A novel diagnostic and prognostic approach for unresponsive patients with anthroponotic cutaneous leishmaniasis using artificial neural networks.

Cutaneous leishmaniasis (CL) imposes a major health burden throughout the tropical and subtropical regions of the globe. Unresponsive cases are common phenomena occurred upon exposure to the standard drugs. Therefore, rapid detection, prognosis and classification of the disease are crucial for selecting the proper treatment modality. Using machine learning (ML) techniques, this study aimed to detect unresponsive cases of ACL, caused by Leishmania tropica, which will consequently be used for a more effective treatment modality. This study was conducted as a case-control setting. Patients were selected in a major ACL focus from both unresponsive and responsive cases. Nine unique and relevant features of patients with ACL were selected. To categorize the patients, different classifier models such as k-nearest neighbors (KNN), support vector machines (SVM), multilayer perceptron (MLP), learning vector quantization (LVQ) and multipass LVQ were applied and compared for this supervised learning task. Comparison of the receiver operating characteristic graphs (ROC) and confusion plots for the above models represented that MLP was a fairly accurate prediction model to solve this problem. The overall accuracy in terms of sensitivity, specificity and area under ROC curve (AUC) of MLP classifier were 87.8%, 90.3%, 86% and 0.88%, respectively. Moreover, the duration of the skin lesion was the most influential feature in MLP classifier, while gender was the least. The present investigation demonstrated that MLP model could be utilized for rapid detection, accurate prognosis and effective treatment of unresponsive patients with ACL. The results showed that the major feature affecting the responsiveness to treatments is the duration of the lesion. This novel approach is unique and can be beneficial in developing diagnostic, prophylactic and therapeutic measures against the disease. This attempt could be a preliminary step towards the expansion of ML application in future directions.

Host's immune response in unresponsive and responsive patients with anthroponotic cutaneous leishmaniasis treated by meglumine antimoniate: A case-control study of Th1 and Th2 pathways.

The objective of the present study was to compare the host's immune responses between unresponsive and responsive patients with anthroponotic cutaneous leishmaniasis (ACL) treated by meglumine antimoniate. A case-control study was carried out in an endemic focus in Iran. Blood samples were taken from patients and peripheral blood mononuclear cells (PBMCs) were isolated. Two wells were considered for each isolate of unresponsive and responsive patients; one was exposed to L. tropica (Lt-stimulated cells) and the other remained non-exposed (non-stimulated cells). After 24 h of incubation, whole RNA was extracted from each sample. Real-time quantitative PCR was carried out to confirm the differences in expression levels of IL-12 P40, IFN-γ, IL-1ß, IL-4 and IL-10 among isolates. Data were analyzed and P < 0.05 was considered to be statistically significant. In our study, Lt-stimulated cells and non-stimulated cells in unresponsive groups demonstrated significantly lower expression levels of IL-1ß, IL-12 P40 and IFN-γ genes and higher expression levels of IL-4 and IL-10 genes, compared to Lt-stimulated cells and non-stimulated cells in responsive groups. There was a negative correlation between IL-12 P40 with IL-10 and IL-1ß with IL-10 in ACL Lt-stimulated cells in unresponsive group, while a positive correlation between IL-12 P40 with IL-1ß and IL-12 P40 with IFN-γ in ACL Lt-stimulated cells in responsive group. Probably, different immune responses caused by various factors play a major role in the pathogenesis and development of unresponsiveness in ACL patients. The profile and timing of cytokine production correlated well with the treatment outcome of Leishmania infection.