Background/Objectives: Treatment adherence challenges affect 10–20% of tuberculosis patients globally, contributing to drug resistance and continued transmission. While artificial intelligence approaches show promise for identifying patients who may benefit from additional treatment support, most models lack the interpretability necessary for clinical implementation. We aimed to develop and validate an integrated artificial intelligence framework combining traditional machine learning (interpretable algorithms like logistic regression and decision trees), explainable AI (methods showing which patient characteristics influence predictions), deep reinforcement learning (algorithms learning optimal intervention strategies), and natural language processing (clinical text analysis) to identify tuberculosis patients who would benefit from enhanced treatment support services. Methods: We analyzed 103,846 pulmonary tuberculosis cases from São Paulo state surveillance data (2006–2016). We evaluated models using precision (accuracy of positive predictions), recall (ability to identify all patients requiring support), F1-score (balanced performance measure), and AUC-ROC (overall discrimination ability) while maintaining interpretability scores above 0.90 for clinical transparency. Results: Our integrated framework demonstrated that explainable AI matched traditional machine learning performance (both F1-score: 0.77) while maintaining maximum interpretability (score: 0.95). The combined ensemble delivered superior results (F1-score: 0.82, 95% CI: 0.79–0.85), representing a 6.5% improvement over individual approaches (p < 0.001). Key predictors included substance use disorders, HIV co-infection, and treatment supervision factors rather than demographic characteristics. Conclusions: This multi-paradigm AI system provides a methodologically sound foundation for identifying tuberculosis patients who would benefit from enhanced treatment support services. The approach delivers excellent predictive accuracy while preserving full clinical transparency, demonstrating that the accuracy–interpretability trade-off in medical AI can be resolved through the systematic integration of complementary methodologies.

The development of systems that aim to spread public information, for example, public awareness campaigns for spotting the signs and symptoms of infectious diseases and how to prevent them, should be addressed by human-computer interaction, or more specifically, by devising interfaces that have a high degree of usability or user-friendliness. This paper examines a serious game that aims at providing people with the means of preventing diseases transmitted by the Aedes aegypti mosquito. An empirical test with groups of users was carried out to validate and observe the benefits of the game. The first group answered some questions about the diseases and how to combat the Aedes aegypti proliferation without playing the game and the second group answered the same questions after having played the game. The results showed a significant increase in the knowledge of Aedes aegypti and the diseases transmitted by it. As well as seeking to play the game to spread information about this disease, the purpose of this study is to understand the user's experience by interacting with a serious game and assisting in the evaluation of the usability and the cognitive benefits of serious games.

Leprosy, also known as Hansen’s, is one of the listed neglected tropical diseases as a major health problem global. Treatment is one of the main alternatives, however, the scarcity of medication and its poor distribution are important factors that have driven the spread of the disease, leading to irreversible and multi-resistant complications. This paper uses a distribution methodology to optimize medication administration, taking into account the most relevant attributes for the epidemiological profile of patients and the deficit in treatment via Polychemotherapy. Multi-criteria Decision Methods were applied based on AHP-Electre model in a database with information from patients in the state of Para between 2015 and 2020. The results pointed out that 84% of individuals did not receive any treatment and, among these, the method obtained a gain in the distribution of 68% in patients with positive diagnosis for leprosy.

Tuberculosis (TB) is a disease caused by the bacterium Mycobacterium tuberculosis and despite effective treatments, still affects millions of people worldwide. The advent of new treatments has not eliminated the significant challenge of TB drug resistance. Repeated and inadequate exposure to drugs has led to the development of strains of the bacteria that are resistant to conventional treatments, making the eradication of the disease even more complex. In this context, it is essential to seek more effective approaches to fighting TB. This article proposes a model for predicting drug resistance based on the clinical profile of TB patients, using machine learning techniques. The model aims to optimize the work of health professionals directly involved with tuberculosis patients, driving the creation of new containment strategies and preventive measures, as it specifies the clinical data that has the greatest impact and identifies the individuals with the greatest predisposition to develop resistance to anti-tuberculosis drugs. The results obtained show, in one of the scenarios, a probability of development of 70% and an accuracy of 84.65% for predicting drug resistance.

Modelo de Custo Total de Propriedade para Avaliação de Infraestruturas em Nuvem/ Total Cost of Ownership Model for Cloud Infrastructure Assessment

Objetivo: Este estudo propõe o desenvolvimento de um modelo baseado em Redes Neurais do tipo Multilayer Perceptron (MLP) para prever desfechos no tratamento da tuberculose, com ênfase na identificação de casos de cura e abandono. Métodos: Os dados foram pré-processados com imputação de ausentes, codificação categórica e normalização. Utilizou-se a técnica SMOTETomek para balanceamento. A arquitetura da MLP incluiu camadas densas com ativação ReLU, regularização com dropout (50%) e saída sigmoide. O modelo foi treinado com validação e avaliado com e sem balanceamento. Resultados: No cenário sem balanceamento, o modelo obteve acurácia macro de 0,6235, precisão de 0,9115, recall de 0,9781 e F1-macro de 0,6584, indicando viés em favor da majoritária. Com balanceamento, a acurácia micro e o F1-micro atingiram 0,8571. A precisão foi de 0,8857 e o recall reduziu-se para 0,8197. Na análise por classe, o modelo apresentou melhor desempenho ao prever abandono (F1 = 0,8623) em comparação com cura (F1 = 0,8514). Conclusões: O balanceamento de classes contribuiu para a melhoria do desempenho geral do modelo. O uso de MLP, aliado a estratégias técnicas de pré-processamento e balanceamento, mostrou-se eficaz na predição de desfechos no tratamento da tuberculose.