In developing countries, leptospirosis is an emerging health problem affecting urban slum communities [1]–[4]. Annual epidemics of the disease typically occur during periods of seasonal rainfall [1], [5]–[8]. Lack of sanitation infrastructure such as open sewage systems and poor refuse collection services provide conditions for proliferation of rats, which are the main reservoir for leptospirosis in urban settings [1], [9]–[11]

Pathogenic Leptospira infection produces a broad spectrum of clinical manifestations with case fatality exceeding 10% and 50% for Weil's disease and severe pulmonary hemorrhage syndrome, respectively [2], [12], [13]. Currently, there are no effective interventions which can be easily implemented in slum communities to prevent leptospirosis transmission. Rat-control programs are commonly implemented as a control measure for leptospirosis in many cities, such as those in Brazil, but their effectiveness is questionable and has not been systematically explored.

In this setting, two rat species, the Norway rat (Rattus norvegicus) and black rat (Rattus rattus), are the main reservoirs for this bacterium and contaminate environments via urinary shedding, providing conditions for transmission to humans [2]. Prior studies in urban areas have shown that Leptospira carriage ranges between 7–82% for R. norvegicus [14], [15] and between 7–34% for R. rattus [16], [17]. However, the Norway rat is far more common within the urban slum environments: nearly 100% of rats trapped in the city of Salvador, Brazil comprised of this species [14], [15], [18]. Leptospira strains isolated from Norway rats were genotypically identical with strains obtained from human patients based on PCR-based typing methods [19]. Additionally, epidemiological studies have found that peri-domiciliary resident reporting of rat sightings and living in proximity to open sewers placed residents at increased risk for leptospiral transmission in slum areas [5], [10]. These findings support the role of urban peri-domestic transmission due to contact with water contaminated with rat urine.

Rodent control programs based on environmental application of a chemical rodenticide [20] as an strategy to reduce the incidence of leptospirosis are costly and their effectiveness has not been evaluated [20], [21]. Programs implemented in Brazil [20] are based on the Centers for Disease Control and Prevention (CDC) approach for pest management [22] which includes an environmental form to assess rodent infestation levels and infrastructural deficiencies in peridomestic areas. Nevertheless, the CDC survey form has not been validated for application in slum areas of developing countries. Furthermore, no studies have systematically examined whether indicators of rodent infestation assessed during rodent surveys can be used to predict leptospirosis risk and, therefore, guide targeted interventions specifically implemented among high risk households. Herein, by using a community-based cohort study aimed to evaluate Leptospira infection, we describe an environmental and rodent survey instrument, adapted from CDC guidelines, for use in a tropical slum area. In addition, we developed and evaluated the accuracy of a scoring system to predict Leptospira transmission using data easily produced by this instrument.

As previously described, we enrolled 2,003 participants from 684 households in a community cohort study designed to measure risk factors and infection rates for leptospirosis [11]. Of these, 1,585 (79%), 1,324 (66%) and 1,394 (70%) participants completed the first, second and third year of follow-up, respectively. We identified 104 Leptospira infections in 97 participants residing in 80 households during the three year study period. We identified fifty-one infections (49%) in the first year, 26 (25%) in the second and 27 (26%) in the third year. In all but four cases (96%), L. interrogans serogroup Icterohaemorrhagiae was identified as the presumptive infectious serogroup based on agglutination titers. A majority of the case households (63, 79%) had a single participant with evidence of infection, while 17 (21%) case households had two participants. Seven participants had serologic evidence of two exposures. In addition to the 80 households defined as case-households we also included 115 households, out of a possible 186, meeting inclusion criteria as controls.

We performed environmental surveys in 189 (97%) of the 195 households (80 case and 109 control households). Six control households could not be inspected because no persons were present during at least three attempted visits. The final number of case and control households included in this study was 80 and 109, respectively. We observed that case households had a higher number of inhabitants and number of subjects enrolled in the cohort study than control subjects (4 [IQR: 4–6] vs. 4 [3]–[5], respectively, Table 1; and 4 [IQR: 2–5] vs. 3 [2]–[4], respectively, P<0.05). Other characteristics regarding environment and rodent signs, of case and control households with comparative bivariate values of p<0.1 (inclusion criterion for logistic regression analyses), are shown in Table 1.

