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 8,041people 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 111 ED visits in year 1, performed as well as more sophisticated models. Epilepsy is an ambulatory care sensitive condition; that is, high quality outpatient care may reduce unnecessary inpatient and emergency department (ED) care.
Conclusions:1-5 Thus, frequent ED use is a "health services marker," indicating inadequate disease control and/or poor access to care. 6 Health care organizations in the United States, encouraged by recent state and federal policy changes, frequently hire care managers to coordinate care for people with ambulatory care sensitive conditions such as epilepsy.7-9 One common strategy is to focus on patients at high risk of frequent ED use.10 For people with epilepsy, several factors are associated with frequent ED use: low socioeconomic status, more seizures, anxiety, poor knowledge of epilepsy by self or caregivers, and greater stigma.11-13 However, the predictability of frequent ED use is understudied. Studying frequent ED use is challenging, in part because people often use multiple EDs for care.14,15 Health information exchange (HIE) networks allow users to view medical information in the electronic health records of multiple unaffiliated institutions, creating a more complete record than possible from a single center's data.14 These technologies are increasingly available, 16,17 and may provide a data source to describe and predict frequent ED use.From the