Objective: This study aimed to determine whether a search index could provide insight into trends in asthma admission in China. An Internet search index is a powerful tool to monitor and predict epidemic outbreaks. However, whether using an internet search index can significantly improve asthma admissions forecasts remains unknown. The long-term goal is to develop a surveillance system to help early detection and interventions for asthma and to avoid asthma health care resource shortages in advance.
Methods: In this study, we used a search index combined with air pollution data, weather data, and historical admissions data to forecast asthma admissions using machine learning.
Results: Results demonstrated that the best area under the curve in the test set that can be achieved is 0.832, using all predictors mentioned earlier.
Conclusion: A search index is a powerful predictor in asthma admissions forecast, and a recent search index can reflect current asthma admissions with a lag-effect to a certain extent. The addition of a real-time, easily accessible search index improves forecasting capabilities and demonstrates the predictive potential of search index.
Keywords: asthma hospitalization; internet search; machine learning.
Copyright © 2018 John Wiley & Sons, Ltd.