Aline B Maddux1, Carter Sevick, Matthew Cox-Martin, Tellen D Bennett. 1. Section of Critical Care Medicine, University of Colorado School of Medicine and Children's Hospital Colorado, Aurora (Dr Maddux); Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus and Children's Hospital Colorado, Aurora (Mr Sevick and Dr Cox-Martin); and Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, and Children's Hospital Colorado, Aurora (Dr Bennett).
Abstract
OBJECTIVE: For children hospitalized with acute traumatic brain injury (TBI), to use postdischarge insurance claims to identify: (1) healthcare utilization patterns representative of functional outcome phenotypes and (2) patient and hospitalization characteristics that predict outcome phenotype. SETTING: Two pediatric trauma centers and a state-level insurance claim aggregator. PATIENTS: A total of 289 children, who survived a hospitalization after TBI between 2009 and 2014, were in the hospital trauma registry, and had postdischarge insurance eligibility. DESIGN: Retrospective cohort study. MAIN MEASURES: Unsupervised machine learning to identify phenotypes based on postdischarge insurance claims. Regression analyses to identify predictors of phenotype. RESULTS: Median age 5 years (interquartile range 2-12), 29% (84/289) female. TBI severity: 30% severe, 14% moderate, and 60% mild. We identified 4 functional outcome phenotypes. Phenotypes 3 and 4 were the highest utilizers of resources. Morbidity burden was highest during the first 4 postdischarge months and subsequently decreased in all domains except respiratory. Severity and mechanism of injury, intracranial pressure monitor placement, seizures, and hospital and intensive care unit lengths of stay were phenotype predictors. CONCLUSIONS: Unsupervised machine learning identified postdischarge phenotypes at high risk for morbidities. Most phenotype predictors are available early in the hospitalization and can be used for prognostic enrichment of clinical trials targeting mitigation or treatment of domain-specific morbidities.
OBJECTIVE: For children hospitalized with acute traumatic brain injury (TBI), to use postdischarge insurance claims to identify: (1) healthcare utilization patterns representative of functional outcome phenotypes and (2) patient and hospitalization characteristics that predict outcome phenotype. SETTING: Two pediatric trauma centers and a state-level insurance claim aggregator. PATIENTS: A total of 289 children, who survived a hospitalization after TBI between 2009 and 2014, were in the hospital trauma registry, and had postdischarge insurance eligibility. DESIGN: Retrospective cohort study. MAIN MEASURES: Unsupervised machine learning to identify phenotypes based on postdischarge insurance claims. Regression analyses to identify predictors of phenotype. RESULTS: Median age 5 years (interquartile range 2-12), 29% (84/289) female. TBI severity: 30% severe, 14% moderate, and 60% mild. We identified 4 functional outcome phenotypes. Phenotypes 3 and 4 were the highest utilizers of resources. Morbidity burden was highest during the first 4 postdischarge months and subsequently decreased in all domains except respiratory. Severity and mechanism of injury, intracranial pressure monitor placement, seizures, and hospital and intensive care unit lengths of stay were phenotype predictors. CONCLUSIONS: Unsupervised machine learning identified postdischarge phenotypes at high risk for morbidities. Most phenotype predictors are available early in the hospitalization and can be used for prognostic enrichment of clinical trials targeting mitigation or treatment of domain-specific morbidities.
Authors: Samuel M Brown; Emily L Wilson; Angela P Presson; Victor D Dinglas; Tom Greene; Ramona O Hopkins; Dale M Needham Journal: Thorax Date: 2017-08-04 Impact factor: 9.139
Authors: Tellen D Bennett; Rebecca R Dixon; Cory Kartchner; Peter E DeWitt; Yamila Sierra; Diane Ladell; Allison Kempe; Desmond K Runyan; J Michael Dean; Heather T Keenan Journal: Pediatr Crit Care Med Date: 2016-12 Impact factor: 3.624
Authors: Nikoloas Papachristou; Payam Barnaghi; Bruce A Cooper; Xiao Hu; Roma Maguire; Kathi Apostolidis; Jo Armes; Yvette P Conley; Marilyn Hammer; Stylianos Katsaragakis; Kord M Kober; Jon D Levine; Lisa McCann; Elisabeth Patiraki; Steven M Paul; Emma Ream; Fay Wright; Christine Miaskowski Journal: J Pain Symptom Manage Date: 2017-08-30 Impact factor: 3.612
Authors: François Aspesberro; Megan D Fesinmeyer; Chuan Zhou; Jerry J Zimmerman; Rita Mangione-Smith Journal: Pediatr Crit Care Med Date: 2016-06 Impact factor: 3.624
Authors: Jerry J Zimmerman; Russell Banks; Robert A Berg; Athena Zuppa; Christopher J Newth; David Wessel; Murray M Pollack; Kathleen L Meert; Mark W Hall; Michael Quasney; Anil Sapru; Joseph A Carcillo; Patrick S McQuillen; Peter M Mourani; Hector Wong; Ranjit S Chima; Richard Holubkov; Whitney Coleman; Samuel Sorenson; James W Varni; Julie McGalliard; Wren Haaland; Kathryn Whitlock; J Michael Dean; Ron W Reeder Journal: Crit Care Med Date: 2020-03 Impact factor: 7.598
Authors: Aline B Maddux; Peter M Mourani; Kristen Miller; Todd C Carpenter; Jaime LaVelle; Laura L Pyle; R Scott Watson; Tellen D Bennett Journal: Pediatr Crit Care Med Date: 2022-03-07 Impact factor: 3.971
Authors: Michelle Vo; Kristen Miller; Tellen D Bennett; Peter M Mourani; Jaime LaVelle; Todd C Carpenter; R Scott Watson; Laura L Pyle; Aline B Maddux Journal: Pediatr Pulmonol Date: 2022-04-26