Abstract INTRODUCTION: As highly specific molecular biology-based techniques may not be sensitive enough for the diagnosis of American tegumentary leishmaniasis (ATL), clinicians frequently rely on immunological tests before treatment initiation. Hence, the correct combination of diagnostic tests is imperative for ATL diagnosis. We aimed to evaluate the accuracy of the Montenegro (Leishmanin) skin test (MST) in polymerase chain reaction (PCR)-negative patients to accurately detect ATL. METHODS: Patients with a clinical picture compatible with ATL were divided into ATL (confirmed by lesion smear, culture indirect immunofluorescence, and/or histopathology) and no-ATL (diseases that can mimic leishmaniasis) groups. Conventional PCR for the minicircle kDNA of Leishmania was performed, and the MST was carried out for PCR-negative patients. RESULTS: Ninety-nine patients were included in this study, including 79 diagnosed with ATL (6 with mucocutaneous leishmaniasis) and 20 without ATL (no-ATL group). The MST showed a high sensitivity of 90.0% (95% confidence interval [CI] = 69.90-97.21) in PCR-negative patients that was 10% higher than the sensitivity reported in PCR-positive population (79.66%; 95% CI = 67.73-87.96). CONCLUSIONS: One of the most important reasons for PCR negativity among patients with active ATL is the presence of a strong cellular immunological response, especially in chronic and mucocutaneous leishmaniasis. This reinforces the considerable utility of the tests that detect cellular responses against Leishmania antigens such as the MST in PCR-negative patients when the performance in screening situations is questionable.

RESUMO Deep Learning é uma técnica de aprendizado de máquina na qual o programa computacional aprende padrões diretamente a partir de imagens classificadas previamente. O presente ensaio objetivou apresentar essa técnica e algumas de suas aplicações para diagnóstico de doenças e identificação de insetos vetores para incentivar profissionais da saúde que não tenham conhecimento aprofundado em informática e que desejem utilizar a ferramenta para realizar análises automatizadas. Deep Learning tem sido aplicado para diagnóstico de câncer, fibrose cardíaca, tuberculose, detecção de parasitos como Plasmodium e Leishmania e ainda para identificação de insetos vetores. Na Universidade de Brasília, a técnica tem sido aplicada para desenvolver uma ferramenta para identificar lesões ulceradas de leishmaniose em diagnóstico diferencial e para detectar Leishmania em lâminas de estudos histopatológicos. Além disso, Deep Learning tem sido usado para identificar as espécies de vetores da doença de Chagas – o que é importante para auxiliar na vigilância epidemiológica. O uso da tecnologia envolve desafios éticos e procedimentais que são discutidos no presente ensaio. O ensaio aponta perspectivas de desenvolvimento de aplicativos que auxiliem os profissionais de saúde no diagnóstico de Leishmaniose e de vetores da doença de Chagas, o que vai ao encontro dos objetivos da pesquisa translacional.

ABSTRACT Deep Learning is a machine learning technique in which the computational algorithm learns patterns directly from images previously classified. The present essay aims to show some of its applications for clinical diagnosis and identification of insect vectors to encourage health professionals who do not have deep knowledge of computer science and who wish to use the tool to perform automated analyzes. Deep Learning has been applied to the diagnosis of cancer, cardiac fibrosis, tuberculosis, detection of parasites such as Plasmodium and Leishmania, and to identify insect vectors. At the University of Brasília, Deep Learning has been used to develop a tool to identify ulcers caused by leishmaniasis, as well as to detect Leishmania parasites. Moreover, Deep Learning was applied to identify the species of vectors of Chagas disease, an important contribution to the epidemiological surveillance of the disease. The use of Deep Learning involves some ethical and procedural issues that are discussed in this paper. Finally, the essay points out perspectives of development of apps that assist health professionals in the diagnosis of Leishmaniasis and Chagas disease vectors, which meets the goals of translational research.

