Visceral leishmaniasis (VL) is a severe parasitic disease that poses significant diagnostic challenges due to its complex presentation and the necessity for comprehensive diagnostic methods. This exploratory study investigates the potential of Chat Generative Pre-trained Transformer (ChatGPT)/GPT-4, an artificial intelligence (AI) chatbot, in assisting the diagnostic process for VL. We evaluated the diagnostic accuracy of ChatGPT/GPT-4 in generating differential diagnosis lists for eight clinical vignette cases of VL, authored by a Brazilian infectious disease doctor. Our findings reveal that ChatGPT/GPT-4 included VL in the top five differential diagnoses in 75% of the cases (95% confidence interval [CI]: 40.1 – 93.7%) and identified VL as the top diagnosis in 50% of the cases (95% CI: 30.3 – 86.5%). These results underscore the high potential of ChatGPT/GPT-4 as an AI-assisted diagnostic tool, which is capable of providing accurate differential diagnoses and assisting healthcare professionals in resource-limited settings. The study highlights the broader applicability of AI chatbots in medical diagnostics, not only for common conditions but also for specialized and less prevalent diseases like VL. By integrating AI tools into the diagnostic workflow, healthcare providers can enhance their diagnostic accuracy and efficiency, ultimately improving patient outcomes. This research contributes to the growing body of evidence supporting the utility of AI in healthcare and underscores the need for further studies to validate these findings across larger and more diverse clinical scenarios.
OBJECTIVE: To evaluate the influence of the Mais Medicos (More Doctors) Program on the performance of primary health care by quantifying health services access and use in Northeast Brazil, based on the population size of the municipalities, on the financial investment in health, and on the number of physicians in the family health teams. METHOD: Evaluative research of quantitative nature. Access was evaluated by the population coverage ratio of the Family Health Strategy and use of health services, which were measured by medical appointments conducted between April 2013 and September 2015. We defined processes for database selection, adjustment, and validation, including explanatory variables for a sample of 896 municipalities. The analysis was based on the time periods before and after the implementation of the program. The Wilcoxon signed-rank test and non-parametric alternatives constituted statistical tests in the comparative analysis of the data. RESULTS: A 19.2% increase was observed in the number of medical appointments between the first six months and the final six months of the data series. In this period, the median appointments in municipalities with up to 5,000 inhabitants increased from 701.0 to 768.0; while in those with more than 100,000 inhabitants it decreased from 285.5 to 280.0 (p < 0.05). Between April 2013 and September 2015, the median coverage ratio of the family health teams increased from 89.2% to 95.3%, approaching 100% in the municipalities with up to 20,000 inhabitants. CONCLUSIONS: The study highlights the expansion of access and use of primary health care services in the northeast region after the implementation of the Mais Medicos (More Doctors) Program. Between April 2013 and September 2015, the coverage of family health teams and the production of medical appointments increased, constituting important achievements for SUS.
O estudo analisa a confiabilidade dos dados relativos ao cumprimento da Emenda Constitucional nº. 29 (EC29) declarados ao Sistema de Informações sobre Orçamentos Públicos em Saúde (SIOPS) pelos municípios de Pernambuco, Brasil. Configura-se como um estudo quantitativo, do tipo transversal e de caráter analítico, tendo como referência o período de 2000 a 2005. Os demonstrativos contábeis auditados pelo Tribunal de Contas do Estado (TCE) foram tomados como parâmetro para verificar a confiabilidade dos percentuais de aplicação da EC29 declarados ao SIOPS, sendo utilizado o coeficiente de correlação intraclasses (CCI) como prova estatística na medição da concordância dos dados. Os resultados demonstram a dissonância existente entre as bases consultadas, sugerindo um nível de concordância discreto a moderado entre os dados do SIOPS e do TCE. A baixa concordância identificada pode ser decorrente da falta de consenso pelos municípios acerca da composição das receitas e despesas vinculadas à saúde ou da existência de critérios diferentes no cálculo da EC29 entre o SIOPS e a auditoria do TCE.
