ABSTRACTObjectiveThrombotic microangiopathy induced Thrombocytopenia Associated Multiple Organ Failure and hyperinflammatory Macrophage Activation Syndrome are important causes of late pediatric sepsis mortality that are often missed or have delayed diagnosis. Our objective is to derive computable 24-hour sepsis phenotypes to facilitate enrollment in early precise anti-inflammatory trials targeting mortality from these conditions.DesignMachine learning analysis using consensus k-means clustering.SettingNine pediatric intensive care units.Patients404 children with severe sepsis.Interventions24-hour computable phenotypes derived using 25 bedside variables including C-reactive protein and ferritin.Measurements and Main ResultsFour computable phenotypes (PedSep-A, B, C, and D) are derived. Compared to the overall population mean, PedSep-A has the least inflammation (median C-reactive protein 7.3 mg/dL, ferritin 125 ng/mL), younger age, less chronic illness, and more respiratory failure (n = 135; 2% mortality); PedSep-B (median C-reactive protein 13.2 mg/dL, ferritin 225 ng/ mL) has organ failure with intubated respiratory failure, shock, and Glasgow Coma Scale score < 7 (n = 102, 12% mortality); PedSep-C (median C-reactive protein 15.2 mg/dL, ferritin 405 ng/mL) has elevated ferritin, lymphopenia, more shock, more hepatic failure and less respiratory failure (n = 110; mortality 10%); and, PedSep D (median C-reactive protein 13.1 mg/dL ferritin 610 ng/mL), has hyperferritinemic, thrombocytopenic multiple organ failure with more cardiovascular, respiratory, hepatic, renal, hematologic, and neurologic system failures (n = 56, 34% mortality). PedSep-D has highest likelihood of Thrombocytopenia Associated Multiple Organ Failure (Adj OR 47.51 95% CI [18.83-136.83], p < 0.0001) and Macrophage Activation Syndrome (Adj OR 38.63 95% CI [13.26-137.75], p <0.0001), and an observed survivor interaction with combined methylprednisolone and intravenous immunoglobulin therapies (p < 0.05).CONCLUSIONS AND RELEVANCEMachine learning identifies four computable phenotypes (www.pedsepsis.pitt.edu). Membership in PedSep-D appears optimal for enrollment in early anti-inflammatory trials targeting Thrombocytopenia Associated Multiple Organ Failure and Macrophage Activation Syndrome.Author’s CommentQuestionCan machine learning methods derive 24-hour computable pediatric sepsis phenotypes that facilitate early identification of patients for enrollment in precise anti-inflammatory therapy trials?FindingsFour distinct phenotypes (PedSep-A, B, C, and D) were derived by assessing 25 bedside clinical variables in 404 children with sepsis. PedSep-D patients had a thrombotic microangiopathy and hyperinflammatory macrophage activation biomarker response, and improved survival odds associated with combined methylprednisolone plus intravenous immunoglobulin therapy.MeaningFour novel computable 24-hour phenotypes are identifiable (www.pedsepsis.pitt.edu) that could potentially facilitate enrollment in early precise anti-inflammatory trials targeting thrombotic microangiopathy and macrophage activation in pediatric sepsis.
PPARαmediates the anti-inflammatory effect of simvastatin in an experimental model of zymosan-induced multiple organ failure
