Sepsis remains a significant contributor to neonatal mortality worldwide. However, the nonspecific nature of sepsis symptoms in neonates often leads to the necessity of empirical treatment, placing a burden of ineffective treatment on patients. Furthermore, the global challenge of antimicrobial resistance is exacerbating the situation. Artificial intelligence (AI) is transforming medical practice and in hospital settings. AI shows great potential for assessing sepsis risk and devising optimal treatment strategies. Background/Objectives: This review aims to investigate the application of AI in the detection and management of neonatal sepsis. Methods: A systematic literature review (SLR) evaluating AI methods in modeling and classifying sepsis between 1 January 2014, and 1 January 2024, was conducted. PubMed, Scopus, Cochrane, and Web of Science were systematically searched for English-language studies focusing on neonatal sepsis. Results: The analyzed studies predominantly utilized retrospective electronic medical record (EMR) data to develop, validate, and test AI models to predict sepsis occurrence and relevant parameters. Key predictors included low gestational age, low birth weight, high results of C-reactive protein and white blood cell counts, and tachycardia and respiratory failure. Machine learning models such as logistic regression, random forest, K-nearest neighbor (KNN), support vector machine (SVM), and XGBoost demonstrated effectiveness in this context. Conclusions: The summarized results of this review highlight the great promise of AI as a clinical decision support system for diagnostics, risk assessment, and personalized therapy selection in managing neonatal sepsis.

Background/Objective: Early diagnosis of neonatal sepsis remains a challenge due to the nonspecific nature of clinical symptoms and the delayed dynamics of conventional inflammatory markers. The traditional diagnostic approach is based on static cut-off points, which often do not consider the nonlinear nature of the inflammatory response. The aim of this study was to identify dynamic variables associated with sepsis progression, constituting the foundation for future artificial intelligence (AI) models. Methods: A retrospective analysis was performed using anonymised clinical and laboratory data from a cohort of newborns (n = 122) with suspected sepsis, along with maternal clinical data. Using feature engineering, descriptive statistics parameters were generated for selected parameters, including rates of change in the 24 h and 48 h time windows. This was combined with the verification of clinical and perinatal parameters that affect the assessment of clinical status and diagnosis of sepsis. The correlation analysis was performed using Spearman’s rank correlation coefficient (p < 0.05). Results: Dynamic parameters showed significant associations with sepsis progression than static measurements. The highest correlation was recorded for the rate of CRP growth (CRP_abs_change_rate_max, r = 0.613, p < 0.001), compared with the maximum values (CRP_value_max, r = 0.591, p < 0.001). High correlations were also observed for leukocyte parameters, especially neutrophils (NEUT_%_pct_change_rate_max, r = 0.547, p < 0.001) and basophils (BASO_%_value_max, r = 0.606, p < 0.001), with the strongest correlations observed within the first 24 h (r > 0.70). Conclusions: Neonatal sepsis progression may be more comprehensively characterised by temporal changes in laboratory parameters, not by their absolute values. Rates of change in inflammatory markers may provide clinically relevant complementary information on the course of the disease, reflecting the complex and nonlinear nature of the inflammatory response. The results indicate that the analysis of the trajectory of changes in parameters provides a promising basis for the future development and validation of predictive models based on artificial intelligence for earlier and more accurate diagnosis of neonatal sepsis.