Data architecture to facilitate the diagnosis of arboviruses.

Arboviruses are diseases caused by viruses transmitted by mosquitoes, with dengue, chikungunya, and Zika being the most common in urban environments, transmitted by Aedes aegypti. In Brazil, dengue poses a constant threat, with over 3 million cases reported in 2024. Arboviruses share similar characteristics, complicating accurate diagnosis and treatment, and under-reporting remains a significant challenge. To improve diagnosis and treatment, a system is proposed that integrates and standardizes data collected at health posts. This system utilizes artificial intelligence algorithms to diagnose and suggest treatments.

Challenges include collecting relevant patient data, such as temperature, symptoms, and travel history, through electronic medical records (EMRs), which avoid paper waste and ensure information security and organization. Additionally, ensuring the accuracy and completeness of data collection is crucial for the effectiveness of the proposed system. After collection, the data must be stored in appropriate database systems, depending on whether they are structured or unstructured.

Subsequently, the ETL (extraction, transformation, and loading) process is necessary to move the data to suitable repositories, enabling the use of machine learning algorithms. These measures aim to improve diagnostic accuracy and treatment effectiveness for arboviruses, contributing to saving lives.

Furthermore, continuous monitoring and updating of the system are required to adapt to new strains of arboviruses and emerging health threats. Public health education and awareness campaigns are also essential to encourage the public to participate in prevention measures, such as eliminating mosquito breeding sites. By addressing these challenges, the proposed system can significantly enhance public health responses to arboviruses outbreaks, ultimately reducing the burden of these diseases and saving lives.