High turnover stays for pediatric asthma in the United States: analysis of the 2006 Kids' Inpatient Database

Abstract

Background: Pediatric observation units provide an alternative to traditional hospitalization. The extent to which observation units could replace inpatient care for asthmatic children is unknown.

Objective: To describe brief inpatient ("high-turnover," HTO) stays for US children hospitalized with a principal discharge diagnosis of asthma, to characterize cases that may be appropriate for observation.

Design: We analyzed the 2006 Kids' Inpatient Database, a nationally representative sample of hospital discharges. HTO stays were defined as hospitalizations of 0 or 1 night in duration. We conducted descriptive statistics and case-mix adjusted, sample-weighted regression analysis of HTO stays, and associated hospital charges.

Subjects: Discharges among children aged 2 to 20 years with a principal discharge diagnosis of asthma.

Measures: HTO stays and total charges.

Results: Overall, 34,592 (34%) pediatric asthma hospitalizations were HTO, accounting for 66,278 hospital days in 2006. HTO stays were associated with younger age, uncomplicated asthma, and private insurance. Freestanding children's hospitals had the highest proportion of HTO stays, 38% (95% CI: 34%-42%) compared with 32% (95% CI: 28%-36%) for children's units and 33% (95% CI: 31%-34%) for general hospitals. In multivariate regression analyses, charges were significantly higher across hospital types when HTO stays begin in the emergency department.

Conclusions: The presence of a large number of HTO stays for children hospitalized for asthma suggests the need to explore opportunities to restructure care for this condition, perhaps through the development of physically or operationally distinct observation units.

FIGURE 1

Mean adjusted total charges for HTO stays by admission source within hospital type. The bars display mean adjusted total charges for HTO stays by admission source in the overall sample and by hospital type. The vertical lines represent the 95% confidence interval for the adjusted mean value. Charges are adjusted for patient age, APR-DRG illness severity, admission source, hospital type, hospital teaching status, and LOS.