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

Abstract

Background: Accurate malaria diagnosis is mandatory for the treatment and management of severe cases. Moreover, individuals with asymptomatic malaria are not usually screened by health care facilities, which further complicates disease control efforts. The present study compared the performances of a malaria rapid diagnosis test (RDT), the thick blood smear method and nested PCR for the diagnosis of symptomatic malaria in the Brazilian Amazon. In addition, an innovative computational approach was tested for the diagnosis of asymptomatic malaria.

Methods: The study was divided in two parts. For the first part, passive case detection was performed in 311 individuals with malaria-related symptoms from a recently urbanized community in the Brazilian Amazon. A cross-sectional investigation compared the diagnostic performance of the RDT Optimal-IT, nested PCR and light microscopy. The second part of the study involved active case detection of asymptomatic malaria in 380 individuals from riverine communities in Rondônia, Brazil. The performances of microscopy, nested PCR and an expert computational system based on artificial neural networks (MalDANN) using epidemiological data were compared.

Results: Nested PCR was shown to be the gold standard for diagnosis of both symptomatic and asymptomatic malaria because it detected the major number of cases and presented the maximum specificity. Surprisingly, the RDT was superior to microscopy in the diagnosis of cases with low parasitaemia. Nevertheless, RDT could not discriminate the Plasmodium species in 12 cases of mixed infections (Plasmodium vivax + Plasmodium falciparum). Moreover, the microscopy presented low performance in the detection of asymptomatic cases (61.25% of correct diagnoses). The MalDANN system using epidemiological data was worse that the light microscopy (56% of correct diagnoses). However, when information regarding plasma levels of interleukin-10 and interferon-gamma were inputted, the MalDANN performance sensibly increased (80% correct diagnoses).

Conclusions: An RDT for malaria diagnosis may find a promising use in the Brazilian Amazon integrating a rational diagnostic approach. Despite the low performance of the MalDANN test using solely epidemiological data, an approach based on neural networks may be feasible in cases where simpler methods for discriminating individuals below and above threshold cytokine levels are available.

Figure 1

General design of the Artificial Neural Network used by the MalDANN software. (A) The neural network used by the MalDANN software was based on the Multilayer Perceptron, which consists of: (i) one input layer, where the standards and data are presented to the neural network; (ii) intermediate (or hidden) layers, where all the processing of the neural network is performed; and (iii) one output layer, in which the result of the network is presented to the observer. (B) Two software versions were created using different neural network structures to perform the diagnosis of asymptomatic Plasmodium infections. One version used epidemiological variables, and plasma levels of IL-10 and IFN-gamma were added to the epidemiological variables in the second version. (C) The intuitive interface of the MalDANN software was developed in order to facilitate the input of the data into the artificial network. * First, 31 epidemiological variables were added to the system for data mining. Of these, five variables presented very strong association with the asymptomatic malaria. The same five variables were added to the MalDANN version that used cytokine data.

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).