@Article{info:doi/10.2196/15394，作者=“Cheng, Hao-Yuan and Wu, Yu-Chun and Lin, Min-Hau and Liu, Yu-Lun and Tsai, Yue-Yang and Wu, Jo-Hua and Pan, Ke- han and Ke, Chih-Jung and Chen, Chiu-Mei and Liu, Ding-Ping and Lin, I-Feng and chuan - xiangang”，title=“基于集成方法的机器学习模型在台湾流感准确实时预测中的应用:《发展与验证研究》，期刊=“J Med Internet Res”，年=“2020”，月=“8”，日=“5”，卷=“22”，号=“8”，页=“e15394”，关键词=“流感;流感样疾病;预测;机器学习;人工智能;流行预测;背景:台湾等亚热带地区季节性流感活动的变化给疫情防范带来了问题。自2004年以来，台湾疾病控制中心一直维持着全国流感实时监测系统。除了及时监测外，利用国家流感监测数据进行疫情预测可为公共卫生应对提供关键信息。 Objective: We aimed to develop predictive models using machine learning to provide real-time influenza-like illness forecasts. Methods: Using surveillance data of influenza-like illness visits from emergency departments (from the Real-Time Outbreak and Disease Surveillance System), outpatient departments (from the National Health Insurance database), and the records of patients with severe influenza with complications (from the National Notifiable Disease Surveillance System), we developed 4 machine learning models (autoregressive integrated moving average, random forest, support vector regression, and extreme gradient boosting) to produce weekly influenza-like illness predictions for a given week and 3 subsequent weeks. We established a framework of the machine learning models and used an ensemble approach called stacking to integrate these predictions. We trained the models using historical data from 2008-2014. We evaluated their predictive ability during 2015-2017 for each of the 4-week time periods using Pearson correlation, mean absolute percentage error (MAPE), and hit rate of trend prediction. A dashboard website was built to visualize the forecasts, and the results of real-world implementation of this forecasting framework in 2018 were evaluated using the same metrics. Results: All models could accurately predict the timing and magnitudes of the seasonal peaks in the then-current week (nowcast) ($\rho$=0.802-0.965; MAPE: 5.2{\%}-9.2{\%}; hit rate: 0.577-0.756), 1-week ($\rho$=0.803-0.918; MAPE: 8.3{\%}-11.8{\%}; hit rate: 0.643-0.747), 2-week ($\rho$=0.783-0.867; MAPE: 10.1{\%}-15.3{\%}; hit rate: 0.669-0.734), and 3-week forecasts ($\rho$=0.676-0.801; MAPE: 12.0{\%}-18.9{\%}; hit rate: 0.643-0.786), especially the ensemble model. In real-world implementation in 2018, the forecasting performance was still accurate in nowcasts ($\rho$=0.875-0.969; MAPE: 5.3{\%}-8.0{\%}; hit rate: 0.582-0.782) and remained satisfactory in 3-week forecasts ($\rho$=0.721-0.908; MAPE: 7.6{\%}-13.5{\%}; hit rate: 0.596-0.904). Conclusions: This machine learning and ensemble approach can make accurate, real-time influenza-like illness forecasts for a 4-week period, and thus, facilitate decision making. ", issn="1438-8871", doi="10.2196/15394", url="//www.mybigtv.com/2020/8/e15394", url="https://doi.org/10.2196/15394", url="http://www.ncbi.nlm.nih.gov/pubmed/32755888" }