HIV, malnutrition, and noncommunicable disease epidemics among tuberculosis-affected households in east and southern Africa: A cross-sectional analysis of the ERASE-TB cohort

Abstract

Background: As a result of shared social and structural risk factors, people in households affected by tuberculosis may have an increased risk of chronic conditions; at the same time, tuberculosis screening may be an opportunity for interventions. We sought to describe the prevalence of HIV, nutritional disorders, and noncommunicable diseases (NCDs) among members of tuberculosis-affected households in 3 African countries.

Methods and findings: A part of a multicountry cohort study, we screened for tuberculosis, HIV, nutritional disorders (underweight, anaemia, overweight/obesity), and NCDs (diabetes, hypertension, and chronic lung disease) among members of tuberculosis-affected households aged ≥10 years in Mozambique, Tanzania, and Zimbabwe. We describe the prevalence of these conditions, their co-occurence within individuals (multimorbidity) and household-level clustering. Of 2,109 household contacts recruited, 93% (n = 1,958, from 786 households) had complete data and were included in the analysis. Sixty-two percent were female, median age was 27 years, and 0.7% (n = 14) were diagnosed with co-prevalent tuberculosis. Six percent of household members (n = 120) had previous tuberculosis, 15% (n = 294) were living with HIV, 10% (n = 194) had chronic lung disease, and 18% (n = 347) were anaemic. Nine percent of adults (n = 127) had diabetes by HbA1c criteria, 32% (n = 439) had hypertension. By body mass index criteria, 18% household members (n = 341) were underweight while 29% (n = 549) were overweight or obese. Almost half the household members (n = 658) had at least 1 modifiable tuberculosis risk factor. Sixty-one percent of adults (n = 822) had at least 1 chronic condition, 1 in 4 had multimorbidity. While most people with HIV knew their status and were on treatment, people with NCDs were usually undiagnosed and untreated. Limitations of this study include use of point-of-care HbA1c for definition of diabetes and definition of hypertension based on single-day measurements.

Conclusions: Households affected by tuberculosis also face multiple other health challenges. Integrated approaches to tuberculosis screening may represent an opportunity for identification and treatment, including prioritisation of individuals at highest risk for tuberculosis to receive preventive therapy.

Fig 1. Flow diagram illustrating recruitment of participants and inclusion in analysis data set.

HHC, household contacts; N, number.

Fig 2. Intersection of chronic conditions (A) and cascade of care for HIV, diabetes, and hypertension (B) among adult tuberculosis household contacts (N = 1,356).

For panel A, Intersections are exclusive (i.e., individuals are only represented in the graph once) and only intersections containing at least 10 individuals are shown. The bottom sub-panel shows the included chronic conditions (y axis), with the left section indicating the overall number (N) participants with each and the right section showing the specific disease combinations (represented by black circles). The top sub-panel shows intersection size, i.e., the percentage and number of participants with each disease combination. For panel B, known (disease) was defined as a self-report of having, or being on medication for a condition; treated was defined as being on a relevant medication for the condition; controlled was defined as, for HIV, CD4 count >350 cells/μl, for diabetes, an HbA1c of <6.5% and for hypertension, as a blood pressure of <140 mmHg systolic and <90 mmHg diastolic. These are presented as relative proportions of the total number of people with each condition (100%, with number of people with disease [N] shown in sub-panel header), stratified by sex, with their 95% confidence intervals (grey lines).