Prediction of COVID-19 Severity Using Chest Computed Tomography and Laboratory Measurements: Evaluation Using a Machine Learning Approach

Abstract

Background Most of the mortality resulting from COVID-19 has been associated with severe disease. Effective treatment of severe cases remains a challenge due to the lack of early detection of the infection. Objective This study aimed to develop an effective prediction model for COVID-19 severity by combining radiological outcome with clinical biochemical indexes. Methods A total of 46 patients with COVID-19 (10 severe, 36 nonsevere) were examined. To build the prediction model, a set of 27 severe and 151 nonsevere clinical laboratory records and computerized tomography (CT) records were collected from these patients. We managed to extract specific features from the patients’ CT images by using a recently published convolutional neural network. We also trained a machine learning model combining these features with clinical laboratory results. Results We present a prediction model combining patients’ radiological outcomes with their clinical biochemical indexes to identify severe COVID-19 cases. The prediction model yielded a cross-validated area under the receiver operating characteristic (AUROC) score of 0.93 and an F1 score of 0.89, which showed a 6% and 15% improvement, respectively, compared to the models based on laboratory test features only. In addition, we developed a statistical model for forecasting COVID-19 severity based on the results of patients’ laboratory tests performed before they were classified as severe cases; this model yielded an AUROC score of 0.81. Conclusions To our knowledge, this is the first report predicting the clinical progression of COVID-19, as well as forecasting severity, based on a combined analysis using laboratory tests and CT images.

The Applications of Artificial Intelligence in Chest Imaging of COVID-19 Patients: A Literature Review

“…They segmented CT imaging through a deep CNN to extract essential features and selected 12 laboratory tests that showed the largest change in the two groups of patients, mainly D-dimer, LDH and lymphocytes as predictors of higher mortality risk. Moreover, lymphocytes, neutrophils, D-dimer and platelets-large cell ratio demonstrated a significant correlation with selected CT features [101].…”

The diagnostic accuracy of Artificial Intelligence-Assisted CT imaging in COVID-19 disease: A systematic review and meta-analysis

“…Based on the number of enrolled images, 32,857 images (19,623‬ COVID-19 images and 13,234 Healthy images) classified by analysis were included. The AI algorithm based on the neural network was established in a number of research articles [ 21 , 22 , 23 , 25 , 26 , 27 , 29 , 30 , 31 , 33 , 34 , 35 , 36 , 37 , 41 , 42 , 43 , 47 , 48 , 50 , 51 , 52 , 53 , 54 , 55 , 57 ]. Among the included studies, twenty-nine models were selected for meta-analysis on DL assisted detection for predict COVID-19 [ 21 , 22 , 25 , 26 , 27 , 30 , 33 , 34 , 35 , 36 , 37 , 40 , 41 , 42 , 46 , 47 , 50 , 51 , 52 , 53 , 54 , 56 , 57 ] and fourteen models on ML assisted detection for predict COVID-19 [ 21 , 24 , 28 , 31 , 38 , 43 , 45 , 46 , 48 , 49 ] ( Table 1 ).…”

“…Daowei Li et al, 2020, showed that the AUR score of ML was 0.93 [ 34 ]. However, in our study, pooled AUC in ML was higher, 0.97 (95% CI, 0.96-0.99).…”

“…Among the 37 studies [ 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 ] of image-based analysis, the pooled sensitivity was 0.90 (95% CI, 0.90 - 0.91), specificity was 0.90 (95% CI, 0.90 - 0.91), the AUC was 0.96 (95% CI, 0.91 - 0.98), and diagnostic odds ratio (DOR) was 88.98 (95% CI, 56.38 – 140.44) as shown in ( Figure 2 ) ( Supplementary Figures 2-8 ).

Figure 2 The summary receiver-operating characteristic (SROC) curves of the diagnostic performance of AI and CT-Scan on detection.

…”

A deep learning approach for predicting severity of COVID-19 patients using a parsimonious set of laboratory markers

“…Recently, there has been a proliferation of studies proposing prediction models based on various clinical parameters aimed at early stratification of deteriorating patients (Abdulaal et al, 2020;Aktar et al, 2021;Gao et al, 2020;Yan et al, 2020). These approaches are primarily based on traditional machine learning approaches (Aktar et al, 2021) such as support vector machines (SVM) (Gao et al, 2020), random forests (RF) (An et al, 2020), or deep neural networks based (DNN) (Li et al, 2020) methods specifically when it comes to analyzing X-ray or computed tomography (CT) images (Lassau et al, 2021). Despite these advances, we have yet to see a practical system, which could be used universally with an evidence of generalizability to help with early identification of patients, who develop severe clinical trajectory.…”