Department of Biostatistics, Harvard School of Public Health, Boston, Massachusetts, USA.
Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA.
J Am Med Inform Assoc. 2019 Dec 1;26(12):1574-1583. doi: 10.1093/jamia/ocz154.
Emergency departments (EDs) are increasingly overcrowded. Forecasting patient visit volume is challenging. Reliable and accurate forecasting strategies may help improve resource allocation and mitigate the effects of overcrowding. Patterns related to weather, day of the week, season, and holidays have been previously used to forecast ED visits. Internet search activity has proven useful for predicting disease trends and offers a new opportunity to improve ED visit forecasting. This study tests whether Google search data and relevant statistical methods can improve the accuracy of ED volume forecasting compared with traditional data sources.
Seven years of historical daily ED arrivals were collected from Boston Children's Hospital. We used data from the public school calendar, National Oceanic and Atmospheric Administration, and Google Trends. Multiple linear models using LASSO (least absolute shrinkage and selection operator) for variable selection were created. The models were trained on 5 years of data and out-of-sample accuracy was judged using multiple error metrics on the final 2 years.
All data sources added complementary predictive power. Our baseline day-of-the-week model recorded average percent errors of 10.99%. Autoregressive terms, calendar and weather data reduced errors to 7.71%. Search volume data reduced errors to 7.58% theoretically preventing 4 improperly staffed days.
The predictive power provided by the search volume data may stem from the ability to capture population-level interaction with events, such as winter storms and infectious diseases, that traditional data sources alone miss.
This study demonstrates that search volume data can meaningfully improve forecasting of ED visit volume and could help improve quality and reduce cost.
急诊部（ED）越来越拥挤。预测患者就诊量具有挑战性。可靠且准确的预测策略可能有助于改善资源分配并减轻过度拥挤的影响。先前已经使用与天气、星期几、季节和节假日有关的模式来预测 ED 就诊量。互联网搜索活动已被证明可用于预测疾病趋势，并为改善 ED 就诊量预测提供了新的机会。本研究测试了 Google 搜索数据和相关统计方法是否可以提高 ED 量预测的准确性，与传统数据源相比。
从波士顿儿童医院收集了七年的历史每日 ED 到达数据。我们使用了公立学校日历、美国国家海洋和大气管理局以及 Google Trends 的数据。使用 LASSO（最小绝对收缩和选择算子）进行变量选择的多元线性模型。该模型在 5 年的数据上进行训练，并使用最后 2 年的多个误差指标来判断样本外准确性。
所有数据源都增加了互补的预测能力。我们的基线星期几模型记录的平均百分比误差为 10.99%。自回归项、日历和天气数据将误差降低到 7.71%。搜索量数据将误差降低到 7.58%，理论上可以防止 4 天人员配备不当。
搜索量数据提供的预测能力可能源于其捕捉人群与事件（如冬季风暴和传染病）之间相互作用的能力，而传统数据源单独错过。
本研究表明，搜索量数据可以显著提高 ED 就诊量的预测，并有助于提高质量和降低成本。
