Reliability of Machine Learning in Eliminating Data Redundancy of Radiomics and Reflecting Pathophysiology in COVID-19 Pneumonia: Impact of CT Reconstruction Kernels on Accuracy
18
Issued Date
2022-01-01
Resource Type
eISSN
21693536
Scopus ID
2-s2.0-85139444789
Journal Title
IEEE Access
Volume
10
Start Page
120901
End Page
120921
Rights Holder(s)
SCOPUS
Bibliographic Citation
IEEE Access Vol.10 (2022) , 120901-120921
Suggested Citation
Statsenko Y., Habuza T., Talako T., Kurbatova T., Simiyu G.L., Smetanina D., Sido J., Qandil D.S., Meribout S., Gelovani J.G., Gorkom K.N.V., Almansoori T.M., Zahmi F.A., Loney T., Bedson A., Naidoo N., Dehdashtian A., Ljubisavljevic M., Koteesh J.A., Das K.M. Reliability of Machine Learning in Eliminating Data Redundancy of Radiomics and Reflecting Pathophysiology in COVID-19 Pneumonia: Impact of CT Reconstruction Kernels on Accuracy. IEEE Access Vol.10 (2022) , 120901-120921. 120921. doi:10.1109/ACCESS.2022.3211080 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/84356
Title
Reliability of Machine Learning in Eliminating Data Redundancy of Radiomics and Reflecting Pathophysiology in COVID-19 Pneumonia: Impact of CT Reconstruction Kernels on Accuracy
Author's Affiliation
Sheikh Shakhbout Medical City
Siriraj Hospital
Ras Al Khaima Medical and Health Sciences University (RAK)
Mohammed Bin Rashid University of Medicine and Health Sciences
Université Constantine 3
College of Medicine and Health Sciences United Arab Emirates University
Tawam Hospital
Wayne State University
United Arab Emirates University
Eye Microsurgery Center ''Voka''
Mediclinic Parkview Hospital
Siriraj Hospital
Ras Al Khaima Medical and Health Sciences University (RAK)
Mohammed Bin Rashid University of Medicine and Health Sciences
Université Constantine 3
College of Medicine and Health Sciences United Arab Emirates University
Tawam Hospital
Wayne State University
United Arab Emirates University
Eye Microsurgery Center ''Voka''
Mediclinic Parkview Hospital
Other Contributor(s)
Abstract
Background: Radiomical data are redundant but they might serve as a tool for lung quantitative assessment reflecting disease severity and actual physiological status of COVID-19 patients. Objective: Test the effectiveness of machine learning in eliminating data redundancy of radiomics and reflecting pathophysiologic changes in patients with COVID-19 pneumonia. Methods: We analyzed 605 cases admitted to Al Ain Hospital from 24 February to 1 July, 2020. They met the following inclusion criteria: age ≥ 18 years; inpatient admission; PCR positive for SARS-CoV-2; lung CT available at PACS. We categorized cases into 4 classes: mild <5% of pulmonary parenchymal involvement, moderate - 5-24%, severe - 25-49%, and critical ≥50 %. We used CT scans to build regression models predicting the oxygenation level, respiratory and cardiovascular functioning. Results: Radiomical findings are a reliable source of information to assess the functional status of patients with COVID-19. Machine learning models can predict the oxygenation level, respiratory and