Department of Industrial and Manufacturing Systems Engineering, The University of Hong Kong, Pokfulam Road, Hong Kong.
Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong.
Int J Med Inform. 2020 Jul;139:104143. doi: 10.1016/j.ijmedinf.2020.104143. Epub 2020 Apr 12.
The objective of this study is to apply machine learning algorithms for real-time and personalized waiting time prediction in emergency departments. We also aim to introduce the concept of systems thinking to enhance the performance of the prediction models.
Four popular algorithms were applied: (i) stepwise multiple linear regression; (ii) artificial neural networks; (iii) support vector machines; and (iv) gradient boosting machines. A linear regression model served as a baseline model for comparison. We conducted computational experiments based on a dataset collected from an emergency department in Hong Kong. Model diagnostics were performed, and the results were cross-validated.
All the four machine learning algorithms with the use of systems knowledge outperformed the baseline model. The stepwise multiple linear regression reduced the mean-square error by almost 15%. The other three algorithms had similar performances, reducing the mean-square error by approximately 20%. Reductions of 17 - 22% in mean-square error due to the utilization of systems knowledge were observed.
The multi-dimensional stochasticity arising from the ED environment imposes a great challenge on waiting time prediction. The introduction of the concept of systems thinking led to significant enhancements of the models, suggesting that interdisciplinary efforts could potentially improve prediction performance.
Machine learning algorithms with the utilization of the systems knowledge could significantly improve the performance of waiting time prediction. Waiting time prediction for less urgent patients is more challenging.
本研究旨在应用机器学习算法对急诊科的实时和个性化等候时间进行预测。我们还旨在引入系统思维的概念来提高预测模型的性能。
应用了四种流行的算法：（i）逐步多元线性回归；（ii）人工神经网络；（iii）支持向量机；和（iv）梯度提升机。线性回归模型作为比较的基准模型。我们基于从香港一家急诊科收集的数据集进行了计算实验。进行了模型诊断，并对结果进行了交叉验证。
所有四种机器学习算法与系统知识的应用均优于基准模型。逐步多元线性回归将均方误差降低了近 15%。其他三种算法的性能相似，将均方误差降低了约 20%。由于系统知识的利用，观察到均方误差降低了 17-22%。
ED 环境中出现的多维随机性对等候时间预测构成了巨大挑战。系统思维概念的引入极大地提高了模型的性能，这表明跨学科的努力可能会潜在地提高预测性能。
利用系统知识的机器学习算法可以显著提高等候时间预测的性能。对不太紧急的患者的等候时间预测更具挑战性。
