Tuberculosis (TB) is among the top 10 causes of death globally, and an estimated 10 million new cases and 1.6 million deaths occurred in 2017 [1]. Multidrug resistant (MDR) and extensively drug resistant (XDR) TB are becoming a global public health threat due to difficulty in performing drug susceptibility test (DST) and poor treatment response to existing medication [1]. An estimated 558,000 new MDR-TB/Rifampin Resistant TB cases occurred worldwide in 2017 [1]. MDR-TB refers to a Mycobacterium tuberculosis strain resistant to at least isoniazid and rifampin [2]. Rifampin resistant TB (RR-TB) is defined as a M. tuberculosis strain that is rifampin mono/poly resistant on the basis of drug susceptibility test (DST) result [2]. In this study, we defined DR-TB as M. tuberculosis resistant to any of the first line drugs that are used to treat drug susceptible TB (DS-TB) and eligible for treatment with MDR-TB regimens.

Although pediatric TB has been gaining attention in recent years, it is one of the most neglected public health problems [3,4] because low proportion of children are diagnosed and enrolled to the treatment compared to adults. TB in children accounts about 15–20% of global TB burden [4–6], and it is among the top ten causes of mortality in under-5 children worldwide [6]. Moreover, a global estimate indicated that about half a million TB cases occur per year in children younger than 15 years [5].

Diagnosis of DR-TB is the most challenging in resource limited countries due to limited laboratory infrastructure for DST and the long duration required for laboratory confirmation [4–6]. Even diagnosis of DR-TB in children is more difficult and it is rarely bacteriologically confirmed due to paucibacillary nature of the disease and the challenges in obtaining appropriate specimens [7]. A recent estimate indicates that about 25,000 to 32,000 of children develop DR-TB annually, which accounts for 3% of TB cases in children in the world [7]. Children are also at greater risk of contracting DR-TB from adult cases due to their biological and social vulnerability. The burden of the disease is also overlooked in this group of population due to difficulty in diagnosis and bacteriological confirmation [4,8]. Moreover, despite the number of children contracting DR-TB is increasing globally, still small proportion of children are detected and enrolled to the treatment [4].

Treating DR-TB cases is more expensive and difficult than treating drug-susceptible TB cases [9,10]. Moreover, second line drugs (SLDs) used for the treatment of DR-TB are more toxic and less effective than the first line drugs [9–11]. The number of drugs and duration of treatment required for the successful treatment outcome in children infected with DR-TB is unknown because of the lack of strong evidence from different countries on statistically optimum sample size [12,13]. Recently, there is some evidence on the magnitude and status of treatment outcomes of DR-TB in children [14–25]. This evidence indicates that the current treatment increases the likelihood of treatment success and has the potential of decreasing the mortality rate [14–25]. For instance, a study reported from Peru [25] shows that 77.2% of children achieved cure or probable cure. A study reported from South Africa [26] also indicated that 68% of children treated for DR-TB had the probability of curing from the disease. A systematic review and meta-analysis studies reported on children with DR-TB is also indicated considerable treatment success [12,13]. However, due to data limitation in certain settings, the World Health Organization (WHO) recommends that DR-TB treatment in children should be based on expert opinion or extrapolation of adult treatment guidelines wherever evidence on children is unavailable [27].

The current global treatment success of DR-TB is low, and only 55% of DR-TB cases were successfully treated in 2017 [1]. A recently reported review studies also indicated low (61% and 64%) DR-TB treatment success in adults [28,29]. However, DR-TB treatment success in children is relatively higher than in adults [12,13]. For instance, a meta-analysis study pooled data on 975 children with DR-TB has reported 78% treatment success [13]. Another meta-analysis study which included 315 children with DR-TB also reported 82% of treatment success [12] which is relatively higher than the previous studies’ reports on adults (61% and 64%) [28,29].

