Shanbehzadeh Mostafa, Kazemi-Arpanahi Hadi, Orooji Azam, Mobarak Sara, Jelvay Saeed
Assistant Professor of Health Information Management, Department of Health Information Technology, School of Paramedical, Ilam University of Medical Sciences, Ilam, Iran.
Assistant Professor of Health Information Management, Department of Health Information Technology, Abadan University of Medical Sciences, Abadan, Iran.
J Educ Health Promot. 2021 Aug 31;10:285. doi: 10.4103/jehp.jehp_1424_20. eCollection 2021.
Given coronavirus disease (COVID-19's) unknown nature, diagnosis, and treatment is very complex up to the present time. Thus, it is essential to have a framework for an early prediction of the disease. In this regard, machines learning (ML) could be crucial to extract concealed patterns from mining of huge raw datasets then it establishes high-quality predictive models. At this juncture, we aimed to apply different ML techniques to develop clinical predictive models and select the best performance of them.
The dataset of Ayatollah Talleghani hospital, COVID-19 focal center affiliated to Abadan University of Medical Sciences have been taken into consideration. The dataset used in this study consists of 501 case records with two classes (COVID-19 and non COVID-19) and 32 columns for the diagnostic features. ML algorithms such as Naïve Bayesian, Bayesian Net, random forest (RF), multilayer perceptron, K-star, C4.5, and support vector machine were developed. Then, the recital of selected ML models was assessed by the comparison of some performance indices such as accuracy, sensitivity, specificity, precision, F-score, and receiver operating characteristic (ROC).
The experimental results indicate that RF algorithm with the accuracy of 92.42%, specificity of 75.70%, precision of 92.30%, sensitivity of 92.40%, F-measure of 92.00%, and ROC of 97.15% has the best capability for COVID-19 diagnosis and screening.
The empirical results reveal that RF model yielded higher performance as compared to other six classification models. It is promising to the implementation of RF model in the health-care settings to increase the accuracy and speed of disease diagnosis for primary prevention, screening, surveillance, and early treatment.
鉴于冠状病毒病（COVID-19）的性质、诊断和治疗目前尚不明朗，极为复杂。因此，建立一个疾病早期预测框架至关重要。在这方面，机器学习（ML）对于从海量原始数据集中挖掘隐藏模式并建立高质量预测模型可能至关重要。在此关头，我们旨在应用不同的ML技术来开发临床预测模型并选择其中性能最佳的模型。
考虑了阿巴丹医科大学附属的COVID-19重点中心阿亚图拉·塔莱加尼医院的数据集。本研究中使用的数据集由501条病例记录组成，分为两类（COVID-19和非COVID-19），有32列诊断特征。开发了朴素贝叶斯、贝叶斯网络、随机森林（RF）、多层感知器、K星、C4.5和支持向量机等ML算法。然后，通过比较一些性能指标，如准确率、灵敏度、特异性、精度、F分数和受试者工作特征（ROC）曲线，来评估所选ML模型的性能。
实验结果表明，随机森林（RF）算法在COVID-19诊断和筛查方面具有最佳性能，其准确率为92.42%，特异性为75.70%，精度为92.30%，灵敏度为92.40%，F值为92.00%，ROC曲线下面积为97.15%。
实证结果表明，与其他六种分类模型相比，随机森林（RF）模型具有更高的性能。将随机森林（RF）模型应用于医疗保健环境，有望提高疾病诊断的准确性和速度，以进行一级预防、筛查、监测和早期治疗。
