Reliability of Machine Learning in Eliminating Data Redundancy of Radiomics and Reflecting Pathophysiology in COVID-19 Pneumonia: Impact of CT Reconstruction Kernels on Accuracy
oleh: Yauhen Statsenko, Tetiana Habuza, Tatsiana Talako, Tetiana Kurbatova, Gillian Lylian Simiyu, Darya Smetanina, Juana Sido, Dana Sharif Qandil, Sarah Meribout, Juri G. Gelovani, Klaus Neidl-Van Gorkom, Taleb M. Almansoori, Fatmah Al Zahmi, Tom Loney, Anthony Bedson, Nerissa Naidoo, Alireza Dehdashtian, Milos Ljubisavljevic, Jamal Al Koteesh, Karuna M. Das
| Format: | Article |
|---|---|
| Diterbitkan: | IEEE 2022-01-01 |
Deskripsi
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<inline-formula> <tex-math notation="LaTeX">$\geq 18$ </tex-math></inline-formula> 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 <inline-formula> <tex-math notation="LaTeX">$\geq50$ </tex-math></inline-formula>%. 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