Predição de aplicação de doses de vacinas com N-BEATS: uma solução de saúde digital para a gestão de imunobiológicos no SUS

Abstract

Vaccine demand forecasting is essential for the efficient management of stock and the proper distribution of immunobiologicals, ensuring vaccination coverage and preventing waste. Time series models are widely used in this context, allowing the anticipation of vaccine demand and the optimization of available resources. With advancements in deep learning, the N-BEATS (Neural Basis Expansion Analysis Time Series) algorithm has stood out for its effectiveness in modeling complex data without requiring extensive preprocessing. Introduced by Oreshkin et al. (2020), N-BEATS outperforms traditional models, such as autoregressive models and Multi-Layer Perceptrons (MLPs), by handling nonlinear patterns through a block-stacking architecture that iteratively refines predictions. This study applies NBEATS to forecast the weekly number of vaccines to be administered in the states of Rio Grande do Norte and Espírito Santo, using data from the RN+VACINA and Vacina e Confia systems. In Rio Grande do Norte, the forecast focuses on a macro analysis covering state and municipal levels, while in Espírito Santo, a more granular approach is taken, with vaccinespecific predictions. The results highlighted the superior performance of N-BEATS compared to traditional models such as XGBoost. In Rio Grande do Norte, the model achieved an R² of 0.81 and a MAPE of 16.59%, while XGBoost obtained an R² of 0.73. In Natal, a municipality in the state, the values were R² of 0.77 and MAPE of 21.59%. In Espírito Santo, the analysis was conducted at the state level and for the municipality of Cariacica, focusing on the BCG vaccine. The statelevel results showed a MAPE of 1.00% and R² of 0.83, while at the municipal level, the values were MAPE of 2.46% and R² of 0.85. These metrics demonstrate that N-BEATS is a robust and efficient solution for time series forecasting in vaccination systems. Its ability to handle nonlinear and complex patterns, combined with minimal preprocessing requirements, makes it suitable for scenarios where speed and accuracy are essential. Additionally, its superior performance compared to traditional models reinforces the potential of N-BEATS as a reliable tool for managing vaccination campaigns, contributing to a more efficient and strategic distribution of immunizers.