Abstract
Influenza is an infectious disease that leads to an estimated 5 million cases of severe illness and 650,000 respiratory deaths worldwide each year. The early detection and prediction of influenza outbreaks are crucial for efficient resource planning to save patient’s lives and healthcare costs. We propose a new data-driven methodology for influenza outbreak detection and prediction at very local levels. A doctor’s diagnostic dataset of influenza-like illness from more than 3000 clinics in Malaysia is used in this study because these diagnostic data are reliable and can be captured promptly. A new region index (RI) of the influenza outbreak is proposed based on the diagnostic dataset. By analysing the anomalies in the weekly RI value, potential outbreaks are identified using statistical methods. An ensemble learning method is developed to predict potential influenza outbreaks. Cross-validation is conducted to optimize the hyperparameters of the ensemble model. A testing data set is used to provide an unbiased evaluation of the model. The proposed methodology is shown to be sensitive and accurate at influenza outbreak prediction, with average of 75% recall, 74% precision, and 83% accuracy scores across five regions in Malaysia. The results are also validated by Google Flu Trends data, news reports, and surveillance data released by World Health Organization.
Highlights
Influenza is an infectious disease that leads to an estimated 5 million cases of severe illness and 650,000 respiratory deaths worldwide each year
Based on a study conducted at the University of Malaya Medical Centre in Malaysia in 2009, the direct healthcare cost for each hospitalized H1N1 patient was USD 510, which was 60% higher than the year 2007 per capita national expenditure on health of USD 3183
To study the regional influenza outbreak, we introduce the region index (RI), a metric that normalizes the impact of the weekly number of clinics and the clinic size
Summary
Influenza is an infectious disease that leads to an estimated 5 million cases of severe illness and 650,000 respiratory deaths worldwide each year. Based on a study conducted at the University of Malaya Medical Centre in Malaysia in 2009, the direct healthcare cost for each hospitalized H1N1 patient was USD 510, which was 60% higher than the year 2007 per capita national expenditure on health of USD 3183. Given these circumstances, investigators are working on detecting and predicting influenza outbreaks early. Many papers built prediction models based on historical ILI case data from traditional surveillance or WHO reports These data had the limitations such as low geographic coverage and small sample size. It was shown that the generalized linear autoregressive moving average (GARMA) model with
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have