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

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.

Artificial Intelligence in Cutaneous Leishmaniasis Diagnosis: Current Developments and Future Perspectives

“…Table 1 presents a summary of the studies that were analyzed as part of this research. Bamorovat et al [19] presented a Machine Learning-based approach to identify unresponsive cases of ACL caused by L.…”

Mutual Role of Patients and the Healthcare System in the Control of Cutaneous Leishmaniasis

“…In a time of restriction and contraindication for choice drug therapy, other drugs such as lipid formulations of amphotericin B (AmBisome ® ), paromomycin, miltefosine, ketoconazole, itraconazole, and fluconazole and also multiple therapies as a combination, could be used [31]. In general efficacy of MA against ACL, is high; however, cases of treatment failures (unresponsiveness) have been reported [25,[32][33][34][35].…”

Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence

“…Recent advances in artificial intelligence (AI) have revolutionized medicine, with machine learning (ML) algorithms and their identification capacity having an important application to help diagnosis [15][16][17][18]. Furthermore, dermatology has benefited from novel diagnostic tools.…”

“…However, there are few studies applying ML to diagnose dermatoses caused by infectious agents such as Leishmania. Bamorovat et al [18], presented a new diagnostic and prognostic method for classifying CL including responsive and non-responsive patients, showing the potential for automatic identification of leishmaniasis using ML algorithms. Furthermore, Noureldeen et al [27], showed a new diagnostic method of CL detection and classification with an ML model.…”