Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Denmark; Biomedical Engineering, School of Science and Technology, SUSS, Singapore; College of Engineering, Science and Environment, University of Newcastle, Singapore.
Department of Regional Health Research, University of Southern Denmark, Denmark; Hospital of South West Jutland, Esbjerg, Denmark.
Comput Biol Med. 2021 Aug;135:104541. doi: 10.1016/j.compbiomed.2021.104541. Epub 2021 Jun 3.
The volume of daily patient arrivals at Emergency Departments (EDs) is unpredictable and is a significant reason of ED crowding in hospitals worldwide. Timely forecast of patients arriving at ED can help the hospital management in early planning and avoiding of overcrowding. Many different ED patient arrivals forecasting models have previously been proposed by using time series analysis methods. Even though the time series methods such as Linear and Logistic Regression, Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), Exponential Smoothing (ES), and Artificial Neural Network (ANN) have been explored extensively for the ED forecasting model development, the few significant limitations of these methods associated in the analysis of time series data make the models inadequate in many practical situations. Therefore, in this paper, Machine Learning (ML)-based Random Forest (RF) regressor, and Deep Neural Network (DNN)-based Long Short-Term Memory (LSTM) and Convolutional Neural network (CNN) methods, which have not been explored to the same extent as the other time series techniques, are implemented by incorporating meteorological and calendar parameters for the development of forecasting models. The performances of the developed three models in forecasting ED patient arrivals are evaluated. Among the three models, CNN outperformed for short-term (3 days in advance) patient arrivals prediction with Mean Absolute Percentage Error (MAPE) of 9.24% and LSTM performed better for moderate-term (7 days in advance) patient arrivals prediction with MAPE of 8.91% using weather forecast information. Whereas, LSTM model outperformed with MAPE of 8.04% compared to 9.53% by CNN and 10.10% by RF model for current day prediction of patient arrivals using 3 days past weather information. Thus, for short-term ED patient arrivals forecasting, DNN-based model performed better compared to RF regressor ML-based model.
急诊科（ED）每日患者到达量是不可预测的，也是全球医院 ED 拥堵的一个重要原因。及时预测到达 ED 的患者可以帮助医院管理部门提前规划，避免过度拥挤。之前已经使用时间序列分析方法提出了许多不同的 ED 患者到达预测模型。尽管时间序列方法（如线性和逻辑回归、自回归综合移动平均（ARIMA）、季节性 ARIMA（SARIMA）、指数平滑（ES）和人工神经网络（ANN））已被广泛用于开发 ED 预测模型，但这些方法在分析时间序列数据时存在一些显著的局限性，使得模型在许多实际情况下都不够充分。因此，在本文中，我们实现了基于机器学习（ML）的随机森林（RF）回归器和基于深度神经网络（DNN）的长短期记忆（LSTM）和卷积神经网络（CNN）方法，这些方法尚未像其他时间序列技术那样得到充分探索，同时纳入气象和日历参数来开发预测模型。评估了为预测 ED 患者到达量而开发的这三个模型的性能。在这三个模型中，CNN 在预测短期（提前 3 天）患者到达量方面表现最佳，平均绝对百分比误差（MAPE）为 9.24%，LSTM 在预测中期（提前 7 天）患者到达量方面表现更好，MAPE 为 8.91%，同时使用天气预报信息。然而，LSTM 模型在使用过去 3 天的天气信息对当天的患者到达量进行预测时，MAPE 为 8.04%，而 CNN 为 9.53%，RF 回归器为 10.10%，表现优于其他两个模型。因此，对于短期 ED 患者到达量的预测，基于 DNN 的模型比基于 RF 回归器的 ML 模型表现更好。
Zotero 插件