Ethiopia is among the 30 countries with high TB, TB/HIV and MDR-TB burden [1]. Although, earlier studies have indicated high treatment success of DR-TB in all age group patients in Ethiopia [30,31], there is no national or regional level report on the burden and treatment outcome status in children infected with DR-TB. However, the earlier study [31] included only 5% of patients who were younger than 18 years old and the youngest participant was 8 years old. In addition, there is limited evidence on the magnitude of children infected with DR-TB and enrolled to the treatment in the country. Therefore, we aimed to determine the proportion of children diagnosed and enrolled to the treatment in the study period, treatment outcome status and determine factors that are associated with the duration from treatment initiation to death or treatment failure in children treated for DR-TB from February 2009 to February 2019 in Ethiopia.

The current study is a national level cohort study in children diagnosed and treated for DR-TB for a ten year period in Ethiopia. Of the 3,478 DR-TB patients who were diagnosed and enrolled into the treatment, only 155 (4.5%) were children younger than 15 years old. Furthermore, DR-TB treatment enrollment proportion in children was the lowest in the years 2017 and 2018. The overall treatment success in the children was 126 (81.3%), while the overall failure event (death and treatment failure considered as a failure event) was 22 (14.2%). In this cohort, the proportion of children who died (11.6%) was considerable. Hazard of death or treatment failure was higher in children younger than 5 years, HIV sero-reactive and in children with any grade of anemia.

Our findings indicated that the proportion of children diagnosed for DR-TB and enrolled into the treatment in Ethiopia in the last ten years is low compared to reports from elsewhere [11–13,16,17,19]. This implies that the majority of the deaths that occurred in children due to DR-TB could have been undiagnosed or untreated in the country. This low treatment enrollment of children infected with DR-TB in the country is due to poor laboratory infrastructures for DST, lack of clinical experience to detect the disease, poor health seeking behavior of the family and health system delays. The proportion of treatment enrollment in 2017 and 2018 was the lowest in this cohort. This could be due to the fact that the burden of DR-TB is decreasing in the country or probably emanating from case registration related problems due to the decentralization of treatment centers to the periphery.

Our study suggests that DR-TB treatment success rate (81.3%) in children who have received a standardized long regimen was as good as the treatment successes reported from other countries [11–13,16,17,19]. For instance in line with our finding, a review study that pooled data on 315 children from eight studies indicated an excellent treatment success rate (81.7%) [12]. In addition, a review study that pooled data on 975 children reported a 78% treatment success rate [13]. These review studies’ findings are in agreement with our finding. In contrast, previous studies from elsewhere in the world have shown low treatment success (ranging from 36% to 58%) in children on DR-TB treatment [15,18]. This discrepancy is most likely due to differences in sample size between the studies, severity of the disease, TB/HIV co-infection burden and treatment regimens. For example, unlike study reported by Hall et al [18] which was performed on a large sample size of patients (423), the sample size of the study conducted by Fairle et al [15] was only 13 children, which might underestimate the treatment success rate. In contrast, other studies even reported a higher proportion of treatment success rates than our finding [14,22]. This difference is due to the quality of care in the study area, disease severity status of the children, prevalence of TB/HIV co-infection and sample size difference. Interestingly, when we compare our finding with previously reported data on adult participants, our finding indicates that the DR-TB treatment success in children is relatively better than that for adults [28–30]. A study reported from Ethiopia on both children and adults also reported a relatively lower (78.6%) treatment success rate than our finding [30], which suggests that DR-TB treatment success in children is relatively better in children than in adults. In fact, in comparison to previously reported studies in adults, mortality seemed to be lower for children than for adults [12]. The probable explanation for the low mortality rate in children than in adults is due to the paucibacillary nature of the disease in children than in adults which leads to faster bacillary clearance in children [12,21].

The mortality in children in the current study was higher than previously reported studies from different countries [14,22,25], but it was similar to other studies [19,21,23]. Moreover, the proportion of children who died in our study was almost twice the result reported by a meta-analysis that pooled eight studies on 315 children (5.9%) [12]. This difference is due to the difference in the study period, quality of care and case registration, treatment regimens used, severity of the disease during diagnosis and nutritional status of the included children.

