Development and external validation of a machine learning prediction model for Epstein-Barr virus-associated hemophagocytic lymphohistiocytosis in children using routine blood parameters: a retrospective cohort study.
A quick blood test can now reliably distinguish a life-threatening immune condition from routine mono in children, enabling urgent treatment when it matters most.
Random Forest model using routine CBC parameters (WBC, PLT, LAC, Hb) distinguishes EBV-associated HLH from infectious mononucleosis in 4,871 pediatric patients with AUC 0.993 (internal) and 0.971 (external validation), enabling life-saving early triage.
What the study was
- Study design
- retrospective_cohort
- Category
- cbc_ml_hematology
- Maturity
- clinical
- Journal
- BMC Infectious Diseases
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.