Global, regional, and national sepsis incidence and mortality, 1990-2017: analysis for the Global Burden of Disease Study

Abstract

Background: Sepsis is life-threatening organ dysfunction due to a dysregulated host response to infection. It is considered a major cause of health loss, but data for the global burden of sepsis are limited. As a syndrome caused by underlying infection, sepsis is not part of standard Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) estimates. Accurate estimates are important to inform and monitor health policy interventions, allocation of resources, and clinical treatment initiatives. We estimated the global, regional, and national incidence of sepsis and mortality from this disorder using data from GBD 2017.

Methods: We used multiple cause-of-death data from 109 million individual death records to calculate mortality related to sepsis among each of the 282 underlying causes of death in GBD 2017. The percentage of sepsis-related deaths by underlying GBD cause in each location worldwide was modelled using mixed-effects linear regression. Sepsis-related mortality for each age group, sex, location, GBD cause, and year (1990-2017) was estimated by applying modelled cause-specific fractions to GBD 2017 cause-of-death estimates. We used data for 8·7 million individual hospital records to calculate in-hospital sepsis-associated case-fatality, stratified by underlying GBD cause. In-hospital sepsis-associated case-fatality was modelled for each location using linear regression, and sepsis incidence was estimated by applying modelled case-fatality to sepsis-related mortality estimates.

Findings: In 2017, an estimated 48·9 million (95% uncertainty interval [UI] 38·9-62·9) incident cases of sepsis were recorded worldwide and 11·0 million (10·1-12·0) sepsis-related deaths were reported, representing 19·7% (18·2-21·4) of all global deaths. Age-standardised sepsis incidence fell by 37·0% (95% UI 11·8-54·5) and mortality decreased by 52·8% (47·7-57·5) from 1990 to 2017. Sepsis incidence and mortality varied substantially across regions, with the highest burden in sub-Saharan Africa, Oceania, south Asia, east Asia, and southeast Asia.

Interpretation: Despite declining age-standardised incidence and mortality, sepsis remains a major cause of health loss worldwide and has an especially high health-related burden in sub-Saharan Africa.

Funding: The Bill & Melinda Gates Foundation, the National Institutes of Health, the University of Pittsburgh, the British Columbia Children's Hospital Foundation, the Wellcome Trust, and the Fleming Fund.

Figure 1

Age-standardised global sepsis incidence per 100 000 population, for both sexes and by underlying cause category, 1990–2017 Shaded areas represent 95% uncertainty intervals.

Figure 2

Leading 20 Level 3 causes of global incident sepsis (A) and sepsis-related deaths (B) for both sexes and all ages combined, in 1990, 2007, and 2017 Causes are connected by lines between periods (1990, 2007, and 2017); solid lines are ranked increases (or no change in rank) and dashed lines are ranked decreases. Numbers in bold highlight statistically significant changes between periods. COPD=chronic obstructive pulmonary disease. iNTS=invasive non-typhoidal salmonella.

Figure 3

Age-standardised sepsis incidence per 100 000 population for both sexes, in 2017 (A), and percentage of all deaths related to sepsis, age-standardised for both sexes, in 2017 (B) ATG=Antigua and Barbuda. FSM=Federated States of Micronesia. LCA=Saint Lucia. TLS=Timor-Leste. TTO=Trinidad and Tobago. VCT=Saint Vincent and the Grenadines.

Figure 4

Age-standardised sepsis incidence (A) and mortality (B) per 100 000 population and SDI, by location and underlying cause category for both sexes, in 2017 Every point represents one country or territory. 195 countries and territories worldwide are categorised according to SDI. SDI=Socio-demographic Index.

Figure 5

Percentage of all sepsis-related deaths in each underlying cause category, by age group and for both sexes, in 2017 Bars represent 95% uncertainty intervals.