Background: COVID-19 has become a challenge worldwide and properly planning of medical resources is the key to combating COVID-19. In the US Veteran Affairs Health Care System (VA), many of the enrollees are susceptible to COVID-19. Predicting the COVID-19 to allocate medical resources promptly becomes a critical issue. When the VA enrollees have COVID-19 symptoms, it is recommended that their first step should be to call the VA Call Center. For confirmed COVID-19 patients, the median time from the first symptom to hospital admission was seven days. By predicting the number of COVID-19 related calls, we could predict imminent surges in healthcare use and plan medical resources ahead. Objective: The study aims to develop a method to forecast the daily number of COVID-19 related calls for each of the 110 VA medical centers. Methods: In the proposed method, we pre-trained a model using a cluster of medical centers and fine-tuned it for individual medical centers. At the cluster level, we performed feature selection to select significant features and automatic hyper-parameter search to select optimal hyper-parameter value combinations for the model. Conclusions: This study proposed an accurate method to forecast the daily number of COVID-19 related calls for VA medical centers. The proposed method was able to overcome modeling challenges by grouping similar medical centers into clusters to enlarge the dataset for training models, and using hyper-parameter search to automatically find optimal hyper-parameter value combinations for models. With the proposed method, surges in health care can be predicted ahead. This allows health care practitioners to better plan medical resources and combat COVID-19.
翻译:COVID-19已经成为全球范围的一个挑战,适当规划医疗资源是抗击COVID-19的关键。在美国退伍军人医疗体系(VA)中,许多注册者都容易感染COVID-19。预测COVID-19以迅速分配医疗资源是一个关键问题。当VA注册者有COVID-19症状时,建议他们的第一步应该是呼叫VA呼叫中心。对于已确认的COVID-19病人,从第一个症状到住院住院的中间时间是7天。通过预测COVID-19相关电话的数量,我们可以预测保健使用量的即将激增,并规划未来的医疗资源。目标:这项研究旨在为110个VA医疗中心中的每一个中心制定每天预测COVID-19相关电话数量的方法。方法:在拟议的方法中,我们预先训练一个使用医疗中心集群的模型,并为各个医疗中心进行微调。在集群一级,我们进行了特征选择,并自动进行超临界值搜索,以选择最佳的模型,将HID-19类医疗使用最佳的模型,从而可以选择最佳的超比数值计算方法。这一研究旨在预测与VA相关模型的实验室的模型。该组的计算方法。该组的计算,以更精确的计算方法对V类的计算。