Zachary M Grinspan1, Jason S Shapiro2, Erika L Abramson2, Giles Hooker2, Rainu Kaushal2, Lisa M Kern2. 1. From the Departments of Healthcare Research and Policy (Z.M.G., E.L.A., G.H., R.K.), Pediatrics (Z.M.G., E.L.A., R.K.), and Medicine (R.K., L.M.K.), and Center for Healthcare Informatics and Policy (Z.M.G., E.L.A., G.H., R.K., L.M.K.), Weill Cornell Medical College, New York; New York Presbyterian Hospital (Z.M.G., E.L.A., R.K., L.M.K.); Department of Emergency Medicine (J.S.S.), Mount Sinai School of Medicine, New York; Health Information Technology Evaluation Collaborative (E.L.A., R.K., L.M.K.), New York; and Departments of Statistical Science (G.H.) and Biological Statistics and Computational Biology (G.H.), Cornell University, Ithaca, NY. zag9005@med.cornell.edu. 2. From the Departments of Healthcare Research and Policy (Z.M.G., E.L.A., G.H., R.K.), Pediatrics (Z.M.G., E.L.A., R.K.), and Medicine (R.K., L.M.K.), and Center for Healthcare Informatics and Policy (Z.M.G., E.L.A., G.H., R.K., L.M.K.), Weill Cornell Medical College, New York; New York Presbyterian Hospital (Z.M.G., E.L.A., R.K., L.M.K.); Department of Emergency Medicine (J.S.S.), Mount Sinai School of Medicine, New York; Health Information Technology Evaluation Collaborative (E.L.A., R.K., L.M.K.), New York; and Departments of Statistical Science (G.H.) and Biological Statistics and Computational Biology (G.H.), Cornell University, Ithaca, NY.
Abstract
OBJECTIVES: To describe (1) the predictability of frequent emergency department (ED) use (a marker of inadequate disease control and/or poor access to care), and (2) the demographics, comorbidities, and use of health services of frequent ED users, among people with epilepsy. METHODS: We obtained demographics, comorbidities, and 2 years of encounter data for 8,041 people with epilepsy from a health information exchange in New York City. Using a retrospective cohort design, we explored bivariate relationships between baseline characteristics (year 1) and subsequent frequent ED use (year 2). We then built, evaluated, and compared predictive models to identify frequent ED users (≥4 visits year 2), using multiple techniques (logistic regression, lasso, elastic net, CART [classification and regression trees], Random Forests, AdaBoost, support vector machines). We selected a final model based on performance and simplicity. RESULTS: People with epilepsy who, in year 1, were adults (rather than children or seniors), male, Manhattan residents, frequent users of health services, users of multiple health systems, or had medical, neurologic, or psychiatric comorbidities, were more likely to frequently use the ED in year 2. Predictive techniques identified frequent ED visitors with good positive predictive value (approximately 70%) but poor sensitivity (approximately 20%). A simple strategy, selecting individuals with 11+ ED visits in year 1, performed as well as more sophisticated models. CONCLUSIONS: People with epilepsy with 11+ ED visits in a year are at highest risk of continued frequent ED use and may benefit from targeted intervention to avoid preventable ED visits. Future work should focus on improving the sensitivity of predictions.
OBJECTIVES: To describe (1) the predictability of frequent emergency department (ED) use (a marker of inadequate disease control and/or poor access to care), and (2) the demographics, comorbidities, and use of health services of frequent ED users, among people with epilepsy. METHODS: We obtained demographics, comorbidities, and 2 years of encounter data for 8,041 people with epilepsy from a health information exchange in New York City. Using a retrospective cohort design, we explored bivariate relationships between baseline characteristics (year 1) and subsequent frequent ED use (year 2). We then built, evaluated, and compared predictive models to identify frequent ED users (≥4 visits year 2), using multiple techniques (logistic regression, lasso, elastic net, CART [classification and regression trees], Random Forests, AdaBoost, support vector machines). We selected a final model based on performance and simplicity. RESULTS:People with epilepsy who, in year 1, were adults (rather than children or seniors), male, Manhattan residents, frequent users of health services, users of multiple health systems, or had medical, neurologic, or psychiatric comorbidities, were more likely to frequently use the ED in year 2. Predictive techniques identified frequent ED visitors with good positive predictive value (approximately 70%) but poor sensitivity (approximately 20%). A simple strategy, selecting individuals with 11+ ED visits in year 1, performed as well as more sophisticated models. CONCLUSIONS:People with epilepsy with 11+ ED visits in a year are at highest risk of continued frequent ED use and may benefit from targeted intervention to avoid preventable ED visits. Future work should focus on improving the sensitivity of predictions.
Authors: John Billings; Ian Blunt; Adam Steventon; Theo Georghiou; Geraint Lewis; Martin Bardsley Journal: BMJ Open Date: 2012-08-10 Impact factor: 2.692
Authors: Nancy J Thompson; Robin E McGee; Amanda Garcia-Williams; Linda M Selwa; Shelley C Stoll; Erica K Johnson; Robert T Fraser Journal: Epilepsy Behav Date: 2019-10-22 Impact factor: 2.937
Authors: Anup D Patel; Andrea Debs; Debbie Terry; William Parker; Mary Burch; Debra Luciano; Lauren Patton; Jena Brubaker; Julie Chrisman; Kathy Moellman; James Herbst; Daniel M Cohen Journal: Neurol Clin Pract Date: 2021-10
Authors: Anup D Patel; Debbie Terry; Jayne Pacheco Moore; Jacy Sale; Eric G Wood; Zachary M Grinspan; Daniel M Cohen Journal: Neurol Clin Pract Date: 2016-12
Authors: Benjamin D Wissel; Hansel M Greiner; Tracy A Glauser; John P Pestian; Andrew J Kemme; Daniel Santel; David M Ficker; Francesco T Mangano; Rhonda D Szczesniak; Judith W Dexheimer Journal: Acta Neurol Scand Date: 2021-03-26 Impact factor: 3.915