RESUMO Deep Learning é uma técnica de aprendizado de máquina na qual o programa computacional aprende padrões diretamente a partir de imagens classificadas previamente. O presente ensaio objetivou apresentar essa técnica e algumas de suas aplicações para diagnóstico de doenças e identificação de insetos vetores para incentivar profissionais da saúde que não tenham conhecimento aprofundado em informática e que desejem utilizar a ferramenta para realizar análises automatizadas. Deep Learning tem sido aplicado para diagnóstico de câncer, fibrose cardíaca, tuberculose, detecção de parasitos como Plasmodium e Leishmania e ainda para identificação de insetos vetores. Na Universidade de Brasília, a técnica tem sido aplicada para desenvolver uma ferramenta para identificar lesões ulceradas de leishmaniose em diagnóstico diferencial e para detectar Leishmania em lâminas de estudos histopatológicos. Além disso, Deep Learning tem sido usado para identificar as espécies de vetores da doença de Chagas – o que é importante para auxiliar na vigilância epidemiológica. O uso da tecnologia envolve desafios éticos e procedimentais que são discutidos no presente ensaio. O ensaio aponta perspectivas de desenvolvimento de aplicativos que auxiliem os profissionais de saúde no diagnóstico de Leishmaniose e de vetores da doença de Chagas, o que vai ao encontro dos objetivos da pesquisa translacional.

ABSTRACT Deep Learning is a machine learning technique in which the computational algorithm learns patterns directly from images previously classified. The present essay aims to show some of its applications for clinical diagnosis and identification of insect vectors to encourage health professionals who do not have deep knowledge of computer science and who wish to use the tool to perform automated analyzes. Deep Learning has been applied to the diagnosis of cancer, cardiac fibrosis, tuberculosis, detection of parasites such as Plasmodium and Leishmania, and to identify insect vectors. At the University of Brasília, Deep Learning has been used to develop a tool to identify ulcers caused by leishmaniasis, as well as to detect Leishmania parasites. Moreover, Deep Learning was applied to identify the species of vectors of Chagas disease, an important contribution to the epidemiological surveillance of the disease. The use of Deep Learning involves some ethical and procedural issues that are discussed in this paper. Finally, the essay points out perspectives of development of apps that assist health professionals in the diagnosis of Leishmaniasis and Chagas disease vectors, which meets the goals of translational research.

Abstract INTRODUCTION: The treatment of mucosal leishmaniasis (ML) is difficult due to the toxicity and route of administration of standard drugs. Miltefosine is an oral agent used for leishmaniasis treatment; however, no data exist regarding its use for ML in Brazil. In this study, we aimed to evaluate the efficacy of miltefosine for ML treatment compared to that of pentavalent antimonial in a pilot study. METHODS: We performed a randomized clinical trial with two parallel groups. The tested intervention consisted of miltefosine 1.3-2 mg/kg/day (two capsules) for 28 days or intravenous 20 mg SbV/kg/day of meglumine antimoniate (N-MA) for 30 days. The final endpoint was defined as complete healing of the lesion four years after treatment. We also analyzed an early endpoint at 90 days after treatment. RESULTS: Forty patients were included in this study: each experimental group comprised 20 patients. Applying a multivariate model in an intention-to-treat analysis, we observed that patients treated with miltefosine had a cure probability 2.08 times greater (95% confidence interval [CI] = 1.03-4.18) than those treated with N-MA at 90 days after treatment. At the final endpoint, we observed no differences in cure probability between miltefosine and N-MA (relative risk = 0.66; 95% CI = 0.33-1.32). With respect to adverse reactions, significant differences between groups were related to gastrointestinal effects, which were more frequent in the miltefosine group. CONCLUSIONS: Miltefosine may be an interesting alternative for treating ML because of its oral administration and cure rate after long-term follow-up.

Abstract: Dermatofibroma is a frequent benign tumor of easy clinical diagnosis in most cases, but that can mimic other dermatoses. Dermoscopy may help to define the diagnosis and its classical pattern is a central white area, similar to a scar, surrounded by a discrete pigment network. However, dermoscopic findings are not always typical. We describe here a case of dermatofibroma exhibiting ridges, furrows and pseudocomedos, a pattern which is typical of seborrheic keratosis, in dermoscopy.

Abstract In Brazil, visceral Leishmaniasis is caused by Leishmania chagasi. The development of cutaneous lesions in visceral leishmaniasis patients has been described in two different clinical contexts. Patients with compromised immunity can develop skin lesions as a direct consequence of a current visceral disease. Equally, patients with a history of kala-azar and progressive, immune improvement occasionally develop skin lesions as a consequence of immune reconstitution infl ammatory syndrome. These cases manifest in similar fashion to the classic form of post-kala-azar dermal Leishmaniasis. We describe different cases that exemplify these two clinical presentations.