TY - JOUR
T1 - A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records
AU - Gong, Kuang
AU - Wu, Dufan
AU - Arru, Chiara Daniela
AU - Homayounieh, Fatemeh
AU - Neumark, Nir
AU - Guan, Jiahui
AU - Buch, Varun
AU - Kim, Kyungsang
AU - Bizzo, Bernardo Canedo
AU - Ren, Hui
AU - Tak, Won Young
AU - Park, Soo Young
AU - Lee, Yu Rim
AU - Kang, Min Kyu
AU - Park, Jung Gil
AU - Carriero, Alessandro
AU - Saba, Luca
AU - Masjedi, Mahsa
AU - Talari, Hamidreza
AU - Babaei, Rosa
AU - Mobin, Hadi Karimi
AU - Ebrahimian, Shadi
AU - Guo, Ning
AU - Digumarthy, Subba R.
AU - Dayan, Ittai
AU - Kalra, Mannudeep K.
AU - Li, Quanzheng
N1 - Publisher Copyright:
© 2021
PY - 2021/6
Y1 - 2021/6
N2 - Purpose: As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease of 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based on their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients’ electronic health records (EHR), which included vital signs and laboratory data, with deep learning- and CT-based severity prediction. Method: We first developed a CT segmentation network using datasets from multiple institutions worldwide. Two biomarkers were extracted from the CT images: total opacity ratio (TOR) and consolidation ratio (CR). After obtaining TOR and CR, further prognosis analysis was conducted on datasets from INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3. For each data cohort, generalized linear model (GLM) was applied for prognosis prediction. Results: For the deep learning model, the correlation coefficient of the network prediction and manual segmentation was 0.755, 0.919, and 0.824 for the three cohorts, respectively. The AUC (95 % CI) of the final prognosis models was 0.85(0.77,0.92), 0.93(0.87,0.98), and 0.86(0.75,0.94) for INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3 cohorts, respectively. Either TOR or CR exist in all three final prognosis models. Age, white blood cell (WBC), and platelet (PLT) were chosen predictors in two cohorts. Oxygen saturation (SpO2) was a chosen predictor in one cohort. Conclusion: The developed deep learning method can segment lung infection regions. Prognosis results indicated that age, SpO2, CT biomarkers, PLT, and WBC were the most important prognostic predictors of COVID-19 in our prognosis model.
AB - Purpose: As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease of 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based on their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients’ electronic health records (EHR), which included vital signs and laboratory data, with deep learning- and CT-based severity prediction. Method: We first developed a CT segmentation network using datasets from multiple institutions worldwide. Two biomarkers were extracted from the CT images: total opacity ratio (TOR) and consolidation ratio (CR). After obtaining TOR and CR, further prognosis analysis was conducted on datasets from INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3. For each data cohort, generalized linear model (GLM) was applied for prognosis prediction. Results: For the deep learning model, the correlation coefficient of the network prediction and manual segmentation was 0.755, 0.919, and 0.824 for the three cohorts, respectively. The AUC (95 % CI) of the final prognosis models was 0.85(0.77,0.92), 0.93(0.87,0.98), and 0.86(0.75,0.94) for INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3 cohorts, respectively. Either TOR or CR exist in all three final prognosis models. Age, white blood cell (WBC), and platelet (PLT) were chosen predictors in two cohorts. Oxygen saturation (SpO2) was a chosen predictor in one cohort. Conclusion: The developed deep learning method can segment lung infection regions. Prognosis results indicated that age, SpO2, CT biomarkers, PLT, and WBC were the most important prognostic predictors of COVID-19 in our prognosis model.
KW - COVID-19
KW - Computed tomography
KW - Deep learning
KW - Electronic health records
KW - Prognosis
UR - http://www.scopus.com/inward/record.url?scp=85104458617&partnerID=8YFLogxK
U2 - 10.1016/j.ejrad.2021.109583
DO - 10.1016/j.ejrad.2021.109583
M3 - Article
SN - 0720-048X
VL - 139
JO - European Journal of Radiology
JF - European Journal of Radiology
M1 - 109583
ER -