Trend Prediction of Influenza and the Associated Pneumonia in Taiwan Using Machine Learning

摘要

Trend prediction of influenza and the associated pneumonia can provide the information for taking preventive actions for public health. This paper uses meteorological and pollution parameters, and acute upper respiratory infection (AVRI) outpatient number as input to multilayer perceptron (MLP) to predict the patient number of influenza and the associated pneumonia in the following week. The meteorological parameters in use are temperature and relative humidity, air pollution parameters are Particulate Matter 2.5 (PM 2.5) and Carbon Monoxide (CO), and the patient prediction includes both outpatients and inpatients. Patients are classified by tertiles into three categories: high, moderate, and low volumes. In the nationwide data analysis, the proposed method using MLP machine learning can reach the accuracy of 81.16% for the elderly population and 77.54% for overall population in Taiwan. The regional data analyses with various age groups are also provided in this paper.