Tuberculosis poor treatment outcomes and its determinants in Kilifi County, Kenya: a retrospective cohort study from 2012 to 2019

Background Tuberculosis (TB) is one of the leading causes of deaths in Africa, monitoring its treatment outcome is essential to evaluate treatment effectiveness. The study aimed to evaluate proportion of poor TB treatment outcomes (PTO) and its determinants during six-months of treatment at Kilifi County, Kenya. Methods We conducted a retrospective analysis of data from the TB surveillance system (TIBU) in Kilifi County, Kenya from 2012 to 2019. The outcome of interest was PTO (lost-to-follow-up (LTFU), death, transferred out, treatment failure, drug resistance) or successful treatment (cured or completed treatment). We performed time-stratified (at three months follow-up) survival regression analyses accounting for sub-county heterogeneity to determine factors associated with PTO. Results We included 14,706 TB patients, their median (IQR) age was 37 (28-50) years and 8,791 (60%) were males. A total of 13,389 (91%) were on first line anti-TB treatment (2RHZE/4RH), 4,242 (29%) were HIV infected and 192 (1.3%) had other underlying medical conditions. During 78,882 person-months of follow-up, 2,408 (16%) patients had PTO: 1,074 (7.3%) deaths, 776 (5.3%) LTFU, 415 (2.8%) transferred out, 103 (0.7%) treatment failure and 30 (0.2%) multidrug resistance. The proportion of poor outcome increased from 7.9% in 2012 peaking at 2018 (22.8%) and slightly declining to 20% in 2019 (trend test P = 0.03). Over two-thirds 1,734 (72%) poor outcomes occurred within first three months of follow-up. In the first three months of TB treatment, overweight ((aHR 0.85 (95%CI 0.73-0.98), HIV infected not on ARVS (aHR 1.72 (95% CI 1.28-2.30)) and year of starting treatment were associated with PTO. However, in the last three months of treatment, elderly age >= 50 years (aHR 1.26 (95%CI 1.02-1.55), a retreatment patient (aHR 1.57 (95%CI 1.28-1.93), HIV infected not on ARVs (aHR 2.56 (95%CI 1.39-4.72), other underlying medical conditions (aHR 2.24 (95%CI 1.41-3.54)) and year of starting treatment were positively associated with PTO while being a female (aHR 0.83 (95%CI 0.70-0.97)) was negatively associated with PTO. Conclusions Over two-thirds of poor outcomes occur in the first three months of TB treatment, therefore greater efforts are needed during this phase. Interventions targeting HIV infected and other underlying medical conditions, the elderly and retreated patients provide an opportunity to improve TB treatment outcome.