ABSTRACT
This study aimed to build an machine learning based model to predict the COVID-19 severity and reveal risk factors related to COVID-19 severity based on laboratory testing and clinical data for 420 participants, using tree-based models such as XGBoost, LightGBM, random forest. We calculated the Odds Ratios (OR) to investigate whether the top-ranked features were statistically significant for severity classification, turning out that high sensitivity C-reactive protein (hs-CRP) was the most important feature for determining of COVID-19 severity and XGBoost model showed the highest performance in classifying COVID-19 severity and healthy controls with F1score (0.84) and AUC (0.87). We expect that our results are of considerable significance for early screening for diagnosing COVID-19 severity, which, in turn, assist in further retrospective research for uncommon infectious diseases. © 2023 IEEE.
ABSTRACT
BACKGROUND: The main manifestations of coronavirus disease-2019 (COVID-19) are similar to the many other respiratory diseases. In addition, the existence of numerous uncertainties in the prognosis of this condition has multiplied the need to establish a valid and accurate prediction model. This study aimed to develop a diagnostic model based on logistic regression to enhance the diagnostic accuracy of COVID-19. MATERIALS AND METHODS: A standardized diagnostic model was developed on data of 400 patients who were referred to Ayatollah Talleghani Hospital, Abadan, Iran, for the COVID-19 diagnosis. We used the Chi-square correlation coefficient for feature selection, and logistic regression in SPSS V25 software to model the relationship between each of the clinical features. Potentially diagnostic determinants extracted from the patient's history, physical examination, and laboratory and imaging testing were entered in a logistic regression analysis. The discriminative ability of the model was expressed as sensitivity, specificity, accuracy, and area under the curve, respectively. RESULTS: After determining the correlation of each diagnostic regressor with COVID-19 using the Chi-square method, the 15 important regressors were obtained at the level of P < 0.05. The experimental results demonstrated that the binary logistic regression model yielded specificity, sensitivity, and accuracy of 97.3%, 98.8%, and 98.2%, respectively. CONCLUSION: The destructive effects of the COVID-19 outbreak and the shortage of healthcare resources in fighting against this pandemic require increasing attention to using the Clinical Decision Support Systems equipped with supervised learning classification algorithms such as logistic regression.
ABSTRACT
COVID19 is a respiratory illness that is extremely infectious and is spreading at an alarming rate at the moment. Chest radiography images play an important part in the automated diagnosis of COVID19, which is accomplished via the use of several machine learning approaches. This chapter examines prognostic models for COVID-19 patients’ survival prediction based on clinical data and lung/lesion radiometric characteristics retrieved from chest imaging. While it seems that there are various early indicators of prognosis, we will discuss prognostic models or scoring systems that are useful exclusively to individuals who have received confirmation of their cancer diagnosis. A summary of some of the research work and strategies based on machine learning and computer vision that have been applied for the identification of COVID19 have been presented in this chapter. Some strategies based on pre-processing, segmentation, handmade features, deep features, and classification have been discussed, as well as some other techniques. Apart from that, a few relevant datasets have been provided, along with a few research gaps and challenges in the respective sector that have been identified, all of which will be useful for future study efforts. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.