- Browse by Author
Browsing by Author "Rogerson, Colin"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
Item A machine learning-based phenotype for long COVID in children: an EHR-based study from the RECOVER program(Cold Spring Harbor Laboratory, 2022-12-26) Lorman, Vitaly; Razzaghi, Hanieh; Song, Xing; Morse, Keith; Utidjian, Levon; Allen, Andrea J.; Rao, Suchitra; Rogerson, Colin; Bennett, Tellen D.; Morizono, Hiroki; Eckrich, Daniel; Jhaveri, Ravi; Huang, Yungui; Ranade, Daksha; Pajor, Nathan; Lee, Grace M.; Forrest, Christopher B.; Bailey, L. Charles; Pediatrics, School of MedicineBackground: As clinical understanding of pediatric Post-Acute Sequelae of SARS CoV-2 (PASC) develops, and hence the clinical definition evolves, it is desirable to have a method to reliably identify patients who are likely to have post-acute sequelae of SARS CoV-2 (PASC) in health systems data. Methods and findings: In this study, we developed and validated a machine learning algorithm to classify which patients have PASC (distinguishing between Multisystem Inflammatory Syndrome in Children (MIS-C) and non-MIS-C variants) from a cohort of patients with positive SARS-CoV-2 test results in pediatric health systems within the PEDSnet EHR network. Patient features included in the model were selected from conditions, procedures, performance of diagnostic testing, and medications using a tree-based scan statistic approach. We used an XGboost model, with hyperparameters selected through cross-validated grid search, and model performance was assessed using 5-fold cross-validation. Model predictions and feature importance were evaluated using Shapley Additive exPlanation (SHAP) values. Conclusions: The model provides a tool for identifying patients with PASC and an approach to characterizing PASC using diagnosis, medication, laboratory, and procedure features in health systems data. Using appropriate threshold settings, the model can be used to identify PASC patients in health systems data at higher precision for inclusion in studies or at higher recall in screening for clinical trials, especially in settings where PASC diagnosis codes are used less frequently or less reliably. Analysis of how specific features contribute to the classification process may assist in gaining a better understanding of features that are associated with PASC diagnoses.Item Can Multisystem Inflammatory Syndrome in Children Be Managed in the Outpatient Setting? An EHR-Based Cohort Study From the RECOVER Program(Oxford University Press, 2023) Jhaveri, Ravi; Webb, Ryan; Razzaghi, Hanieh; Schuchard, Julia; Mejias, Asuncion; Bennett, Tellen D.; Jone, Pei-Ni; Thacker, Deepika; Schulert, Grant S.; Rogerson, Colin; Cogen, Jonathan D.; Bailey, L. Charles; Forrest, Christopher B.; Lee, Grace M.; Rao, Suchitra; RECOVER consortium; Pediatrics, School of MedicineUsing electronic health record data combined with primary chart review, we identified seven children across nine participant pediatric medical centers with a diagnosis of Multisystem Inflammatory Syndrome in Children (MIS-C) managed exclusively as outpatients. These findings should raise awareness of mild presentations of MIS-C and the option of outpatient management.Item Derivation, Validation, and Clinical Relevance of a Pediatric Sepsis Phenotype With Persistent Hypoxemia, Encephalopathy, and Shock(Wolters Kluwer, 2023) Sanchez-Pinto, L. Nelson; Bennett, Tellen D.; Stroup, Emily K.; Luo, Yuan; Atreya, Mihir; Bubeck Wardenburg, Juliane; Chong, Grace; Geva, Alon; Faustino, E. Vincent S.; Farris, Reid W.; Hall, Mark W.; Rogerson, Colin; Shah, Sareen S.; Weiss, Scott L.; Khemani, Robinder G.; Pediatrics, School of MedicineObjectives: Untangling the heterogeneity of sepsis in children and identifying clinically relevant phenotypes could lead to the development of targeted therapies. Our aim was to analyze the organ dysfunction trajectories of children with sepsis-associated multiple organ dysfunction syndrome (MODS) to identify reproducible and clinically relevant sepsis phenotypes and determine if they are associated with heterogeneity of treatment effect (HTE) to common therapies. Design: Multicenter observational cohort study. Setting: Thirteen PICUs in the United States. Patients: Patients admitted with suspected infections to the PICU between 2012 and 2018. Interventions: None. Measurements and main results: We used subgraph-augmented nonnegative matrix factorization to identify candidate trajectory-based phenotypes based on the type, severity, and progression of organ dysfunction in the first 72 hours. We analyzed the candidate phenotypes to determine reproducibility as well as prognostic, therapeutic, and biological relevance. Overall, 38,732 children had suspected infection, of which 15,246 (39.4%) had sepsis-associated MODS with an in-hospital mortality of 10.1%. We identified an organ dysfunction trajectory-based phenotype (which we termed persistent hypoxemia, encephalopathy, and shock) that was highly reproducible, had features of systemic inflammation and coagulopathy, and was independently associated with higher mortality. In a propensity score-matched analysis, patients with persistent hypoxemia, encephalopathy, and shock phenotype appeared to have HTE and benefit from adjuvant therapy with hydrocortisone and albumin. When compared with other high-risk clinical syndromes, the persistent hypoxemia, encephalopathy, and shock phenotype only overlapped with 50%-60% of patients with septic shock, moderate-to-severe pediatric acute respiratory distress syndrome, or those in the top tier of organ dysfunction burden, suggesting that it represents a nonsynonymous clinical phenotype of sepsis-associated MODS. Conclusions: We derived and validated the persistent hypoxemia, encephalopathy, and shock phenotype, which is highly reproducible, clinically relevant, and associated with HTE to common adjuvant therapies in children with sepsis.Item