Schweigler Lisa M, Desmond Jeffrey S, McCarthy Melissa L, Bukowski Kyle J, Ionides Edward L, Younger John G
Department of Emergency Medicine, University of Michigan, Ann Arbor, MI, USA.
Acad Emerg Med. 2009 Apr;16(4):301-8. doi: 10.1111/j.1553-2712.2009.00356.x. Epub 2009 Feb 4.
The authors investigated whether models using time series methods can generate accurate short-term forecasts of emergency department (ED) bed occupancy, using traditional historical averages models as comparison.
From July 2005 through June 2006, retrospective hourly ED bed occupancy values were collected from three tertiary care hospitals. Three models of ED bed occupancy were developed for each site: 1) hourly historical average, 2) seasonal autoregressive integrated moving average (ARIMA), and 3) sinusoidal with an autoregression (AR)-structured error term. Goodness of fits were compared using log likelihood and Akaike's Information Criterion (AIC). The accuracies of 4- and 12-hour forecasts were evaluated by comparing model forecasts to actual observed bed occupancy with root mean square (RMS) error. Sensitivity of prediction errors to model training time was evaluated, as well.
The seasonal ARIMA outperformed the historical average in complexity adjusted goodness of fit (AIC). Both AR-based models had significantly better forecast accuracy for the 4- and the 12-hour forecasts of ED bed occupancy (analysis of variance [ANOVA] p < 0.01), compared to the historical average. The AR-based models did not differ significantly from each other in their performance. Model prediction errors did not show appreciable sensitivity to model training times greater than 7 days.
Both a sinusoidal model with AR-structured error term and a seasonal ARIMA model were found to robustly forecast ED bed occupancy 4 and 12 hours in advance at three different EDs, without needing data input beyond bed occupancy in the preceding hours.
作者研究了使用时间序列方法的模型能否生成急诊科床位占用情况的准确短期预测，并将传统的历史平均模型作为对照。
从2005年7月至2006年6月，收集了三家三级医疗机构急诊科每小时床位占用情况的回顾性数据。为每个机构开发了三种急诊科床位占用情况模型：1）每小时历史平均值；2）季节性自回归积分滑动平均模型（ARIMA）；3）带有自回归（AR）结构误差项的正弦模型。使用对数似然和赤池信息准则（AIC）比较拟合优度。通过将模型预测与实际观察到的床位占用情况进行比较，并计算均方根（RMS）误差，来评估4小时和12小时预测的准确性。还评估了预测误差对模型训练时间的敏感性。
在复杂度调整后的拟合优度（AIC）方面，季节性ARIMA模型优于历史平均模型。与历史平均模型相比，两种基于AR的模型在急诊科床位占用情况的4小时和12小时预测方面，具有显著更好的预测准确性（方差分析[ANOVA]p<0.01）。两种基于AR的模型在性能上没有显著差异。当模型训练时间超过7天时，模型预测误差对训练时间没有明显的敏感性。
研究发现，带有AR结构误差项的正弦模型和季节性ARIMA模型，均能在三家不同的急诊科提前4小时和12小时，可靠地预测床位占用情况，且无需除前几小时床位占用情况之外的数据输入。
