Jacks Renan Neves Fernandes

Leprosy remains a major public health challenge in high-burden regions, where its clinical similarity to other dermatoses and reliance on clinical assessment can contribute to delayed diagnosis. Although multimodal Large Language Models (LLMs) have shown potential for dermatological decision support, their performance for leprosy and their acceptance by healthcare professionals remain largely unexplored. This study addressed these issues through two complementary experiments. First, four general-purpose LLMs (ChatGPT, Grok, Claude, and Gemini) were evaluated on 213 clinical cases across three input modalities (image, metadata, and combined image-and-metadata) and four prompting strategies (zero-shot, few-shot, chain-of-thought, and prompt repetition). Second, 62 healthcare professionals were randomised to evaluate LLM-generated diagnostic responses with or without an accompanying Chain-of-Thought (CoT)-generated rationale, assessing trust, perceived usefulness, and intention to use. The best-performing configuration achieved an F1-score of 0.837. Structured clinical metadata provided greater discriminative value than images alone, while combining images with metadata did not consistently improve performance beyond metadata alone. Performance also varied according to the interaction between model, input modality, and prompting strategy, with no prompting strategy being uniformly superior. In the human-centred evaluation, trust did not differ significantly between experimental conditions (p = 0.469), whereas perceived usefulness was higher in the group when diagnostic conclusions were accompanied by CoT-generated rationales (p = 0.043); intention to use showed a similar direction but did not reach statistical significance (p = 0.082). Overall, general-purpose LLMs show potential for leprosy diagnostic support, but their clinical evaluation should extend beyond aggregate classification performance to consider clinically informative inputs, error profiles, response consistency, and the presentation of outputs in ways that support appropriate human oversight.

The increasing integration of Artificial Intelligence (AI) into dermatology holds significant potential to enhance the diagnosis and prognosis of skin diseases, which represent a considerable public health burden. While numerous AI models for skin conditions have been developed, their successful translation into real-world clinical practice critically depends on rigorous external validation to ensure generalizability and reliability beyond their development environment. Despite the growing recognition of external validation’s importance in medical AI, a comprehensive synthesis specifically addressing this process for AI models in dermatology has been lacking. This systematic literature review aimed to identify and synthesize studies focused exclusively on the external validation of AI models for skin diseases, thereby assessing their clinical applicability, methodological robustness, and identifying key challenges. Following the PRISMA framework, a systematic search was conducted across five major digital libraries (ACM Digital Library, IEEE Xplore, Web of Science, PubMed, and Scopus). Study quality was assessed using a customized checklist, and data extraction focused on validation practices, model characteristics, targeted diseases, performance assessment, and identified limitations. The systematic study selection led to a detailed analysis of 41 studies. We observed a clear predominance of retrospective external validation studies focused on diagnostic models, while prognostic models and prospective validation designs were notably scarce. Although some models demonstrated promising performance in external validation, several critical limitations persist. These include the narrow representation of skin disease categories, lack of subgroup fairness analyses, small and imbalanced sample sizes, and insufficient standardization of data collection and evaluation metrics. These findings underscore the need for more rigorous and transparent validation frameworks to support the reliable integration of AI into dermatological practice.

Leprosy is a neglected tropical disease that can cause physical injury and mental disability. Diagnosis is primarily clinical, but can be inconclusive due to the absence of initial symptoms and similarity to other dermatological diseases. Artificial intelligence (AI) techniques have been used in dermatology, assisting clinical procedures and diagnostics. In particular, AI-supported solutions have been proposed in the literature to aid in the diagnosis of leprosy, and this Systematic Literature Review (SLR) aims to characterize the state of the art. This SLR followed the preferred reporting items for systematic reviews and meta-analyses (PRISMA) framework and was conducted in the following databases: ACM Digital Library, IEEE Digital Library, ISI Web of Science, Scopus, and PubMed. Potentially relevant research articles were retrieved. The researchers applied criteria to select the studies, assess their quality, and perform the data extraction process. Moreover, 1659 studies were retrieved, of which 21 were included in the review after selection. Most of the studies used images of skin lesions, classical machine learning algorithms, and multi-class classification tasks to develop models to diagnose dermatological diseases. Most of the reviewed articles did not target leprosy as the study’s primary objective but rather the classification of different skin diseases (among them, leprosy). Although AI-supported leprosy diagnosis is constantly evolving, research in this area is still in its early stage, then studies are required to make AI solutions mature enough to be transformed into clinical practice. Expanding research efforts on leprosy diagnosis, coupled with the advocacy of open science in leveraging AI for diagnostic support, can yield robust and influential outcomes.