Health Care Resource Utilization for Children Requiring Prolonged Mechanical Ventilation via Tracheostomy(AARC, 2020-08) Rogerson, Colin; Beardsley, Andrew; Nitu, Mara; Cristea, Ioana; Pediatrics, School of MedicineBACKGROUND: More children are discharged from ICUs on prolonged mechanical ventilation (PMV) via tracheostomy than ever before. These patients have long hospitalizations with high resource expenditure. Our objective was to describe the characteristics of these resource-intensive patients and to evaluate their costs of care. We hypothesized that subjects requiring PMV for neurologic diagnoses would have higher costs, longer hospital length of stay (LOS), and worse outcomes than those with primarily respiratory diagnoses. METHODS: We identified 50 pediatric subjects between January 2015 and December 2017 at our institution who had a new tracheostomy placement and were enrolled in a home mechanical ventilation program. Collected data included demographics, indication for tracheostomy, LOS, hospital costs, readmissions, and outcomes. We also compared subjects who required PMV for respiratory diagnoses versus neurologic diagnoses. RESULTS: Of 50 subjects, 41 were < 12 months old at the time of tracheostomy. Thirty-four subjects had a respiratory diagnosis requiring PMV, 14 had a neurologic diagnosis, and 2 had a cardiac diagnosis. The total initial hospitalization cost was $31,133,582, which averages to $622,671 per subject. The average initial hospitalization LOS was 155 d. Respiratory subjects had longer LOS and higher average costs than neurologic subjects. The average readmission rate was 2.16 per subject in the first year after discharge, and the average readmission cost per subject was $73,144. Eight subjects died in the first year after discharge, and 4 suffered a serious morbidity. CONCLUSIONS: This descriptive study evaluated the social and medical characteristics of subjects being discharged from the pediatric ICU with PMV via tracheostomy, as well as quantified the financial impact of their care. Those requiring PMV for neurologic diagnoses had shorter hospital LOS and lower hospital costs than those with respiratory diagnoses. No definitive differences in outcomes were found.Item Social risk factors for pediatric asthma exacerbations: A systematic review(medRxiv, 2023-09-20) Vinjimoor, Shriya; Vieira, Caroline; Rogerson, Colin; Owora, Arthur; Mendonca, Eneida A.; Pediatrics, School of MedicineObjective: This systematic review aims to identify social risk factors that influence pediatric asthma exacerbations. Methods: Cohort studies published between 2010 and 2020 were systematically searched on the OVID Medline, Embase, and PsycInfo databases. Using our established phased inclusion and exclusion criteria, studies that did not address a pediatric population, social risk factors, and asthma exacerbations were excluded. Out of a total of 707 initially retrieved articles, 3 prospective cohort and 6 retrospective cohort studies were included. Results: Upon analysis of our retrieved studies, two overarching domains of social determinants, as defined by Healthy People 2030, were identified as major risk factors for pediatric asthma exacerbations: Social/Community Context and Neighborhood/Built Environment. Social/Community factors including African American race and inadequate caregiver perceptions were associated with increased risk for asthma exacerbations. Patients in high-risk neighborhoods, defined by lower levels of education, housing, and employment, had higher rates of emergency department readmissions and extended duration of stay. Additionally, a synergistic interaction between the two domains was found such that patients with public or no health insurance and residence in high-risk neighborhoods were associated with excess hospital utilization attributable to pediatric asthma exacerbations. Conclusion: Social risk factors play a significant role in influencing the frequency and severity of pediatric asthma exacerbations.Item Ten year trends in hospital encounters for pediatric asthma: an Indiana experience(Taylor & Francis, 2021) Rogerson, Colin; He, Tian; Rowan, Courtney; Tu, Wanzhu; Mendonca, Eneida; Pediatrics, School of MedicineINTRODUCTION: Pediatric asthma is a common cause of emergency department visits, hospital admissions, and mortality. Population incidence studies have historically used large-scale survey data. We measured these epidemiologic trends using a health information exchange. METHODS: In this retrospective cohort study, we used electronic health record data from a regional health information exchange to study clinical trends in pediatric patients presenting to the hospital for asthma in the State of Indiana. Data was obtained from 2010 to 2019 and included all patients ages 2-18 years. Study participants were identified using international classification of disease codes. The measured outcomes were number of hospital encounters per year, percentage of admissions per year, and mortality rates. RESULTS: Data included 50,393 unique patients and 88,772 unique encounters, with 57% male patients. Over the ten-year period, hospital encounters ranged from 5000 to 8000 per year with no change in trajectory. Between 2010 and 2012, the percent of encounters admitted to the hospital was ∼30%. This decreased to ∼20-25% for 2015-2019. Patient mortality rates increased from 1 to 3 per 1000 patient encounters in 2010-2014 to between 5 and 7 per 1000 patient encounters from 2016 to 2019. White patients had a significantly higher admission percentage compared to other racial groups, but no difference in mortality rate. CONCLUSIONS: Asthma continues to be a common condition requiring hospital care for pediatric patients. Regional health information exchanges can enable public health researchers to follow asthma trends in near real time, and have potential for informing patient-level public health interventions.