Assessment of Time-Series Machine Learning Methods for Forecasting Hospital Discharge Volume
Assessment of Time-Series Machine Learning Methods for Forecasting Hospital Discharge Volume
复制标题
DOI：
10.1001/jamanetworkopen.2018.4087
复制
发表时间：
2018-11-01
影响因子：
13.8
通讯作者：
Perlis, Roy H.
中科院分区：
文献类型：
--
作者：
McCoy Jr, Thomas H.;Pellegrini, Amelia M.;Perlis, Roy H.
重要性预测出院量对资源分配具有重要意义，并代表了在风险升高期间改善患者安全性的机会。目的确定一种新的时间序列机器学习方法与简单方法相比预测出院量的性能。设计一项回顾性队列研究，2005年1月1日至2014年12月31日（医院1）或1月1日之间的新英格兰学术医疗中心。2005.和2010年12月31日（医院2），比较时间序列预测方法进行预测。数据分析于2017年2月28日至2018年8月30日进行。纳入了所有住院单位出院的组水平数据。除了传统的方法，一种技术最初开发的分配数据中心资源，并比较战略，纳入先验数据和频率的模型更新，进行了识别的模型应用程序，优化预测精度。主要成果和措施模型校准作为衡量的R-2，其次，天数的误差大于1 SD的日流量。第一医院出院人数为54411人（每日平均，149)而第二医院则有47456宗出院个案（每日平均130宗）。机器学习方法在两个站点都得到了很好的校准（R-2，分别为0.843和0.726），并且在两个站点的预测年中，分别只有13天和22天的日流量误差大于1 SD。末值结转模型的表现稍差（校准R-2，分别为0.781和0.596），分别有13和46个1 SD或更大的误差。更频繁的再培训和培训集超过1年的机器学习方法的performance.Conclusions和相关性的影响最小的出院量也许可以可靠地预测使用简单的结转模型，以及从机器学习的方法。后者的好处似乎并不依赖于广泛的训练数据，并可能使预测提前1年，具有上级的绝对准确性结转模型。
IMPORTANCE Forecasting the volume of hospital discharges has important implications for resource allocation and represents an opportunity to improve patient safety at periods of elevated risk.OBJECTIVE To determine the performance of a new time-series machine learning method for forecasting hospital discharge volume compared with simpler methods.DESIGN A retrospective cohort study of daily hospital discharge volumes at 2 large, New England academic medical centers between January 1, 2005, and December 31, 2014 (hospital 1), or January 1. 2005. and December 31, 2010 (hospital 2), comparing time-series forecasting methods for prediction was performed. Data analysis was conducted from February 28, 2017, to August 30, 2018. Group-level data for all discharges from inpatient units were included. In addition to conventional methods, a technique originally developed for allocating data center resources, and comparison strategies for incorporating prior data and frequency of model updates, was conducted to identify the model application that optimized forecast accuracy.MAIN OUTCOMES AND MEASURES Model calibration as measured by R-2 and, secondarily, number of days with errors greater than 1 SD of daily volume.RESULTS During the forecasted year, hospital 1 had 54 411 discharges (daily mean. 149) and hospital 2 had 47 456 discharges (daily mean, 130). The machine learning method was well calibrated at both sites (R-2, 0.843 and 0.726, respectively) and made errors greater than 1 SD of daily volume on only 13 and 22 days, respectively, of the forecast year at the 2 sites. Last-value-carried-forward models performed somewhat less well (calibration R-2, 0.781 and 0.596, respectively) with 13 and 46 errors of 1 SD or greater, respectively. More frequent retraining and training sets of longer than 1 year had minimal effects on the machine learning method's performance.CONCLUSIONS AND RELEVANCE Volume of hospital discharges can perhaps be reliably forecasted using simple carry-forward models as well as methods drawn from machine learning. The benefit of the latter does not appear to be dependent on extensive training data and may enable forecasts up to 1 year in advance with superior absolute accuracy to carry-forward models.