We detected rodent infestation (presence of at least one rodent sign) in 63 (78%) of the case and 46 (42%) of control households. Rat burrows were frequent signs of rodent infestation (65% and 29% for case and control households, respectively). A total of 101 among the 189 households surveyed, had fecal droppings, 77% were from R. norvegicus, 10% from M. musculus and 4% from R. rattus; feces from a non-identified species were present at 9% households. Overall, the presence of R. norvegicus fecal droppings had good concordance with presence of any rodent burrow (kappa = 0.61) and a moderate concordance with any rodent run (kappa = 0.51).

Eighty (42%) households, 35 cases and 45 controls, had structural, sewage or trash modifications between the year of Leptospira infection and date of environmental survey. Case households with modifications were compared with case households lacking modifications. The same analysis was performed for control households. There were no significant differences among the study variables between groups (data not shown) and all 189 households were considered for further analyses.

In bivariate analyses, we identified 13 environmental variables which were associated (P<0.05) with case households (Table 1). A larger percentage of case households (P<0.01) showed signs of rodent infestation related to R. norvegicus. Additionally, the presence of a case of Leptospira infection in a household was associated with low socioeconomic status as per capita income and number of inhabitants in the house. Residents of a large number of case and control households were squatters, 91% and 86% respectively. We did not identify significant differences between case and control households with respect to the presence or number of dogs, cats or chickens (data not shown). Residents also reported ownership of other species of animals as ducks, small birds, rabbits, hamsters, monkeys and turtles, but the presence/number of these animals was not associated with differences in Leptospira infection among residents of case and control households.

The first multivariate logistic regression model, including variables related to household environment, retained the following characteristics: rodent access to water, domicile built on a slope and un-plastered exterior wall surfaces. The second model, including rodent infestation variables, retained the presence of R. norvegicus fecal droppings and rodent burrows. The final model retained four variables: two household environmental variables and two rodent infestation factors (Table 2). R. norvegicus fecal droppings had the strongest association with case households in the final model followed by rodent burrows, rodent access to water and un-plastered exterior wall surface.

To build a risk score, we assigned numerical scores to each of the four independent variables from the final model proportionate to the regression coefficient for each variable (Table 2). The sum of the number was used to classify each household into ten categories ranging from 0 to 9. None of the households received 1 or 8 points. Five percent of the case households and 30% of the control households had a score value of 0. Because score values were not normally distributed within case and control households, we used Wilcoxon rank-sum tests to compare the scores by case status. The median risk score for case households was 7, statistically different from the value of 2 for control households (p<0.001). Receiver operator curve (ROC) analysis yielded a very good to excellent c statistic of 0.78 (95 percent confidence interval: 0.71–0.84) (Figure 2). Table S2 presents the sensitivity, specificity and the estimated proportion of the case and cohort households for each score level.

High levels of rodent infestation and the predominance of Rattus norvegicus are frequent features within urban slum areas, in Brazil and around the world. Efforts to implement and improve rodent management interventions to reduce urban leptospirosis have been hampered by the lack of readily available information and epidemiologically-based markers that allow identification and monitoring of households at increased risk for infection. Our study demonstrates not only the large proportion of houses in a typical Brazilian slum at risk of acquiring Leptospira transmission, but also that the risk is significantly associated with four markers of rodent infestation and environmental factors (R. norvegicus feces, rodent burrows, access to water, un-plastered walls). The risk score system we developed, by weighting and combining values for each of these features, accurately classified households into risk groups for Leptospira infection with high precision. Of note, similar household-based markers of rodent infestation and infection risk have been described in association with Lassa fever [31] and hantavirus pulmonary syndrome [32]. We propose that targeting households at higher predicted risk for leptospirosis for augmented chemical, environmental and educational interventions would result in the greatest reduction of Leptospira transmission.

Our summary score value for high risk environments is easy to use and increases accuracy in identifying high risk households. The score performed well in discriminating case from control households with an accuracy of 0.78 and a sensitivity and specificity at a point value of 3 of 80% and 60%, respectively. These findings are encouraging and suggest that this tool could help inform more aggressive rat control to household locations with similar risk profiles without increasing the current workload of zoonotic control assessment teams.

