Enhancing Pandemic Prediction: A Deep Learning Approach Using Transformer Neural Networks and Multi-Source Data Fusion for Infectious Disease Forecasting.

The Covid-19 pandemic has highlighted the urgent need for accurate prediction of pandemic trends. We propose a deep learning model for predicting Covid-19 cases and deaths at the county level through transformer neural networks with multi-source data fusion, incorporating historical case data, death data, and social media sentiment analysis to capture both temporal (historical trends) and spatial (geographical relationships) dynamics within time series data. Additionally, we develop multi-level and multi-scale attention mechanisms for adaptive time-frequency analysis. Across three Omicron variant waves (December 2021 through February 2023), the model demonstrated strong performance in predicting county-level Covid-19 cases and deaths, with median county agreement accuracy ranging from 74.0% to 82.6% for one-week case forecasts and 68.7% to 79.6% for 5-week case forecasts. Median county agreement accuracy for deaths ranged from 83.2% to 86.3% for one-week forecasts and 84.3% to 87.2% for five-week forecasts. Incorporating social media data yielded mild to moderate improvement in forecasting accuracy. Overall, the proposed model yielded substantial improvements compared to a baseline persistence model utilizing the last observation carried forward. By integrating real-time data and capturing complex pandemic dynamics, this approach surpasses traditional methods. Its high accuracy and generalizability make it a valuable tool for enhancing public health preparedness and response strategies in future outbreaks.