Comparison of deep learning approaches to predict COVID-19 infection.
Comparison of deep learning approaches to predict COVID-19 infection.
复制标题
DOI：
10.1016/j.chaos.2020.110120
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Turkoglu I
中科院分区：
文献类型：
--
作者：
Alakus TB;Turkoglu I
利用深度学习应用模型提供COVID-19疾病的预测研究，该模型具有实验室发现而不是X射线或CT图像。以确保这种新型肺炎的预测模型。引起COVID-19（冠状病毒病）的SARS-CoV 2病毒已成为一种流行病，并已在世界各地蔓延。由于病例数量日益增加，需要时间来解释实验室结果，因此出现了治疗和结果方面的局限性。由于这些限制，出现了对具有预测算法的临床决策系统的需求。预测算法可以通过识别疾病来缓解医疗保健系统的压力。在这项研究中，我们使用深度学习和实验室数据进行临床预测模型，估计哪些患者可能会感染COVID-19疾病。为了评估我们的模型的预测性能，计算了精确度，F1分数，召回率，AUC和准确度分数。用来自600名患者的18个实验室结果对模型进行了测试，并用10倍交叉验证和训练-测试分割方法进行了验证。实验结果表明，我们的预测模型识别患有COVID-19疾病的患者的准确率为86.66%，F1评分为91.89%，精确率为86.75%，召回率为99.42%，AUC为62.50%。据观察，根据实验室发现训练的预测模型可用于预测COVID-19感染，并有助于医学专家正确地优先考虑资源。我们的模型（可在（https：//github.com/burakalakuss/COVID-19-Clinical）获得）可用于协助医学专家验证他们的初步实验室发现，也可用于临床预测研究。
To provide a prediction study for COVID-19 disease with deep learning application models with laboratory findings rather than X-ray or CT images. To ensure the prediction model for this novel pneumonia. The SARS-CoV2 virus, which causes COVID-19 (coronavirus disease) has become a pandemic and has expanded all over the world. Because of increasing number of cases day by day, it takes time to interpret the laboratory findings thus the limitations in terms of both treatment and findings are emerged. Due to such limitations, the need for clinical decisions making system with predictive algorithms has arisen. Predictive algorithms could potentially ease the strain on healthcare systems by identifying the diseases. In this study, we perform clinical predictive models that estimate, using deep learning and laboratory data, which patients are likely to receive a COVID-19 disease. To evaluate the predictive performance of our models, precision, F1-score, recall, AUC, and accuracy scores calculated. Models were tested with 18 laboratory findings from 600 patients and validated with 10 fold cross-validation and train-test split approaches. The experimental results indicate that our predictive models identify patients that have COVID-19 disease at an accuracy of 86.66%, F1-score of 91.89%, precision of 86.75%, recall of 99.42%, and AUC of 62.50%. It is observed that predictive models trained on laboratory findings could be used to predict COVID-19 infection, and can be helpful for medical experts to prioritize the resources correctly. Our models (available at (https://github.com/burakalakuss/COVID-19-Clinical)) can be employed to assists medical experts in validating their initial laboratory findings, and can also be used for clinical prediction studies.
登录
查看更多内容
影响因子：
6.1
作者：
Liu, Kui;Fang, Yuan-Yuan;Liu, Hui-Guo
通讯作者：
Liu, Hui-Guo
影响因子：
20.4
作者：
Mandrekar, Jayawant N.
通讯作者：
Mandrekar, Jayawant N.
影响因子：
3.7
作者：
Ledezma, Carlos A.;Zhou, Xin;Diaz-Zuccarini, Vanessa
通讯作者：
Diaz-Zuccarini, Vanessa
影响因子：
3.1
作者：
Alfaras, Miquel;Soriano, Miguel C.;Ortin, Silvia
通讯作者：
Ortin, Silvia
影响因子：
6.1
作者：
Karthick, P. A.;Ghosh, Diptasree Maitra;Ramakrishnan, S.
通讯作者：
Ramakrishnan, S.