PDF(Sci-hub)
Abstract：
The aim of this study is to propose a model based on machine learning (ML) and Internet of Things (IoT) to diagnose patients with COVID-19 in smart hospitals. In this sense, it was emphasized that by the representation for the role of ML models and IoT relevant technologies in smart hospital environment. The accuracy rate of diagnosis (classification) based on laboratory findings can be improved via light ML models. Three ML models, namely, naive Bayes (NB), Random Forest (RF), and support vector machine (SVM), were trained and tested on the basis of laboratory datasets. Three main methodological scenarios of COVID-19 diagnoses, such as diagnoses based on original and normalized datasets and those based on feature selection, were presented. Compared with benchmark studies, our proposed SVM model obtained the most substantial diagnosis performance (up to 95%). The proposed model based on ML and IoT can be served as a clinical decision support system. Furthermore, the outcomes could reduce the workload for doctors, tackle the issue of patient overcrowding, and reduce mortality rate during the COVID-19 pandemic.
摘要：
这项研究的目的是提出一种基于机器学习（ML）和物联网（IoT）的模型，以诊断智慧医院中的COVID-19患者。在这个意义上,强调了ML模型和物联网相关技术在智能医院环境中的作用。基于实验室发现的诊断（分类）的准确率可以通过轻ML模型来提高。三种ML模型，即,朴素贝叶斯(NB)，随机森林(RF),和支持向量机(SVM)，在实验室数据集的基础上进行了培训和测试。COVID-19诊断的三种主要方法学情景，例如基于原始和规范化数据集的诊断以及基于特征选择的诊断，被介绍了。与基准研究相比，我们提出的SVM模型获得了最实质性的诊断性能(高达95%)。所提出的基于ML和物联网的模型可以用作临床决策支持系统。此外，结果可以减少医生的工作量，解决病人过度拥挤的问题，并降低COVID-19大流行期间的死亡率。
