Objective

The COVID-19 pandemic response relied heavily on statistical and machine learning models to predict key outcomes such as case prevalence and fatality rates. These predictions were instrumental in enabling timely public health interventions that helped break transmission cycles. In this study, we aimed to assess the effectiveness of multimodal data in forecasting SARS-CoV-2 case surges across different phases of the pandemic, characterized by varying levels of data availability.

Materials and methods

Most existing models are grounded in traditional epidemiological data. The potential of alternative datasets, such as those derived from genomic information and human behavior, remains underexplored. In the current study, we investigated the usefulness of diverse modalities of feature sets in predicting case surges using machine learning models.

Results and Discussion

Our results highlight the relative effectiveness of biological (e.g., mutations), public health (e.g., case counts, policy interventions) and human behavioral features (e.g., mobility and social media conversations) in predicting country-level case surges. Importantly, we uncover considerable heterogeneity in predictive performance across countries and feature modalities, suggesting that surge prediction models based on alternative data may need to be tailored to specific national contexts and pandemic phases.

Conclusion

Overall, our work highlights the value of integrating alternative data sources into existing disease surveillance frameworks to enhance the prediction of pandemic dynamics.