Data-Driven Disease Surveillance

The paper introduces a dynamic alert system using a Zoonotic Alert Index to improve disease outbreak detection in wildlife, validated with yellow fever data achieving over 94% accuracy.

The paper uses Google Trends data to show that online search behavior reflects the spread of canine dirofilariosis in Hungary, supporting digital epidemiology as a surveillance tool.

The paper analyzes Brazilian respiratory syndrome data and community mobility changes to assess data quality, estimate cases from mobility patterns, detect disease waves, and cluster cities by behavior.

This study improves nowcasting of Lyme disease rates using Elastic Net regression with environmentally themed search terms from Google Trends.

This paper introduces Inferno, a fast and accurate flu forecasting model that outperforms existing models in speed while maintaining high performance in FluSight 2018/19.

MicrobeTrace integrates and analyzes multi-source public health data to support rapid outbreak response, demonstrating its utility with HIV and SARS-CoV-2 datasets.

The paper improves influenza forecasting by enforcing geographical constraints on forecasts, leading to better accuracy across 90% of tested models.

This study evaluates the implementation of Malawi's IDSR system, finding good completeness but poor timeliness in disease reporting and identifying challenges like lack of supervision and excessive paperwork.