An assessment of the isoniazid preventive therapy programme for children in a busy primary healthcare clinic in Nelson Mandela Bay Health District, Eastern Cape Province, South Africa

Background. Tuberculosis (TB) is a significant contributor to the international and national burden of disease. Global estimates suggest that there were 10.4 million new cases of TB in 2015. Children accounted for similar to 10% of these cases, although in South Africa (SA) this figure is thought to be higher. Despite clear evidence that isoniazid preventive therapy (IPT) can reduce the risk of progression from TB infection to disease in TB contacts, IPT has been poorly implemented in SA national TB control programmes. Objectives. To determine current practices regarding the identification and management of child contacts (<5 years of age) at a primary care clinic in the Nelson Mandela Bay Health District, Eastern Cape Province, SA. Methods. A cross-sectional descriptive study was conducted using a retrospective record review of infectious TB index patients aged >= 15 years. Folders of index patients with bacteriologically confirmed pulmonary TB, who started TB treatment between 21 October 2011 and 28 February 2014, were included. A sample size of 246 child contacts was required to obtain adequate power. A 95% confidence interval (CI) was used to determine statistically significant results. Results. Index patient records (N=491) were assessed and 261 child contacts identified. In a high percentage of index patient folders (87.5%; n=430), contacts were documented, although only 0.53 child contacts were identified per index patient. Of the 261 child contacts identified, 184 (70.5%) were screened for TB, 2 started TB treatment and 108/184 (58.7%) started IPT. For the remaining 74 (40.2%) children, there was no documentation of further management. Only 4 (3.7%) children completed the 24-week IPT course. Male patients reported fewer child contacts (chi(2)=7.31; p=0.01; odds ratio (OR) 0.6; 95% CI 0.42 - 0.86) and were less likely to bring contacts for screening (chi(2)=8.98; p=0.003; OR 0.41; 95% CI 0.24 - 0.72). Retreatment index patients were also less likely to bring contacts for screening (chi(2)=6.37; p=0.01; OR 0.45; 95% CI 0.25 - 0.81) and those who were screened were less likely to initiate IPT (chi(2)=4.05; p=0.04; OR 0.54; 95% CI 0.3 - 0.95). Conclusion. Despite contacts being well documented, child contacts were poorly identified. The fall-out of children at each step from identification to IPT completion was unacceptably high. Contacts of male patients and retreatment index patients were at greater risk of poor management. Recommendations to improve IPT delivery at national and local level include a review of the national IPT guidelines, considering the relative success of shorter courses of TB prophylaxis, the use of standardised IPT stationery, staff training and the involvement of community health workers in contact management.