In agreement with our finding, a previous study also indicated that HIV sero-reactive significantly predicted death in children treated for DR-TB [23]. Moreover, a study by Hall et al [18] indicated that the mortality rate is twofold higher in children who were HIV sero-reactive than those who were non-reactive. The findings of these two studies are in line with our finding in which the hazard of death or treatment failure was 5.3 times greater in HIV sero-reactive children than those who were HIV non-reactive. Moreover, a study conducted on both adults and children in Ethiopia indicated that HIV sero-reactive significantly predicted the duration from treatment beginning to treatment failure/death [31]. However, the earlier study reported from Ethiopia has included only 5% of patients who were younger than 18 years old [31]. The majority of the children co-infected with HIV in our study (12/14 = 85.7%) were on ART. In any case the significant effect of HIV sero-reactivity on treatment outcome might be due to low CD4 count, high viral load and severity of the disease at enrollment. Since data on CD4 count, HIV viral load level and disease severity status at enrollment were not registered in our data sources, we could not assess their effect on the treatment outcome.

Age younger than five years was also significantly associated with the death or treatment failure in this study. In contrast, a previous study indicates that older children are more likely to die than the younger ones [25]. This difference is due to the variation in severity of the disease at treatment initiation, treatment adherence and TB/HIV co-infection burden in the study area. In agreement with our finding, evidence indicated that immature immune system at younger age leads to poor treatment outcome [36,37].

The presence of any grade of anemia was independently associated with the duration from treatment initiation to death or treatment failure in the current study. We could not find any report that indicated the effect of anemia on the treatment outcome of DR-TB in children. However, the study reported from Ethiopia on both adults and children indicated that anemia was independently associated with time to poor treatment outcome and the hazard of poor treatment outcome was 4.2 times higher in anemic patients than non-anemic [31]. This result was similar with our finding in which the hazard of death or treatment failure was 4.3 times higher in the children with any grade of anemia than those who were non-anemic. The presence of anemia in the children at the treatment initiation might be due to malnutrition or parasitic infection.

The main strength of our study was the inclusion of relatively large number of participants, and being the first report on treatment outcome status of children with DR-TB in Ethiopia at national and regional levels. Nevertheless, this study had also limitations. As the data of this study was collected retrospectively from routine DR-TB treatment programme, the main limitation of this study was that some variables were missing. Data on many laboratory tests, weight and height of the children and adverse drug reactions were not recoded and several were missing. Moreover, due to poor record of registration and lack of laboratory results during the follow up period, there was no follow up data on treatment monitoring laboratory tests for almost all children. There were also data missing for liver and renal function enzymes tests for a considerable number of children and we obtained only baseline hemoglobin results for the included children. Thus, missing data on key variables limited our analysis to determine factors associated with duration from treatment initiation to death or treatment failure at baseline and during follow up period. In addition, apart from rifampin, there were few DST results for other first line and all SLDs for many children. This also hindered the explanation of drug susceptibility patterns and their effects on treatment outcome in children with DR-TB.

In this study, the proportion of children enrolled to DR-TB treatment was lower than the proportion of adults enrolled to the DR-TB treatment (4.5% in children versus 95.5% in adults). Our findings also suggest that children with DR-TB can be successfully treated with a standardized long regimen in a resource limited and high TB/HIV burden settings. The overall proportion of children who achieved treatment success in this study was relatively higher than the findings of the previously conducted studies on adults from Ethiopia. The hazard of death or treatment failure was significantly higher in children who were younger than 5 years old, HIV sero-reactive and in children with any grade of anemia. Further prospective cohort study is required to investigate factors contributing to the duration from the treatment initiation to death or treatment failure and low proportion of treatment enrollment. Most importantly, targeting younger children, those who are HIV sero-reactive and anemic is vital to improve DR-TB treatment success.