Our scoring method could benefit other cities in Brazil and other countries where rodent control programs are the principal strategy to decrease leptospirosis incidence [20]. Rodent control programs are time-consuming and expensive, as they require large numbers of trained persons. In Salvador alone, the ZCC programs prioritize target areas with 20,000–60,000 households in locations where a high incidence of leptospiral disease (21.4 cases per 100,000 pop. in 2008 [unpublished data]) has been detected. Considering the coverage of the ZCC program in cities such as Salvador in Brazil and the leptospirosis incidence in these urban centers, it may be feasible to use changes of leptospiral disease incidence to evaluate the efficacy of enhanced targeted rat-control strategies which include the proposed score.

Although our study focused on a single area within Salvador, it would be useful to assess the utility of our measure to predict risk of leptospiral infection in other slum areas. However, this will require some tailoring of the survey instrument to some other locations, as every slum has unique characteristics and significant socioeconomic and environmental heterogeneities [33] within the broad definition for slum settlement as proposed by the United Nations [34]. Additionally, information regarding the incidence of leptospiral infection as determined by annual serosurvey is costly and labor-intensive, consequently such studies are a rarity. In the few reports where geocoded data for leptospirosis are available [35], spatial information has been restricted to outcomes of hospitalized cases of severe leptospirosis. The absence of other prospective studies to evaluate Leptospira infection prevented us from performing an external validation to evaluate the accuracy of our score in other settings. However, even with these limitations it may be possible to test the external validity of our survey methods and subsequent risk-scoring within a large area of Salvador and within other Brazilian cities where up to 33% of the urban population has equal or greater levels of poverty as found in our study community [23].

We identified two environmental risk factors, access to water and un-plastered walls, which were associated with an increased risk of Leptospira infection. Our finding that the presence of standing water, including sewer water, increases the risk of acquiring Leptospira infection, builds on our group's prior findings that household proximity to open sewers is associated with both Leptospira infection and severe disease in humans [5], [10], [11]. This may reflect the need of rats to a ready access of water as suggested by previous studies [36]–[38], and the capacity of open sewers to serve as environmental features contributing to the risk of leptospiral transmission to humans [9]. Infrastructural deficiencies, such as the presence of un-plastered walls in the home, were significantly associated with case households, and are a characteristic presumed to increase the probability of rat ingress into residences. However, Rattus norvergicus, which was the predominant rodent in the study area, typically resides outdoors and consequently it is more probable that un-plastered walls serve as a proxy for socioeconomic status than a proxy of rodent infestation. In conjunction, these specific household environmental and rodent infestation characteristics showed to be objective markers of Leptospira transmission.

This study provides further evidence of the importance of rats in urban leptospirosis transmission. The high household infestation rate, elevated Leptospira prevalence [15] and long term carriage [39] making R. norvegicus a major reservoir host for leptospires. We did not evaluate Leptospira carriage in domestic animals such as dogs. It is possible that dogs, which are often found in poor urban communities and may be infected with serovar Copenhageni [40], could contribute to the transmission cycle. However we think this is unlikely in our study area because this and other studies did not identify an epidemiological link between dogs and human Leptospira infection or leptospirosis [5], [10], [11].

We successfully identified environmental features associated with higher infection risk, but our study was limited by the time lag between occurrence of Leptospira infection and assessment of housing rodent survey. However, we showed that the four major causes of temporal modification in a household or environs (i.e. rebuilding or expansion; closing or creation of a nearby open sewer and removal or creation of refuse deposits since the year of Leptospira infection) did not influence environmental or infestation measures among case or control households. We did not evaluate the characteristics of the places where participants with Leptospira infection worked. However previous studies have found strong associations between risk of leptospiral transmission and environmental conditions around the case household, irrespective of work location [5], [10], [11], so we believe our findings are plausible and consistent.

We used serologically confirmed cases of subclinical Leptospira infection to define case households. Notwithstanding, it is likely that mild or subclinical Leptospira infection and clinical disease share the same environmental risk exposures. A previous study showed that members of households living with an index case of clinical leptospirosis were more likely to have serologic evidence for a prior infection than members of other households in the same communities [41]. Additionally, environmental deficiencies such as presence of open sewer near of the household and sighting rats in the peridomiciliary environment were independent risk factors for both severe leptospirosis [5] and Leptospira infection [10], [11].

In conclusion, we developed a risk score based on four variables related to objective signs of rodent infestation and environmental features that predict risk of Leptospira infection among persons living in households located within urban slums of Salvador. These findings have the potential to better inform policymakers and rodent management programs by identifying high-risk households and areas for frequent interventions and reducing effort directed at lower risk households and neighborhoods.