A Doença de Parkinson (DP) apresenta-se na senescência, limitando o movimento e progredindo para demência, sendo assim a segunda doença neurodegenerativa no mundo relacionada a idade. Desse modo, esta revisão bibliográfica tem como objetivo reunir informações relevantes sobre a DP para direcionar novas abordagens científicas que favorecerão à aplicação clínica, e assim, a qualidade de vida dos pacientes da PD. Foram selecionados e analisados 80 estudos publicados nos últimos 20 anos em base de dados com descritores indexados. O resultado observado direciona para a compreensão de teorias causais, sintomas motores e não-motores, diagnóstico e tratamento. Concluiu-se que o estudo norteia, a partir das informações levantadas, novos estudos experimentais para a melhora da qualidade de vida de pacientes da DP.

Parkinson's disease (PD) is characterized by the dopaminergic neuron's progressive neurodegeneration, which is chronic and results in movement and behavioral disorders. There are still many gaps in the PD etiology and pathogenesis. Thus, aiming to strengthen the evidence that serves as a tool for diagnostic aid and future treatments, this systematic review aims to relate and analyze studies on the PARK proteomics, that is, the class of expressed park proteins that are associated with pathogenesis, PD clinical changes, and temporal effects. 261 papers were selected for eligibility analysis based on their title and abstract, resulting in 56 papers, with a full reading, included in this study. The observed result leads to the understanding of gene expression for a class of proteins that participate in cellular metabolic pathways associated with the PD etiology. Genetic studies applied to proteomics investigated disease-linked loci of PARK genes and their gene expression to relate the cellular pathways that contribute to PD. It was observed that PARK proteins corroborate the PD pathogenesis, highlighting the hypothesis of change in perception over time. Therefore, exploratory, and systematic studies can guide future investigations and strengthen clinically applied evidence.

The circadian rhythm deregulation can result in an alteration in the sleep-wake cycle, causing sleep disturbances and promoting mental and mood disorders development. Conditions that can disrupt this rhythm, such as shift work schedule (SWS) can unbalance neural functioning and favors those professional classes may have a greater tendency to develop depression. In this context, this study aims to carry out a systematic review to understand the relationship between SWS and the risk of depression, so 1,001 articles were selected for eligibility analysis for the study. After an evaluation sequence starting from the title, abstract and complete work, 31 works that responded to the proposed theme were included. Depression was found to be higher in JTT workers such as nurses, company employees, physicians, residents, and firefighters compared to other professionals. The main explanations involve decreased melatonin production, stressful conditions linked to professional activity and lifestyle habits. Thus, it is important to delineate new therapeutic forms, control, prevention, and health promotion for these workers, since the SWS is strongly associated with depression.

