Deep learning for predicting COVID-19 malignant progression

•The first approach leverages both sequential CT scans and clinical data to predict COVID-19 malignant progression.•Our method achieves an AUC of 0.920 in the single-center study and an average AUC of 0.874 in the multicenter study.•The proposed domain adaptation can improve the generalization power...

Full description

Saved in:
Bibliographic Details
Published in:Medical image analysis 2021-08, Vol.72, p.102096-102096, Article 102096
Main Authors: Fang, Cong, Bai, Song, Chen, Qianlan, Zhou, Yu, Xia, Liming, Qin, Lixin, Gong, Shi, Xie, Xudong, Zhou, Chunhua, Tu, Dandan, Zhang, Changzheng, Liu, Xiaowu, Chen, Weiwei, Bai, Xiang, Torr, Philip H.S.
Format: Article
Language:English
Subjects:
Aspartate aminotransferase
Brain natriuretic peptide
C-reactive protein
Calcium-binding protein
Computed tomography
Coronaviruses
COVID-19
Creatinine
Deep Learning
Domain adaptation
Early warning systems
Feature fusion
Health services
Humans
Malignant progression
Patients
SARS-CoV-2
Tomography, X-Ray Computed
Troponin
Warning systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•The first approach leverages both sequential CT scans and clinical data to predict COVID-19 malignant progression.•Our method achieves an AUC of 0.920 in the single-center study and an average AUC of 0.874 in the multicenter study.•The proposed domain adaptation can improve the generalization power of our model in the multicenter study.•Our model automatically identifies crucial indicators that contribute to the malignant progression. [Display omitted] As COVID-19 is highly infectious, many patients can simultaneously flood into hospitals for diagnosis and treatment, which has greatly challenged public medical systems. Treatment priority is often determined by the symptom severity based on first assessment. However, clinical observation suggests that some patients with mild symptoms may quickly deteriorate. Hence, it is crucial to identify patient early deterioration to optimize treatment strategy. To this end, we develop an early-warning system with deep learning techniques to predict COVID-19 malignant progression. Our method leverages CT scans and the clinical data of outpatients and achieves an AUC of 0.920 in the single-center study. We also propose a domain adaptation approach to improve the generalization of our model and achieve an average AUC of 0.874 in the multicenter study. Moreover, our model automatically identifies crucial indicators that contribute to the malignant progression, including Troponin, Brain natriuretic peptide, White cell count, Aspartate aminotransferase, Creatinine, and Hypersensitive C-reactive protein.
ISSN:1361-8415
1361-8423
DOI:10.1016/j.media.2021.102096