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

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

Cutaneous Leishmaniasis (CL) is a major global health problem requiring appropriate diagnosis methods. Its diagnosis is challenging, particularly in resource-limited settings. The integration of Artificial Intelligence (AI) into medical diagnostics has shown promising results in various fields, including dermatology. In this systematic review, we aim to highlight the value of using AI for CL diagnosis and the AI-based algorithms that are employed in this process, and to identify gaps that need to be addressed. Our work highlights that only a limited number of studies are related to using AI algorithms for CL diagnosis. Among these studies, seven gaps were identified for future research. Addressing these considerations will pave the way for the development of robust AI systems and encourage more research in CL detection by AI. This could contribute to improving CL diagnosis and, ultimately, healthcare outcomes in CL-endemic regions.

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

The polymorphism of cutaneous leishmaniasis (CL) complicates diagnosis in health care services because lesions may be confused with other dermatoses such as sporotrichosis, paracocidiocomycosis, and venous insufficiency. Automated identification of skin diseases based on deep learning (DL) has been applied to assist diagnosis. In this study, we evaluated the performance of AlexNet, a DL algorithm, to identify pictures of CL lesions in patients from Midwest Brazil. We used a set of 2458 pictures (up to 10 of each lesion) obtained from patients treated between 2015 and 2022 in the Leishmaniasis Clinic at the University Hospital of Brasilia. We divided the picture database into training (80%), internal validation (10%), and testing sets (10%), and trained and tested AlexNet to identify pictures of CL lesions. We performed three simulations and trained AlexNet to differentiate CL from 26 other dermatoses (e.g., chromomycosis, ecthyma, venous insufficiency). We obtained an average accuracy of 95.04% (Confidence Interval 95%: 93.81-96.04), indicating an excellent performance of AlexNet in identifying pictures of CL lesions. We conclude that automated CL identification using AlexNet has the potential to assist clinicians in diagnosing skin lesions. These results contribute to the development of a mobile application to assist in the diagnosis of CL in health care services.

Cutaneous leishmaniasis situation analysis in the Islamic Republic of Iran in preparation for an elimination plan

Iran has invariably been under the growing public health threat of cutaneous leishmaniasis (CL), a significant barrier to local development that hinders the prevention and control efforts toward eliminating the disease. So far, no comprehensive and in-depth epidemiological analysis of the CL situation has been carried out nationwide. This study aimed to employ advanced statistical models to analyze the data collected through the Center for Diseases Control and Prevention of Communicable Diseases during 1989-2020. However, we emphasized the current trends, 2013-2020, to study temporal and spatial CL patterns. In the country, the epidemiology of CL is incredibly intricate due to various factors. This fact indicates that the basic infrastructure, the preceding supports, and the implementation plan related to preventive and therapeutic measures need crucial support. The leishmaniasis situation analysis is consistent with desperate requirements for efficient information on the control program in the area. This review provides evidence of temporally regressive and spatially expanding incidence of CL with characteristic geographical patterns and disease hotspots, signifying an urgent need for comprehensive control strategies. This information could be a suitable model and practical experience in the Eastern Mediterranean Region, where over 80% of CL is reported.

Emerging computational technologies in human leishmaniasis: where are we?

Human leishmaniasis is a neglected tropical disease (NTD) with high morbidity and is endemic in low- to middle-income countries. Its diagnosis, treatment and epidemiological control methods are outdated and obsolete, which has become a challenge for health practitioners in controlling the disease. Computational methods have proven to be beneficial and have become popular in many fields of medicine, especially in affluent countries. However, they have not been widely used for NTDs. To date, few computational technologies have been employed for leishmaniasis. Although new technologies in leishmaniasis are theorized, they have only been minimally applied and have not been updated, even in other infections. Research and development on NTDs suffers from the inherent difficulties of the demographic regions the diseases afflict. In this narrative review we described the e-tools available in managing leishmaniasis, ranging from drug discovery to treatment.

Development of Novel Anti-Leishmanials: The Case for Structure-Based Approaches

The neglected tropical disease (NTD) leishmaniasis is the collective name given to a diverse group of illnesses caused by ~20 species belonging to the genus Leishmania, a majority of which are vector borne and associated with complex life cycles that cause immense health, social, and economic burdens locally, but individually are not a major global health priority. Therapeutic approaches against leishmaniasis have various inadequacies including drug resistance and a lack of effective control and eradication of the disease spread. Therefore, the development of a rationale-driven, target based approaches towards novel therapeutics against leishmaniasis is an emergent need. The utilization of Artificial Intelligence/Machine Learning methods, which have made significant advances in drug discovery applications, would benefit the discovery process. In this review, following a summary of the disease epidemiology and available therapies, we consider three important leishmanial metabolic pathways that can be attractive targets for a structure-based drug discovery approach towards the development of novel anti-leishmanials. The folate biosynthesis pathway is critical, as Leishmania is auxotrophic for folates that are essential in many metabolic pathways. Leishmania can not synthesize purines de novo, and salvage them from the host, making the purine salvage pathway an attractive target for novel therapeutics. Leishmania also possesses an organelle glycosome, evolutionarily related to peroxisomes of higher eukaryotes, which is essential for the survival of the parasite. Research towards therapeutics is underway against enzymes from the first two pathways, while the third is as yet unexplored.