Burden of enteric fever at three urban sites in Africa and Asia: a multicentre population-based study

Abstract

Background: Enteric fever is a serious public health concern in many low-income and middle-income countries. Numerous data gaps exist concerning the epidemiology of Salmonella enterica serotype Typhi (S Typhi) and Salmonella enterica serotype Paratyphi (S Paratyphi), which are the causative agents of enteric fever. We aimed to determine the burden of enteric fever in three urban sites in Africa and Asia.

Methods: In this multicentre population-based study, we did a demographic census at three urban sites in Africa (Blantyre, Malawi) and Asia (Kathmandu, Nepal and Dhaka, Bangladesh) between June 1, 2016, and Sept 25, 2018. Households were selected randomly from the demographic census. Participants from within the geographical census area presenting to study health-care facilities were approached for recruitment if they had a history of fever for 72 h or more (later changed to >48 h) or temperature of 38·0°C or higher. Facility-based passive surveillance was done between Nov 11, 2016, and Dec 31, 2018, with blood-culture collection for febrile illness. We also did a community-based serological survey to obtain data on Vi-antibody defined infections. We calculated crude incidence for blood-culture-confirmed S Typhi and S Paratyphi infection, and calculated adjusted incidence and seroincidence of S Typhi blood-culture-confirmed infection.

Findings: 423 618 individuals were included in the demographic census, contributing 626 219 person-years of observation for febrile illness surveillance. 624 S Typhi and 108 S Paratyphi A isolates were collected from the blood of 12 082 febrile patients. Multidrug resistance was observed in 44% S Typhi isolates and fluoroquinolone resistance in 61% of S Typhi isolates. In Blantyre, the overall crude incidence of blood-culture confirmed S Typhi was 58 cases per 100 000 person-years of observation (95% CI 48-70); the adjusted incidence was 444 cases per 100 000 person-years of observation (95% credible interval [CrI] 347-717). The corresponding rates were 74 (95% CI 62-87) and 1062 (95% CrI 683-1839) in Kathmandu, and 161 (95% CI 145-179) and 1135 (95% CrI 898-1480) in Dhaka. S Paratyphi was not found in Blantyre; overall crude incidence of blood-culture-confirmed S Paratyphi A infection was 6 cases per 100 000 person-years of observation (95% CI 3-11) in Kathmandu and 42 (95% CI 34-52) in Dhaka. Seroconversion rates for S Typhi infection per 100 000 person-years estimated from anti-Vi seroconversion episodes in serological surveillance were 2505 episodes (95% CI 1605-3727) in Blantyre, 7631 (95% CI 5913-9691) in Kathmandu, and 3256 (95% CI 2432-4270) in Dhaka.

Interpretation: High disease incidence and rates of antimicrobial resistance were observed across three different transmission settings and thus necessitate multiple intervention strategies to achieve global control of these pathogens.

Funding: Wellcome Trust and the Bill & Melinda Gates Foundation.

Figure 1

Dates and recruitment numbers for each component of the study

Figure 2

Crude observed incidence and adjusted incidence of typhoid fever caused by Salmonella enterica serotype Typhi across the three study sites CrI=credible interval.

Figure 3

Seroincidence estimates of Salmonella enterica serotype Typhi exposure Seroincidence was calculated based on data from the serological survey, with randomly selected participants sampled approximately 3 months apart. Seroconversion was defined as a 2-fold rise increase in anti-Vi IgG titres and an absolute titre of 50 EU/mL or higher in the second sample at the second timepoint.