Association Between Hurricane Sandy and Emergency Department Visits in New York City by Age and Cause

Abstract

The magnitude, timing, and etiology of morbidity associated with tropical cyclones remains incompletely quantified. We examined the relative change in cause-specific emergency department (ED) visits among residents of New York City during and after Hurricane Sandy, a tropical cyclone that affected the northeastern United States in October 2012. We used quasi-Poisson constrained distributed lag models to compare the number of ED visits on and after Hurricane Sandy with all other days, 2005-2014, adjusting for temporal trends. Among residents aged ≥65 years, Hurricane Sandy was associated with a higher rate of ED visits due to injuries and poisoning (relative risk (RR) = 1.19, 95% confidence interval (CI): 1.10, 1.28), respiratory disease (RR = 1.35, 95% CI: 1.21, 1.49), cardiovascular disease (RR = 1.10, 95% CI: 1.02, 1.19), renal disease (RR = 1.44, 95% CI: 1.22, 1.72), and skin and soft tissue infections (RR = 1.20, 95% CI: 1.03, 1.39) in the first week following the storm. Among adults aged 18-64 years, Hurricane Sandy was associated with a higher rate of ED visits for renal disease (RR = 2.15, 95% CI: 1.79, 2.59). Among those aged 0-17 years, the storm was associated with lower rates of ED visits for up to 3 weeks. These results suggest that tropical cyclones might result in increased health-care utilization due to a wide range of causes, particularly among older adults.

Keywords: New York City; cyclonic storms; emergency service; hospital; morbidity.

Figure 1

Daily emergency department (ED) visits occurring among individuals of all ages in New York City between October 1 and November 30, 2012, by cause. The vertical dotted line is placed on October 29, 2012, the date of Hurricane Sandy’s closest approach to New York City. In order of descending value on October 1, 2012, causes are represented with the following line types: injury and poisoning (dot dash), respiratory (long dash), cardiovascular (short dash), skin and soft tissue infections (dotted line), gastrointestinal (solid line), renal (alternating short and long dash).

Figure 2

Age-group–specific relative risks and 95% confidence intervals for the association between Hurricane Sandy and all-cause emergency department (ED) visits in New York City, 2005–2014. Results are shown from constrained distributed lag models examining associations on the day of and in the 28 days following the storm, assuming associations are homogeneous within each week after the storm (``4-week analysis''), as well as from unconstrained distributed lag models examining associations from 2 days before to 7 days after the storm (``10-day analysis''). The top row shows plots for individuals aged 65 or older: 4-week analysis (A) and 10-day analysis (B). The middle row shows plots for individuals aged 18 to 64 years: 4-week analysis (C) and 10-day analysis (D). The bottom row shows plots for individuals aged 0–17 years: 4-week analysis (E) and 10-day analysis (F). Associations on the 2 days before Hurricane Sandy are plotted in gray. All results were estimated from models comparing the number of ED visits occurring on and around the date of Hurricane Sandy's closest approach to New York City with the number of ED visits occurring on all other days between 2005 and 2014.

Figure 3

Relative risks and 95% confidence intervals for the association between Hurricane Sandy and cause-specific emergency department (ED) visits among those aged 65 or older in New York City, 2005–2014, from 2 days before to 7 days after the storm. Plots are shown for injury and poisoning (A), respiratory disease (B), cardiovascular disease (C), renal disease (D), gastrointestinal disease (E), and skin and soft tissue infections (F). Note that ED visits due to renal disease (D) are presented with a larger range of values on the y-axis than the other causes. Associations on the 2 days before Hurricane Sandy are plotted in gray. The associations presented here were estimated from unconstrained distributed lag regression models comparing the number of ED visits occurring on and around the date of Hurricane Sandy’s closest approach to New York City with the number of ED visits occurring on all other days between 2005 and 2014.