Abstract
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.
Highlights
There have been advancements and achievements in various fields of science, medicine
The results demonstrated that the most suitable classifier for our classification problem was multilayer perceptron (MLP) classifier; the receiver operating characteristic graph (ROC), which illustrated the diagnostic ability of a classifier model, was provided
This plot had two various threshold settings that were named as the true positive rate (TPR) against the false positive rate (FPR) [46]
Summary
There have been advancements and achievements in various fields of science, medicine. Using different methods and algorithms, the learning process of ML requires observations and labels for classification and pattern recognition, which are considered as supervised learning, to identify patterns among the data [1]. Previous researches have used various methods such as support vector machine (SVM), decision tree and different artificial neural network (ANN) structures. ANN structures were the most commonly used method in the detection and diagnosis process in various medical fields [8]. They have been surveyed in classification processes for medical decision-making from ML perspectives [9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
