Undertreated HIV and drug-resistant tuberculosis at a referral hospital in Irkutsk, Siberia

Abstract

Setting: A referral hospital for tuberculosis (TB) in Irkutsk, the Russian Federation.

Objective: To describe disease characteristics, treatment and hospital outcomes of TB-HIV (human immunodeficiency virus).

Design: Observational cohort of HIV-infected patients admitted for anti-tuberculosis treatment over 6 months.

Results: A total of 98 patients were enrolled with a median CD4 count of 147 cells/mm(3) and viral load of 205 943 copies/ml. Among patients with drug susceptibility testing (DST) results, 29 (64%) were multidrug-resistant (MDR), including 12 without previous anti-tuberculosis treatment. Nineteen patients were on antiretroviral therapy (ART) at admission, and 10 (13% ART-naïve) were started during hospitalization. Barriers to timely ART initiation included death, in-patient treatment interruption, and patient refusal. Of 96 evaluable patients, 21 (22%) died, 14 (15%) interrupted treatment, and 10 (10%) showed no microbiological or radiographic improvement. Patients with a cavitary chest X-ray (aOR 7.4, 95%CI 2.3-23.7, P = 0.001) or central nervous system disease (aOR 6.5, 95%CI 1.2-36.1, P = 0.03) were more likely to have one of these poor outcomes.

Conclusion: High rates of MDR-TB, treatment interruption and death were found in an HIV-infected population hospitalized in Irkutsk. There are opportunities for integration of HIV and TB services to overcome barriers to timely ART initiation, increase the use of anti-tuberculosis regimens informed by second-line DST, and strengthen out-patient diagnosis and treatment networks.

Figure

Comparison of MIC within the class of second-line aminoglycosides by MYCOTB Sensititre (Trek Diagnostics). Green/dark grey = susceptible (MIC ≤2 dilutions below critical concentration using the agar proportion method); yellow/pale grey = borderline susceptible (MIC at or within one dilution of critical concentration); red/black =resistant (MIC more than two dilutions above). No isolate was of borderline susceptibility for amikacin. * P = 0.003 for difference in resistance using critical concentration by agar proportion method as breakpoint. This image can be viewed online in color at http://www.ingentaconnect.com/content/iuatld/ijtld/2016/00000020/00000001/art00011.