Predicting leishmaniasis outbreaks in Brazil using machine learning models based on disease surveillance and meteorological data

Leishmaniasis poses a significant global health concern due to the absence of vaccines for humans and high infection rates in some countries. It is classified as a neglected tropical disease. In 2022, roughly 85% of global visceral leishmaniasis cases were reported in seven countries: Brazil, Ethiopia, India, Kenya, Somalia, South Sudan, and Sudan. Despite Brazil's advanced medical capabilities compared to other affected regions, certain areas still witness a significant number of cases, prompting increased attention from researchers and raising concerns within the healthcare system. This study explores the application of artificial intelligence algorithms, particularly machine learning (ML) models to predict leishmaniasis outbreaks in selected Brazilian cities based on accumulated cases from 2007 to 2022, leveraging available meteorological data to enhance model accuracy. Our investigation concentrated on the following cities in Brazil: Fortaleza/CE, Teresina/PI, and S & atilde;o Luis/MA were chosen for the study of visceral leishmaniasis, whereas Manaus/AM, Rio Branco/AC, and Macap & aacute;/AP were selected for the study of tegumentary leishmaniasis, encompassing both cutaneous and mucocutaneous forms. Several Artificial Neural Network (ANN) architectures were evaluated, including a Simple Feedforward Neural Network (SFNN), a Deep Feedforward Neural Network (DFNN), and a Long Short-Term Memory (LSTM) recurrent neural network. Additionally, the Support Vector Machine (SVM), specifically the Support Vector Regression (SVR), was tested. Various metrics were used to identify the most effective models, in which the Root Mean Squared Error (RMSE) was the primary one. The results highlight the significance of meteorological data as a crucial factor in ML models for predicting leishmaniasis outbreaks, while also emphasizing the importance of fine-tuning these models to achieve greater accuracy. Finally, data and the pseudo-code of the models are accessible through an open repository to encourage further studies in this area.