis. The children were admitted to the Second Affiliated Hospital of Wenzhou Medical University between January 2010 and December 2022. Propensity score matching was used to explore the potential risk factors and predictors of persistent diarrhea following S. typhimurium infection. As a result, body temperature, C-reactive protein (CRP) levels, alanine aminotransferase (ALT) levels, white blood cellcount, and lactose intolerance were significant predictors of persistent diarrhea. Nomogram models developed based on these predictors demonstrated robust performance in predicting persistent diarrhea risk, with an accuracy of > 90%. Conclusions: The developed nomogram models provide a practical tool for the early identification of children at high risk of persistent diarrhea, facilitating intervention, potentially preventing serious sequelae, and improving the prognosis of children with S. typhimuriumenteritis.