Investigating the Performance of Artificial Intelligence in the Diagnosis of Cutaneous Leishmaniasis: A Systematic Review

Cutaneous leishmaniasis is a common skin disease in developing countries that is transmitted by the protozoan Leishmania through the bite of a female phlebotomus and can have different symptoms from a simple skin ulcer to a progressive systemic disease, but due to parasite resistance to common treatments. Control and early diagnosis of leishmaniasis is important. Today, artificial intelligence has been used in the medical diagnosis of different diseases, and the purpose of this study is to investigate the use of artificial intelligence in the diagnosis of cutaneous leishmaniasis. This study was conducted using a systematic review method in October ۲۰۲۳, by searching for the keywords leishmaniasis, artificial intelligence, and diagnosis, along with their English equivalents, in databases such as PubMed, SID, Scopus, ScienceDirect, and the Google Scholar search engine. After applying inclusion and exclusion criteria, ۱۱ English and Persian articles published between ۲۰۱۹ and ۲۰۲۳ were studied and reviewed according to the PRISMA checklist. In order to improve the diagnostic methods of cutaneous leishmaniasis, artificial intelligence has provided several solutions in Python, which were fruitful in diagnosing leishmaniasis lesions with high accuracy and sensitivity, such as Yolov۵, MLP, and Viola-Jones patterns that use images. Lesion process the diagnostic characteristics of the lesion and by forming integrated images, send the prognosis and proposed treatment plan based on the patient's profile, drug selection warnings and estimation of the patient's treatment adherence to the dermatologist for definitive diagnosis. Some protocols require sampling of exudate from the edges of the wound to check factors such as infected macrophages and enzyme activity in the lesion. Artificial intelligence algorithms can accurately, comprehensively, quickly and cheaply diagnose cutaneous leishmaniasis and it is suggested to conduct similar studies in other skin diseases to create a comprehensive diagnostic library of skin lesions.

کلیدواژه ها:

cutaneous leishmaniasis ، artificial intelligence ، diagnosis