Vineet K Raghu1, Christopher M Horvat1,2,3,4,5,6, Patrick M Kochanek1,2,3,4,5,6, Ericka L Fink1,2,3,4,5,6, Robert S B Clark1,2,3,4,5,6, Panayiotis V Benos1,6, Alicia K Au1,2,3,4,5,6. 1. Department of Computer Science, University of Pittsburgh, Pittsburgh, PA. 2. Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA. 3. Department of Pediatrics, University of Pittsburgh School of Medicine, Pittsburgh, PA. 4. Safar Center for Resuscitation Research, University of Pittsburgh School of Medicine, Pittsburgh, PA. 5. Brain Care Institute, UPMC Children's Hospital of Pittsburgh, Pittsburgh, PA. 6. Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA.
Abstract
OBJECTIVES: Neurologic complications, consisting of the acute development of a neurologic disorder, that is, not present at admission but develops during the course of illness, can be difficult to detect in the PICU due to sedation, neuromuscular blockade, and young age. We evaluated the direct relationships of serum biomarkers and clinical variables to the development of neurologic complications. Analysis was performed using mixed graphical models, a machine learning approach that allows inference of cause-effect associations from continuous and discrete data. DESIGN: Secondary analysis of a previous prospective observational study. SETTING: PICU, single quaternary-care center. PATIENTS: Individuals admitted to the PICU, younger than18 years old, with intravascular access via an indwelling catheter. INTERVENTIONS: None. MEASUREMENTS: About 101 patients were included in this analysis. Serum (days 1-7) was analyzed for glial fibrillary acidic protein, ubiquitin C-terminal hydrolase-L1, and alpha-II spectrin breakdown product 150 utilizing enzyme-linked immunosorbent assays. Serum levels of neuron-specific enolase, myelin basic protein, and S100 calcium binding protein B used in these models were reported previously. Demographic data, use of selected clinical therapies, lengths of stay, and ancillary neurologic testing (head CT, brain MRI, and electroencephalogram) results were recorded. The Mixed Graphical Model-Fast-Causal Inference-Maximum algorithm was applied to the dataset. MAIN RESULTS: About 13 of 101 patients developed a neurologic complication during their critical illness. The mixed graphical model identified peak levels of the neuronal biomarker neuron-specific enolase and ubiquitin C-terminal hydrolase-L1, and the astrocyte biomarker glial fibrillary acidic protein to be the direct causal determinants for the development of a neurologic complication; in contrast, clinical variables including age, sex, length of stay, and primary neurologic diagnosis were not direct causal determinants. CONCLUSIONS: Graphical models that include biomarkers in addition to clinical data are promising methods to evaluate direct relationships in the development of neurologic complications in critically ill children. Future work is required to validate and refine these models further, to determine if they can be used to predict which patients are at risk for/or with early neurologic complications.
OBJECTIVES: Neurologic complications, consisting of the acute development of a neurologic disorder, that is, not present at admission but develops during the course of illness, can be difficult to detect in the PICU due to sedation, neuromuscular blockade, and young age. We evaluated the direct relationships of serum biomarkers and clinical variables to the development of neurologic complications. Analysis was performed using mixed graphical models, a machine learning approach that allows inference of cause-effect associations from continuous and discrete data. DESIGN: Secondary analysis of a previous prospective observational study. SETTING: PICU, single quaternary-care center. PATIENTS: Individuals admitted to the PICU, younger than18 years old, with intravascular access via an indwelling catheter. INTERVENTIONS: None. MEASUREMENTS: About 101 patients were included in this analysis. Serum (days 1-7) was analyzed for glial fibrillary acidic protein, ubiquitin C-terminal hydrolase-L1, and alpha-II spectrin breakdown product 150 utilizing enzyme-linked immunosorbent assays. Serum levels of neuron-specific enolase, myelin basic protein, and S100 calcium binding protein B used in these models were reported previously. Demographic data, use of selected clinical therapies, lengths of stay, and ancillary neurologic testing (head CT, brain MRI, and electroencephalogram) results were recorded. The Mixed Graphical Model-Fast-Causal Inference-Maximum algorithm was applied to the dataset. MAIN RESULTS: About 13 of 101 patients developed a neurologic complication during their critical illness. The mixed graphical model identified peak levels of the neuronal biomarker neuron-specific enolase and ubiquitin C-terminal hydrolase-L1, and the astrocyte biomarker glial fibrillary acidic protein to be the direct causal determinants for the development of a neurologic complication; in contrast, clinical variables including age, sex, length of stay, and primary neurologic diagnosis were not direct causal determinants. CONCLUSIONS: Graphical models that include biomarkers in addition to clinical data are promising methods to evaluate direct relationships in the development of neurologic complications in critically ill children. Future work is required to validate and refine these models further, to determine if they can be used to predict which patients are at risk for/or with early neurologic complications.
Authors: Alicia K Au; Michael J Bell; Ericka L Fink; Rajesh K Aneja; Patrick M Kochanek; Robert S B Clark Journal: Neurocrit Care Date: 2018-02 Impact factor: 3.210
Authors: Georgios D Kitsios; Libing Yang; Dimitris V Manatakis; Mehdi Nouraie; John Evankovich; William Bain; Daniel G Dunlap; Faraaz Shah; Ian J Barbash; Sarah F Rapport; Yingze Zhang; Rebecca S DeSensi; Nathaniel M Weathington; Bill B Chen; Prabir Ray; Rama K Mallampalli; Panayiotis V Benos; Janet S Lee; Alison Morris; Bryan J McVerry Journal: Crit Care Med Date: 2019-12 Impact factor: 7.598
Authors: Patrick M Kochanek; Robert C Tasker; Nancy Carney; Annette M Totten; P David Adelson; Nathan R Selden; Cynthia Davis-O'Reilly; Erica L Hart; Michael J Bell; Susan L Bratton; Gerald A Grant; Niranjan Kissoon; Karin E Reuter-Rice; Monica S Vavilala; Mark S Wainwright Journal: Pediatr Crit Care Med Date: 2019-03 Impact factor: 3.624
Authors: Jiri Bartek; Eric Peter Thelin; Per Hamid Ghatan; Martin Glimaker; Bo-Michael Bellander Journal: PLoS One Date: 2016-03-28 Impact factor: 3.240