Open Access 01-12-2021 | COVID-19 | Research Letter
A practical integrated radiomics model predicting intensive care hospitalization in COVID-19
Published in: Critical Care | Issue 1/2021
Login to get accessExcerpt
It has been widely demonstrated that radiological imaging significantly contributes to diagnosing and monitoring pulmonary and systemic involvement of patients affected by COVID-19 using different techniques like chest X-ray (CXR), Computed Tomography (CT), and Magnetic Resonance Imaging [1‐3]. Recently, several authors proposed the application of advanced imaging tools including machine learning and radiomics for COVID-19. For instance, Chandra et al. developed an automatic screening method based on radiomic features and Wang et al. used radiomics to distinguish COVID-19 from other viral infections [4, 5]. Moreover, Ferreira Junior et al. [6], using a publicly available cohort, demonstrated that radiomics not only correlates with the etiologic agent of acute infections but also supports the short-term risk stratification of COVID-19 patients. Inspired by these interesting results, we developed and tested a CXR-based radiomics integrated model including demographics, first-line laboratory and clinical findings collected at admission and we assessed the predicting role of such model for Intensive Care Unit (ICU) hospitalization and overall outcome. We retrospectively examined CXR at admission of 203 patients hospitalized in our tertiary center for COVID-19 (positive at RT-PCR) (Table 1). Eighteen patients deceased; 56 patients were treated in ICU and 147 in COVID-19 wards only. One radiologist with 10 years of experience in thoracic imaging, segmented the lungs of each patient as illustrated in Fig. 1 using an open source software (3D Slicer, www.slicer.org). The manual segmentation was performed by the segment editor and paint tools avoiding the inclusion of hilar and cardiac shadows. The radiomics extension was applied for the extraction of 33 features of first and second order: first-order statistics, gray level co-occurrence matrix, and gray level run length matrix. Factor analysis allowed the selection of five features highly correlating: maximum, kurtosis, inverse variance, cluster shade, and run length non-uniformity normalized (Fig. 1). The logistic regression analysis demonstrated that among the five radiomic features and the clinical and laboratory variables, only inverse variance, run length non-uniformity normalized, and C-reactive protein levels were significant predictors of ICU hospitalization (each, p < 0.05). None of the examined variables played a significant role in predicting the overall outcome (p > 0.05, each).
Table 1
Characteristics of the examined population
Characteristics at admission
|
Entire cohort
|
Patients treated in ICU
|
Patients treated in Covid-19 wards
|
---|---|---|---|
Age (years) (mean ± SD)
|
67.6 ± 14
|
68.8 ± 10
|
67.2 ± 15.6
|
Gender (female/male)
|
60/143
|
10/46
|
50/97
|
Fever (> 37.5 C) (yes/no)
|
178/25
|
51/5
|
127/20
|
Status (alive/deceased)
|
185/18
|
49/7
|
136/11
|
Red blood cells count (× 1012 L−1) (mean ± SD)
|
4.5 ± 0.6
|
4.4 ± 0.5
|
4.5 ± 0.6
|
Hemoglobin (g/l) (mean ± SD)
|
13 ± 2
|
13 ± 2
|
13 ± 2
|
White blood cells count (× 109 L−1) (mean ± SD)
|
7 ± 4
|
8 ± 4
|
6.8 ± 4
|
Lymphocytes count (× 109 L−1) (mean ± SD)
|
1.1 ± 0.9
|
0.8 ± 0.4
|
1.1 ± 1
|
C-reactive protein (mg/L−1) (mean ± SD)
|
80 ± 69
|
116 ± 88
|
65 ± 54
|
×
…