Toward a quantitative estimate of future heat wave mortality under global climate change

Abstract

Background: Climate change is anticipated to affect human health by changing the distribution of known risk factors. Heat waves have had debilitating effects on human mortality, and global climate models predict an increase in the frequency and severity of heat waves. The extent to which climate change will harm human health through changes in the distribution of heat waves and the sources of uncertainty in estimating these effects have not been studied extensively.

Objectives: We estimated the future excess mortality attributable to heat waves under global climate change for a major U.S. city.

Methods: We used a database comprising daily data from 1987 through 2005 on mortality from all nonaccidental causes, ambient levels of particulate matter and ozone, temperature, and dew point temperature for the city of Chicago, Illinois. We estimated the associations between heat waves and mortality in Chicago using Poisson regression models.

Results: Under three different climate change scenarios for 2081-2100 and in the absence of adaptation, the city of Chicago could experience between 166 and 2,217 excess deaths per year attributable to heat waves, based on estimates from seven global climate models. We noted considerable variability in the projections of annual heat wave mortality; the largest source of variation was the choice of climate model.

Conclusions: The impact of future heat waves on human health will likely be profound, and significant gains can be expected by lowering future carbon dioxide emissions.

Figure 1

Schematic describing integration of historical mortality, weather, and air pollution data with climate model output to estimate future heat wave excess mortality. The dots are vertical ellipses indicating where other projections would go.

Figure 2

Annual excess mortality attributable to heat waves in Chicago, 2081–2100, for seven climate models under the B1, A1B, and A2 SRES (with 95% CIs reflecting statistical uncertainty in risk estimation). Full names of climate models are provided in Table 1.