Human visceral leishmaniasis (VL) caused by Leishmania infantum is a neglected, yet severe, zoonotic disease that occurs mainly in Latin America and in the Mediterranean region [1]. Dogs are the main reservoir of L. infantum parasites that are transmitted to humans by the bite of infected phlebotomine sandflies. In humans, the infection can be asymptomatic or lead to an acute form characterized by irregular fever, weight loss, splenomegaly, hepatomegaly, anaemia or pancytopenia [2]. If left untreated, the infection is often fatal. Accurate diagnosis, which is crucial to control the infection, relies on epidemiological data, clinical features, and laboratory tests. Parasite detection by microscopic examination of bone marrow aspirates is the gold standard method, but lacks sensitivity and requires invasive procedures [3]. The culture of parasites isolated from patients might improve the diagnostic sensitivity. The search of specific antibodies in serum or plasma, while requiring non-invasive sampling, remains the most widely used method for VL diagnosis. However, serological tests tend to be less sensitive in children younger than three years [4,5] and in immunocompromised patients [6,7]. Currently, molecular detection is considered the most reliable method [8,9], with a sensitivity higher than 95% for PCR analysis on peripheral blood [10]. Yet, such technique is restricted to well-equipped laboratories and is often combined with serological tests in the routine practices [3].

Various methods are used for VL serodiagnosis. The qualitative detection of Leishmania antibodies is based on Western blot (WB) method and immunochromatographic tests (ICT), whereas quantitative results are obtained by indirect immunofluorescence, direct agglutination, and enzyme-linked immunosorbent assays (ELISA). The WB technique, using L. infantum antigenic fractions, is a highly sensitive and specific method to confirm VL serodiagnosis [11,12]. This technique is time-consuming and quite expensive, thus complex to implement for field surveys and initial serological screenings. Conversely, ICT which are based on the recombinant Leishmania rk39 antigen, are well adapted for field testing. Indeed, they are fast and easy to perform, and display good performances for early VL diagnosis [13]. Among the quantitative methods, ELISA based on crude soluble antigens or the recombinant rk39 protein, are widely used for initial screening of VL [3,7], but their performances are influenced by the nature, purity and stability of the used antigens [14]. In this context, commercial kits may offer more uniform procedures for antigen preparation, compared with home-made assays, and provide standardized experimental conditions. However, large-scale studies comparing the performances of commercial assays are lacking [5,7]. A recent study in Brazil compared, for the first time, different kits tested in the same condition and in the same population [5]. Similarly, in the present study, we evaluated the performances of six commercial tests for the diagnosis of human VL in the Mediterranean region. We compared the sensitivity and specificity of two ICT and four ELISA kits, re-evaluated their positivity thresholds, and analysed their advantages and drawbacks for routine diagnosis. Finally, we use a Western blot technique to confirm the serological status of VL and healthy patients, and discuss discrepant positive results obtained in some asymptomatic patients living in the South of France, a VL endemic area in the Mediterranean basin.

This study complies with the updated Standards for Reporting of Diagnostic Accuracy (STARD) statement [15]. The STARD checklist and a diagram reporting the flow of participant through the study are presented in S1 Checklist and S1 Fig, respectively.

During the last 70 years, various methods have been used for the serodiagnosis of VL caused by L. infantum in humans [17], including commercial kits that require qualifications with specific information about their performance [5]. In this study, we evaluated the analytical performances of commercially available kits based on different methods: ELISA, ICT and WB. One of the limitations of this study is that we did not include immunocompromised patients in the healthy population. Consequently, we could not compare the tests’ accuracy in function of the immune status. In addition, the control group did not include patients with diseases known to cross-react with anti-Leishmania antibodies (i.e. tuberculosis, trypanosomiasis, toxoplasmosis, leprosy or auto-immune diseases [3,7]). The use of a healthy population may have influenced the high specificity observed for all tests (>95%).

