Shafiekhani Sajad, Namdar Peyman, Rafiei Sima
Department of Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
Research Center for Biomedical Technologies and Robotics, Tehran, Iran.
Digit Health. 2022 Mar 28;8:20552076221085057. doi: 10.1177/20552076221085057. eCollection 2022 Jan-Dec.
Centers for Disease Control and Prevention data showed that about 40% of coronavirus disease 2019 (COVID-19) patients had been suffering from at least one underlying medical condition were hospitalized; in which nearly 33% of them needed to be admitted to the intensive care unit (ICU) to receive specialized medical services. Our study aimed to find a proper machine learning algorithm that can predict confirmed COVID-19 hospital admissions with high accuracy.
We obtained data on daily COVID-19 cases in regular medical inpatient units, emergency department, and ICU in the time window between 21 July 2020 and 21 November 2021. Data for the first 183 days (training data set) were used for long short-term memory (LSTM) network, adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR) and decision tree model training, whilst the remaining data for the last 60 days (test data set) were used for model validation. To predict the number of ICU and non-ICU patients, we used these models. Finally, a user-friendly graphical user interface unit was designed to load any time series data (here the trend of population of COVID-19 patients) and train LSTM, ANFIS, SVR or tree models for the prediction of COVID-19 cases for one week ahead.
All models predicted the dynamics of COVID-19 cases in ICU and non- wards. The values of root-mean-square error and as model assessment metrics showed that ANFIS model had better predictive power among all models.
Artificial intelligence-based forecasting models such as ANFIS system or deep learning approach based on LSTM or regression models including SVR or tree regression play a key role in forecasting the required number of beds or other types of medical facilities during the coronavirus pandemic. Thus, the designed graphical user interface of the present study can be used for optimum management of resources by health care systems amid COVID-19 pandemic.
美国疾病控制与预防中心的数据显示，约40%的2019冠状病毒病（COVID-19）患者因至少患有一种基础疾病而住院；其中近33%的患者需要入住重症监护病房（ICU）接受专科医疗服务。我们的研究旨在找到一种合适的机器学习算法，能够高精度预测确诊的COVID-19患者的住院情况。
我们获取了2020年7月21日至2021年11月21日时间窗口内普通内科住院病房、急诊科和ICU的每日COVID-19病例数据。前183天的数据（训练数据集）用于长短期记忆（LSTM）网络、自适应神经模糊推理系统（ANFIS）、支持向量回归（SVR）和决策树模型训练，而最后60天的其余数据（测试数据集）用于模型验证。为预测ICU和非ICU患者的数量，我们使用了这些模型。最后，设计了一个用户友好的图形用户界面单元，用于加载任何时间序列数据（此处为COVID-19患者数量趋势），并训练LSTM、ANFIS、SVR或树模型以预测未来一周的COVID-19病例。
所有模型都预测了ICU和非病房中COVID-19病例的动态情况。作为模型评估指标的均方根误差值表明，ANFIS模型在所有模型中具有更好的预测能力。
基于人工智能的预测模型，如ANFIS系统或基于LSTM的深度学习方法，以及包括SVR或树回归在内的回归模型，在预测冠状病毒大流行期间所需的病床数量或其他类型医疗设施方面发挥着关键作用。因此，本研究设计的图形用户界面可用于在COVID-19大流行期间医疗保健系统对资源的优化管理。
