Childhood stroke can lead to lifelong disability. Developing algorithms for timely recognition of clinical and paraclinical signs is crucial to ensure prompt stroke diagnosis and minimize decision-making time. This study aimed to characterize clinical and paraclinical symptoms of childhood and neonatal stroke as relevant diagnostic criteria encountered in clinical practice, in order to develop algorithms for prompt stroke diagnosis. The analysis included data from 402 pediatric case histories from 2010 to 2016 and 108 prospective stroke cases from 2017 to 2020. Stroke cases were predominantly diagnosed in newborns, with 362 (71%, 95% CI 68.99–73.01) cases occurring within the first 28 days of birth, and 148 (29%, 95% CI 26.99–31.01) cases occurring after 28 days. The findings of the study enable the development of algorithms for timely stroke recognition, facilitating the selection of optimal treatment options for newborns and children of various age groups. Logistic regression serves as the basis for deriving these algorithms, aiming to initiate early treatment and reduce lifelong morbidity and mortality in children. The study outcomes include the formulation of algorithms for timely recognition of newborn stroke, with plans to adopt these algorithms and train a fuzzy classifier-based diagnostic model using machine learning techniques for efficient stroke recognition.

Introduction: Pediatric ischemic stroke (IS) is a rare but severe neurological emergency, with an incidence of 2–13 per 100,000. Most cases occur in the prenatal period or early infancy. Integrating artificial intelligence (AI) into clinical practice may enhance the early recognition of stroke. This pilot study aimed to identify immunoenzymatic markers as early predictors of pediatric IS, supporting machine learning applications. Materials and Methods: A prospective study (2017–2019) in Moldova included 53 children with IS and 53 healthy controls. The serum levels of vascular endothelial growth factor (VEGF), ciliary neurotrophic factor (CNTF), the S100B protein, CD105 (endoglin), antiphospholipid antibodies (APAs), and interleukin-6 (IL-6) were measured using ELISA during the acute phase. Results: Endoglin levels were significantly lower in IS patients (2.06 ± 0.012 ng/mL) vs. controls (2.51 ± 0.071 ng/mL) (p < 0.001). S100B levels were elevated (0.524 ± 0.0850 ng/mL vs. 0.120 ± 0.0038 ng/mL, p < 0.01). VEGF levels were significantly increased (613.41 ± 39.299 pg/mL vs. 185.50 ± 12.039 pg/mL, p < 0.001), correlating with the infarct size and disease severity. CNTF levels were also higher (7.84 ± 0.322 pg/mL vs. 5.29 ± 0.067 pg/mL, p < 0.001). APA levels were elevated (1.37 ± 0.046 U/mL vs. 0.92 ± 0.021 U/mL, p < 0.001). IL-6 levels were 10 times higher in IS patients (22.02 ± 2.143 pg/mL vs. 2.38 ± 0.302 pg/mL, p < 0.001), correlating with the infarct size (p < 0.004) and neurological prognosis at six months (p < 0.01). Conclusions: IL-6, VEGF, CNTF, S100B, CD105, and APAs are key markers in pediatric IS, reflecting neuroinflammation, vascular disruption, and the long-term prognosis. Their integration into AI-driven diagnostic models may improve early stroke detection and pediatric monitoring.