The study of Lee et al. \cite{Lee_2024} estimated the risk of incident tuberculosis (TB) in those diagnosed with latent TB infections (TBI) following screening. Under the current program in the Republic of Korea, only those under the age of 65 with TBI are recommended to undergo TB prevetive therapy (TPT), which is covered by national health insurance.  However, despite this provision, the incidence rate of active TB among those aged over 65 was five times higher than those under age 65, sparking vigorous debate on whether insurance coverage for TPT should be extended to all age groups. Lee et al. suggested that TPT might be less effective in reducing the risk of TB incidence among those aged over 60 (60+), with estimated adjusted hazard ratios (HRs) above one, albeit insignificant (Figure 1 in \cite{Lee_2024}). However, the interpretation of this finding requires caution. Considering the significant impact of comorbidities on increasing the risk of TB, individuals with comorbidities are more likely to be assigned to TPT and more likely to develop TB (Table 3 in \cite{Lee_2024}), suggesting that the presence of comorbidity serves as “confounding by indication” (Fig. 1) \cite{Kyriacou_2016}. While the study attempted to address this issue through multivariate adjustment, residual confounding \cite{Vansteelandt_2014} may persist, particularly when there is a notable imbalance in the comorbidity distribution between TPT recipients and nonrecipients. Specifically, the distribution of individuals with comorbidities within each age group, which is lacking in (1), may skew toward the TPT group, particularly among 60+, who are known to have a higher prevalence of comorbidities than the younger population. In this scenario, the multivariable adjustment, heavily relying on model extrapolation with limited empirical information on the TPT effect among those without comorbidities, might not fully mitigate confounding factors \cite{Vansteelandt_2014}. 

Network meta-analysis (NMA) computes treatment ranking to assist with clinical decision making, but it is not always clear how reliable the ranking is and how likely the ranking may be altered by the accumulation of new evidence. Uncertainty and robustness of ranking are two concepts related to the reliability of ranking. The uncertainty of ranking can be measured by the distribution of ranking probabilities, and the robustness of ranking can be evaluated by the agreement between treatment ranking of complete data and that of modified data with the deletion of a specific trial. However, it is still unclear whether these two approaches would always yield similar conclusions on the reliability of ranking, i.e. a robust ranking is also one of low uncertainty. The aim of this study was to investigate the relationship between the uncertainty and the robustness of treatment ranking by using normalized entropy and quadratic weighted Cohen’s kappa, respectively, to analyze 60 NMAs. We found that when the uncertainty of ranking is very low, treatment ranking is unlikely to be altered by the deletion of a trial from the complete data. However, good robustness of ranking does not always correspond to low uncertainty. An NMA with a robust treatment ranking may have high uncertainty of treatment ranking. The uncertainty of ranking prevents us from naïve interpretation of treatment ranking, and the robustness of ranking may identify trials included in the network which have a substantial influence on the treatment ranking. When an NMA is undertaken, both of them should be evaluated.