RESUMO Este estudo objetivou avaliar o desempenho dos cursos de fisioterapia no país quanto aos conceitos obtidos no Exame Nacional de Desempenho dos Estudantes (Enade), no período de 2004 a 2013, verificando o rendimento dos cursos entre as instituições de ensino superior públicas e privadas e a relação das pontuações do exame com o Conceito Preliminar de Curso (CPC). Estudo quantitativo transversal de base documental, realizado com amostra de 103 cursos de fisioterapia que participaram das avaliações do Enade realizadas de 2004 a 2013. A análise constou da avaliação dos conceitos Enade e do CPC por classificações de desempenho ao longo dos anos. Observou-se avanço dos conceitos Enade e CPC na amostra (valor de p
Background: Large language models (LLMs) are increasingly considered as adjuncts for differential diagnostic reasoning, yet their sensitivity to gender-attributed cues in the persona prompt—particularly for neglected tropical diseases (NTDs) and in non-English clinical settings—remains poorly characterised. Objective: The objective of this study was to compare the diagnostic accuracy of one proprietary and three open-weight LLMs for Chagas disease (CD) and visceral leishmaniasis (VL) under paired persona-prompt conditions in which the only manipulated variable was the linguistic gender of the simulated medical persona. Methods: This experimental, paired study evaluated ChatGPT-4o, LLaMA 3 70B, Meditron-70B, and Mixtral 8x7B across 12 cases per disease (n = 24) from real records at a Brazilian teaching hospital. The primary outcome was top-five diagnostic accuracy. A committee of five infectious-disease specialists assessed the biological plausibility of all differentials. Paired comparisons used Wilcoxon signed-rank tests; 95% confidence intervals were calculated using the Wilson-score method. Results: ChatGPT-4o achieved the highest accuracy (CD: 100% under both prompts; VL: 83.3–91.7%). LLaMA 3 70B and Mixtral 8x7B showed moderate performance (41.7–83.3%); the medically fine-tuned Meditron-70B exhibited paradoxically poor accuracy (16.7–25.0%) and the lowest committee-rated plausibility scores. A consistent small numerical trend favoured the female prompt across most model–disease combinations (differences of 0–16.7 percentage points), but no comparison reached statistical significance (all p > 0.05). Conclusions: Gender-attributed persona-prompt variation did not produce a systematic effect on LLM diagnostic accuracy for CD or VL. ChatGPT-4o outperformed the three evaluated open-weight alternatives, and medical-domain fine-tuning did not confer the expected advantage. Expert-validated assessment of hypothesis plausibility should complement target-disease accuracy in clinical LLM evaluation studies, particularly for NTDs.
RESUMO A regionalização é um processo de governança lógico, potente e indispensável no cenário da política de saúde. Diante dos desafios postos a uma regionalização solidária, que viabilize a universalidade do acesso, equidade e integralidade do cuidado, foi implantada a pioneira Rede Interestadual de Saúde do Vale do Médio São Francisco, na região entre os estados de Pernambuco e Bahia (Rede Peba). O estudo analisou a complexa relação gerencial que envolve, na coordenação do cuidado, agentes públicos e privados. A abordagem foi qualitativa, tendo como foco o processo de regionalização da Rede Peba, por meio da regulação assistencial, sob a perspectiva dos gestores, profissionais dos serviços e usuários. A análise da associação oferta-produção-fila de espera permite constatar que a qualificação da gestão da clínica e do processo de encaminhamento e necessidade de organização e comunicação são imprescindíveis para garantir acesso oportuno. Do contrário, ocorrem efeitos diretos no absenteísmo, impactando no aumento das filas, exigindo uma abordagem sistêmica e multifatorial para organização do processo regulatório. Fica evidente a necessidade de arranjos organizacionais envolvendo todos os atores no processo de formulação e desenvolvimento das políticas públicas de saúde, a fim de superar barreiras para a coordenação do cuidado e a integralidade em saúde.