Background

The current systems of reporting waiting time to patients in public emergency departments (EDs) has largely relied on rolling average or median estimators which have limited accuracy. This study proposes to use machine learning (ML) algorithms that significantly improve waiting time forecasts.

Methods

By implementing ML algorithms and using a large set of queueing and service flow variables, we provide evidence of the improvement in waiting time predictions for low acuity ED patients assigned to the waiting room. In addition to the mean squared prediction error (MSPE) and mean absolute prediction error (MAPE), we advocate to use the percentage of underpredicted observations. The use of ML algorithms is motivated by their advantages in exploring data connections in flexible ways, identifying relevant predictors, and preventing overfitting of the data. We also use quantile regression to generate time forecasts which may better address the patient’s asymmetric perception of underpredicted and overpredicted ED waiting times.

Results

Using queueing and service flow variables together with information on diurnal fluctuations, ML models outperform the best rolling average by over 20 % with respect to MSPE and quantile regression reduces the number of patients with large underpredicted waiting times by 42 %.

Conclusion

We find robust evidence that the proposed estimators generate more accurate ED waiting time predictions than the rolling average. We also show that to increase the predictive accuracy further, a hospital ED may decide to provide predictions to patients registered only during the daytime when the ED operates at full capacity, thus translating to more predictive service rates and the demand for treatments.

中文翻译：

---

预测急诊科患者的等待治疗时间

背景

当前向公共急诊部门（ED）的患者报告等待时间的系统很大程度上依赖于滚动平均值或中位数估计量，其准确性有限。这项研究建议使用机器学习（ML）算法来显着改善等待时间的预测。

方法

通过实施ML算法并使用大量排队和服务流变量，我们为分配给候诊室的低敏度ED患者的等待时间预测提供了改进的证据。除了均方预测误差（MSPE）和均值绝对预测误差（MAPE），我们提倡使用预测不足的百分比。机器学习算法的优势在于其以灵活方式探索数据连接，识别相关预测变量以及防止数据过度拟合的优势。我们还使用分位数回归来生成时间预测，以更好地解决患者对ED预测时间过低和过高的不对称感知。

结果

结合排队和服务流量变量以及日间波动信息，相对于MSPE，ML模型的最佳滚动平均值要高出20％以上，分位数回归将等待时间长的被低估的患者数量减少了42％。

结论

我们发现有力的证据表明，所提出的估计量比滚动平均值能产生更准确的ED等待时间预测。我们还表明，为进一步提高预测准确性，医院急诊室可能会决定仅在急诊室满负荷运转的白天向注册患者提供预测，从而转化为更高的预测服务率和治疗需求。