Multitask LSTM for Arboviral Outbreak Prediction Using Public Health Data

TL;DR

This study introduces a multitask LSTM model that jointly predicts arboviral outbreaks and case counts using public health data, improving epidemic forecasting accuracy and efficiency.

Contribution

It presents a novel multitask LSTM approach that simultaneously performs outbreak detection and case forecasting for multiple arboviruses using public health data.

Findings

Longer input windows improve dengue case prediction accuracy.

Intermediate window lengths optimize outbreak classification performance.

Multitask model achieves competitive results across diseases and tasks.

Abstract

This paper presents a multitask learning approach based on long-short-term memory (LSTM) networks for the joint prediction of arboviral outbreaks and case counts of dengue, chikungunya, and Zika in Recife, Brazil. Leveraging historical public health data from DataSUS (2017-2023), the proposed model concurrently performs binary classification (outbreak detection) and regression (case forecasting) tasks. A sliding window strategy was adopted to construct temporal features using varying input lengths (60, 90, and 120 days), with hyperparameter optimization carried out using Keras Tuner. Model evaluation used time series cross-validation for robustness and a held-out test from 2023 for generalization assessment. The results show that longer windows improve dengue regression accuracy, while classification performance peaked at intermediate windows, suggesting an optimal trade-off between sequence length and generalization. The multitask architecture delivers competitive performance across diseases and tasks, demonstrating the feasibility and advantages of unified modeling strategies for scalable epidemic forecasting in data-limited public health scenarios.