Journal
SENSORS
Volume 22, Issue 17, Pages -Publisher
MDPI
DOI: 10.3390/s22176709
Keywords
COVID-19; pneumonia; radiomic feature; machine learning; chest X-ray
Funding
- Korea Medical Device Development Fund by Korean government (Ministry of Science and ICT) [202011B06-02]
- Korea Medical Device Development Fund by Korean government (Ministry of Trade, Industry and Energy) [202011B06-02]
- Korea Medical Device Development Fund by Korean government (Ministry of Health Welfare) [202011B06-02]
- Korea Medical Device Development Fund by Korean government (Ministry of Food and Drug Safety) [202011B06-02]
- Korea Evaluation Institute of Industrial Technology (KEIT) [202011B06-02] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
Machine learning models were used to differentiate between COVID-19 and pneumonia based on radiomic features extracted from chest X-ray scans. The results showed that radiomic features could serve as indicators for distinguishing between COVID-19 and pneumonia, and different machine learning models had varying performances.
Machine learning approaches are employed to analyze differences in real-time reverse transcription polymerase chain reaction scans to differentiate between COVID-19 and pneumonia. However, these methods suffer from large training data requirements, unreliable images, and uncertain clinical diagnosis. Thus, in this paper, we used a machine learning model to differentiate between COVID-19 and pneumonia via radiomic features using a bias-minimized dataset of chest X-ray scans. We used logistic regression (LR), naive Bayes (NB), support vector machine (SVM), k-nearest neighbor (KNN), bagging, random forest (RF), extreme gradient boosting (XGB), and light gradient boosting machine (LGBM) to differentiate between COVID-19 and pneumonia based on training data. Further, we used a grid search to determine optimal hyperparameters for each machine learning model and 5-fold cross-validation to prevent overfitting. The identification performances of COVID-19 and pneumonia were compared with separately constructed test data for four machine learning models trained using the maximum probability, contrast, and difference variance of the gray level co-occurrence matrix (GLCM), and the skewness as input variables. The LGBM and bagging model showed the highest and lowest performances; the GLCM difference variance showed a high overall effect in all models. Thus, we confirmed that the radiomic features in chest X-rays can be used as indicators to differentiate between COVID-19 and pneumonia using machine learning.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available