O objetivo deste trabalho foi avaliar por meio de uma revisão a interrelação entre COVID-19, periodontite e algumas patologias orais. A transmissão da COVID-19 se dá por pequenas gotículas do nariz ou boca contendo a partícula viral que é expelida por pessoas durante a tosse, fala ou espirro, por exemplo. Cerca de 20% das pessoas infectadas necessitam de internação e 5% provavelmente precisará de um leito em terapia intensiva. Pessoas com problemas médicos subjacentes, têm maior probabilidade de desenvolver doença graves. Pacientes que apresentam comorbidades preexistentes como, diabetes, hipertensão, doenças cardiovasculares, entre outras, podem estar mais suscetíveis a desenvolver a forma mais grave da COVID-19. Diversas alterações sistêmicas podem estar associadas à essa patologia, como, desordens na microbiota oral, aumentando o número de microrganismos nela presente, o que levaria a uma maior propensão às patologias orais. A entrada do vírus pode subverter o sistema imunológico e a microbiota oral do hospedeiro, desencadeando uma disbiose que permite uma superinfecção, compreensão da associação da doença periodontal com COVID-19 grave. Tendo isso em vista, o presente estudo visa avaliar a associação entre patologia oral e agravamento do COVID-19, assim como identificar sua relação de sintomas preexistentes às patologias orais.

O artigo a seguir apresenta o diagnóstico clássico e alguns avanços da paracoccidioidomicose, doença infecciosa com espectro de evolução aguda, subaguda ou crônica causada pelo fungo Paracoccidioides spp., a doença é contraída através da inalação de partículas fúngicas transportadas pelo ar, tendo como principais sintomas a tosse, falta de ar, emagrecimento e lesões na pele ou mucosas. Os sintomas clínicos dificultam um diagnóstico correto, em vista da semelhança com outras doenças, como, por exemplo, a tuberculose e a sarcoidose, além de que em algumas situações pode haver um extenso período de tempo entre a exposição do indivíduo ao fungo e a manifestação dos sintomas. Levando isso em consideração, o objetivo do trabalho é avaliar e discorrer dos métodos de diagnósticos, bem como, identificar os novos avanços realizados pelos métodos moleculares, sorológicos, micológicos e histopatológicos para essa micose. Para esta finalidade, foram realizados uma leitura sobre estudos de casos, ensaio experimental e uma revisão sistemática.

Cybersickness results from the visual vestibule conflict, that is, the incoherence between the sensations related to real movement, in the virtual environment, and the visual stimuli. In response to the virtual environment, one can observe discomforts such as nausea, difficulty in concentrating, and headaches, among others. There are no studies in the literature that analyze the inhibition control of light stimuli in individuals sensitive to Cybersickness. Therefore, this study looked at the control of light stimulus inhibition in Cybersickness. The Sickness Susceptibility Questionnaire was used to divide the subjects into experimental and control groups, and quantify the signs and symptoms, comparing them before and after 3D virtual immersion and. Participants in both groups were examined with EEGq for absolute theta band power in the dorsolateral prefrontal cortex and ventrolateral prefrontal cortex during the light stimulus inhibition task before and after participants watched the 3D video. The partial results showed that there was an increase in the absolute theta band power in both groups comparing the moments before and after, as well as a significant difference in the experimental group compared to the control, for the same moment. Thus, it was observed that individuals who were exposed to 3D virtual reality and developed Cybersikness, showed greater absolute theta band power in the areas studied.

Bromazepam emulates the inhibitory effect of the neurotransmitter gamma-aminobutyric acid (GABA) and can lead to impaired visuomotor performance. However, few studies have evaluated its effects on cortical coupling in target shooting activities. The present study aimed to analyze the acute effects of bromazepam administration in a target shooting task and the EEG theta rhythm coherence between frontal, temporal, and motor cortical areas in four shooting preparation periods. Thus, a double blind, crossover study was conducted with 30 subjects under two conditions: bromazepam (6mg) and placebo, with electroencephalographic analysis to simultaneously study the theta rhythm coherence in frontal, temporal, and motor cortex in a target shooting task; and the possible interferences of bromazepam administration. Subjects in the bromazepam group showed lower performance on the task compared to placebo (p=0.001). In addition, our analysis showed decreased coherence between regions in the same hemisphere, increased theta rhythm coherence in interhemispheric regions in frontal, temporal and motor cortex at different intervals in the preparation preceding the shooting (p=0.001). The use of bromazepam may influence task execution, possibly due to neurochemical modulation, during decision making, developing shooting preparation strategies, as well as interfering with the flow of information at the level of attention during task execution.