Myska Vojtech, Genzor Samuel, Mezina Anzhelika, Burget Radim, Mizera Jan, Stybnar Michal, Kolarik Martin, Sova Milan, Dutta Malay Kishore
Department of Telecommunications, Faculty of Electrical Engineering and Communications, Brno University of Technology, Technicka 12, 616 00 Brno, Czech Republic.
Department of Respiratory Medicine, University Hospital Olomouc and Faculty of Medicine and Dentistry, Palacky University Olomouc, I. P. Pavlova 6, 779 00 Olomouc, Czech Republic.
Diagnostics (Basel). 2023 May 16;13(10):1755. doi: 10.3390/diagnostics13101755.
Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, -NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.
肺纤维化是新冠疫情最严重的长期后果之一。皮质类固醇治疗可增加康复几率；不幸的是，它也可能有副作用。因此，我们旨在开发预测模型，以便个性化选择能从皮质激素治疗中获益的患者。该实验使用了多种算法，包括逻辑回归、神经网络、决策树、极端梯度提升、随机森林、支持向量机、多层感知器、自适应增强和轻量级梯度提升机。此外，还提出了一种易于人工解释的模型。所有算法均在一个由总共281名患者组成的数据集上进行训练。每位患者在新冠治疗后开始时及三个月后都进行了检查。检查包括体格检查、血液检查、肺功能测试，以及基于X光和高分辨率计算机断层扫描的健康状况评估。决策树算法的平衡准确率（BA）为73.52%，ROC曲线下面积（ROC-AUC）为74.69%，F1分数为71.70%。其他实现高精度的算法包括随机森林（BA 70.00%，ROC-AUC 70.62%，F1分数67.92%）和自适应增强（BA 70.37%，ROC-AUC 63.58%，F1分数70.18%）。实验证明，在新冠治疗开始时获得的信息可用于预测患者是否能从皮质激素治疗中获益。临床医生可使用所提出的预测模型来做出个性化治疗决策。
