Skip to main content
Figure 2 | Malaria Journal

Figure 2

From: Towards a precise test for malaria diagnosis in the Brazilian Amazon: comparison among field microscopy, a rapid diagnostic test, nested PCR, and a computational expert system based on artificial neural networks

Figure 2

Performance in discriminating asymptomatic Plasmodium infections. In this investigation in an Amazonian riverine community, 380 apparently healthy individuals exhibiting no malaria-related symptoms were screened for Plasmodium infection by light field microscopy. Before the blood collection, the individuals were interviewed, and epidemiological data was obtained according to the methods. Whole blood and plasma samples were stored for nested PCR and cytokine measurements. The software MalDANN used epidemiological data only or in combination with the plasma levels of IFNgamma - and IL-10 to estimate the discrimination of the asymptomatic malaria cases. The overall performances of the field light microscopy (A) and the MalDANN (B and C) were compared using ROC curves, considering the nested PCR as the gold standard. The X-axes represent 1- specificity; the Y- axes represent sensitivity. Numbers inside the areas under the curves represent the percentages of correct diagnosis, which were statistically different using the chisquare-test (p = 0.002).

Back to article page