Peru has one of the highest incidence rates of tuberculosis (TB) in the Americas [1] despite having a well-functioning National TB Program (NTP) that regularly meets recommended World Health Organization (WHO) [2] targets. As per WHO guidelines, TB control strategies in Peru have focused on successful treatment of active TB patients and targeted case-finding in high-risk groups such as pediatric household contacts of smear-positive patients [3,4] However, molecular epidemiologic methods demonstrate that in high-burden populations extra-domiciliary exposure clearly plays a role in TB transmission even among patients with known household contacts [5]. Though extra-domiciliary TB transmission happens, few studies have evaluated the magnitude of this transmission or the venues in which this transmission occurs in TB endemic settings.

TB transmission while using public transportation has been reported [6–9]. Recent studies also suggest that using public transportation (buses/minibuses) in Lima is associated with an increased risk of TB [10–12]; if correct, these findings may have significant public health implications given the reliance of large segments of the population on buses/minibuses to commute in Lima and other major cities in TB endemic areas. These studies were limited however by a lack of appropriate comparison groups, a limited ability to control for other potential TB risk factors, or both [10–12]. We therefore undertook this study to evaluate the possible role of bus/minibus use on TB risk in Lima.

One hundred forty TB cases and 80 community controls were included in the study; 53.2% of participants were males (117/220) and 47.3% were 25–50 years old (Table 1). There was no difference between cases and control by gender, but TB cases were significantly younger [OR 0.36 (95% CI: 0.16–0.84)], less likely to be married [OR 0.27 (95% CI: 0.12–0.60)] and had less household income [OR 0.35 (95% CI: 0.15–0.81)] than controls (Table 1).

Fifty-three percent of TB cases (72/135) used a bus/minibus to commute to work compared with 30.4% (24/79) of controls [OR 3.5 (95% CI: 1.60–7.64)]. The commute time to work, regardless of the method used, also was associated with TB risk in a dose response fashion. The risk of TB increased 2.66 fold (95% CI: 1.27–5.54) for individuals with commute times ≤ 60 minutes, and over 5 fold for persons with commute times > 60 minutes [OR 5.07 (95% CI: 1.90–13.54)]. TB cases were more likely to report having had a recent household contact with TB than community controls, 25.7% (36/140) versus 3.8% (3/80), OR 8.88 (95% CI: 2.64–29.92), as well as having had a workplace contact with TB, 13% (18/139) versus 4.1% (3/73), OR 3.89, (95% CI: 1.10–13.70) (Table 1).

In the multivariate analysis, older age and higher household income remained protective against acquiring TB, with adjusted ORs of 0.19 (95% CI: 0.04–0.97) for age > 50 years old, and 0.18 (95% CI: 0.05–0.62) for a monthly household income higher than one thousand soles (approximately $300 USD), respectively. Recent household contact with an active TB patient remained independently associated with TB risk, adjusted OR of 26.37 (95% CI: 3.98–174.72), as was being divorced, adjusted OR 7.11 (95% CI: 1.00–50.44). Using a bus/minibus to commute to work also was independently associated with the risk of having TB, with an adjusted OR of 11.8 (95% CI: 1.45–96.07) (Table 2).

In this urban Lima population with high rates of TB, using buses/minibuses to commute to work was independently associated with having active TB even after controlling for other known risk factors such as household contact, socioeconomic factors and age. Regular buses/minibuses users were almost 12 times more likely to have TB than non-users. Time commuting to work was not associated with TB in the multivariate analysis, suggesting that the type of transportation used may be contributing to the dose response trend observed in the univariate analysis. These results also build on previous studies suggesting a relationship between using buses/minibuses in Lima and risk for TB by controlling for other known TB risk factors [10–12].

TB transmission through casual contact in extra-domiciliary settings has been documented [15], including while using public transportation such as buses and airplanes [6–9,15–18]. While these studies demonstrate that TB transmission can occur when using public transportation systems and that the risk of transmission increases with proximity to the index case and the duration of exposure, they have not provided an estimate of the contribution of a public transportation system use to overall risk in a TB endemic population.[16] Given the millions of individuals living in TB endemic regions around the world who use buses/minibuses for public transportation daily, even slight increases in TB risk could have substantial public health implications.

Numerous factors may contribute to an increased TB risk from regularly using bus/minibus systems in this high-risk setting. Buses and minivans in SJL are overcrowded and poorly ventilated, providing ample opportunity for transmission of airborne pathogens. This District has a high population density, significant air pollution, a congested road network and an insufficient and poorly organized public transportation system [19]. These factors, combined with among the highest TB rates in Peru and Latin America, mean that there are ample opportunities for TB transmission to occur while using buses/minibuses.

Our study has several strengths. These strengths include interviewing randomly selected controls who live and work in the same district as cases, being able to control for other known TB risk factors including socioeconomic status, known TB exposures at home and in the workplace, human immunodeficiency virus status, crowding, and age as well as having quantitative data on bus/minibus use. Recall bias and misclassification bias are potential limitations of case-controls studies. Commuting to work in our population is a common daily activity; there is no reason to suspect that TB cases would be more likely to recall using buses/minibuses than controls. TB cases were drawn from patients confirmed by acid-fast bacilli smear or culture; controls were screened for TB symptoms. Cases and controls could have used buses/minibuses for trips besides traveling to work or health facilities, but we assume that bus/minibus use to commute to work is a good proxy for overall bus/minibus use. Hence, misclassification, if it did occur, should serve to reduce the likelihood of a difference between the two groups. Exposure to TB contacts in the workplace was associated with TB risk in the univariate, but not the multivariate analyses. When workplace exposure and buses/minibuses use were added to the multivariate model, workplace exposure dropped out as a significant risk factor for TB. As another limitation, it is possible that some of the increased risk of TB being attributed to bus/minibus use to commute to work may be due to TB exposure in the workplace, but we cannot distinguish further between these two possible effects with the available data. Additional studies may help clarify an interaction, if any, between these two risk factors. Being divorced also was associated with a higher risk of TB; it is possible that being chronically ill or having TB leads to higher divorce rates rather than the reverse.

Much of the world’s growth in urbanization, and hence need for increasing buses/minibuses use, is occurring in TB endemic regions such as the greater Lima metropolitan area. Though TB transmission using public transportation happens [10–12,20,21], there are no clear recommendations regarding what steps should be taken in TB endemic areas, if any, to reduce this risk [16,22]. Our results fill a crucial gap in this debate by demonstrating, at least in SLJ, that using buses/minibuses is a substantial risk factor for acquiring TB even after controlling for other known risk factors. These data suggest that as urban populations grow and bus/minibus use expands in areas with TB risks similar to SLJ, public health officials should be aware that public transportation use may be an important contributor to TB transmission in these settings.