Among the six assays used for antibody screening, none reached the recommended sensitivity of 95% for VL diagnosis (14). Therefore, we lowered the positivity thresholds of the ELISA reagents to obtain a sensitivity of 95% with the highest possible specificity. As no grey zone is defined by the manufacturer of Bordier, we recommend interpreting the index values between 0.7 and 1 as equivocal or positive results. By using these cut-off values, the Bordier kit displayed the highest specificity (>99%). We propose to broaden the cut-off values recommended by the Vircell manufacturer from 9–11 to 8–11, yielding a specificity comparable to that of Bordier. We also suggest reducing the NovaLisa positivity threshold from 9 to 6, although this would entail a significant decrease of specificity and the use of additional confirmation tests, compared with the Bordier and Vircell assays. Moreover, the cut-off values (1.5–11) of the Ridascreen kit required to achieve a sensitivity of 95% significantly reduced specificity (81.9%), therefore making this test less suitable for routine screening.

Few studies evaluated ICT performance for the diagnosis of zoonotic VL [16]. However, commercial ICT kits represent the best choice for rapid, easy and efficient serological screening of VL [17]. In this study, the performances of TruQuick and IT-LEISH were lower than those of the Bordier and Vircell ELISA kits, but their estimated accuracy was comparable to that of NovaLisa and higher than that of the Ridascreen ELISA kits in the whole population. ICT present several advantages compared with ELISA kits in term of practicability. First, TruQuick and IT-LEISH can be performed also on whole blood, thus facilitating screening in field settings. It should be noted that the performances of several commercial ICT kits on whole blood were found comparable to those obtained in serum samples [18]. Second, they provide qualitative results in 15–25 minutes compared to the 2.5–3.5 hours with ELISA kits. Moreover, the sample volume required for ICT is lower than for ELISA when using automated processors.

Recently, Freire et al. compared one ICT (IT LEISH) and three ELISA (Vircell, Novalisa and Ridascreen) kits in Brazil [5]. The overall specificity of these commercial kits (>95% in the whole population) was comparable in our study and in the work by Freire et al., except for Ridascreen (specificity <85% in Brazil). Conversely, while Ridascreen displayed the highest sensitivity value in Brazil, we found that this test had the lowest sensitivity among all kits we evaluated. On the other hand, the sensitivity and specificity of the IT LEISH ICT were similar in both studies, although our values were slightly higher in the whole population. These differences might be explained by antigen variability in parasites from different geographic regions and by cross-reactivity with other endemic pathogens, as highlighted by the World Health Organization (WHO) evaluation of ICT [19]. Finally, like Freire et al. [5] and other works [6,7] that reported lower performances of serodiagnostic tests in immunocompromised patients, we found a higher number of false-negative results in immunocompromised individuals with VL. In Europe, a meta-analysis concluded that serological tests should not be used to rule out a diagnosis of VL among HIV-infected patients [20]. In a recent study in Spain, the sensitivity of the rk39-ICT dropped from 78% to 67.3% in this population [21]. These results support the use of molecular assays as an alternative method for VL diagnosis in immunocompromised patients.

Regarding WB, this technique is currently used to confirm the positive results obtained by serological screening. Its specificity should be discussed by taking into account the existence of asymptomatic carriers. The Leishmanin skin test [22], blood culture [23], and WB [11,12] could indeed detect infection or parasite contact in patient without VL. Here, 10.1% of the control population was positive by WB. This value is consistent with a larger study performed in Italy showing 7.41% of asymptomatic carriers by WB [24]. Thus, a positive result by WB should be discussed and interpreted on the basis of the biological and clinical data to discriminate between disease and asymptomatic carriage.

In conclusion, the Vircell and Bordier ELISA kits displayed significantly higher accuracy rates in the whole population than the other tests. Nevertheless, we had to decrease the cut-off values to improve the performance of the four ELISA tests. For field studies, the TruQuick ICT is the most suitable with satisfactory performances. In immunocompromised patients, the index values of all ELISA reagents were significantly lower than in the immunocompetent population and false-negative results were more frequent, as shown previously [20]. This kits comparison might help to select the most suitable method, using the most appropriate thresholds, and to better understand the limitations of each test.