A Novel Data-driven Methodology for Influenza Outbreak Detection and Prediction [post]

Lin Du, Yan Pang
2020 unpublished
Influenza is an infectious disease that leads to an estimated 5 million severe illness cases and 650,000 respiratory deaths worldwide each year. Early detection and prediction of influenza outbreaks are crucial to efficient resource planning to save patients' lives and healthcare costs. This paper proposes a novel data-driven methodology for influenza outbreaks detection and prediction. The doctor's diagnosis-based prescription dataset of Influenza-Like Illness (ILI) from more than 3,000
more » ... e than 3,000 clinics in Malaysia is used in this study because the prescription data are reliable and can be captured timely. A new Region Index (RI) of the influenza outbreak is proposed based on the prescription dataset. With the newly proposed RI metric, statistical and machine learning models are developed to detect and predict influenza outbreaks. Cross-validation is conducted to evaluate the prediction model performance. The proposed methods are also validated by real-world evidence. It is proved to be sensitive and accurate in influenza outbreak prediction with 80-90% accuracy, 70-80% recall, and 70-80% precision scores.
doi:10.21203/rs.3.rs-109171/v1 fatcat:3fhozrq5bvhknkg4b56iuc5k4q