CASIA OpenIR  > 中国科学院分子影像重点实验室
A Deep Learning Radiomics Model to Identify Poor Outcome in COVID-19 Patients With Underlying Health Conditions: A Multicenter Study
Wang, Siwen1,2; Dong, Di1,2; Li, Liang3; Li, Hailin1,4; Bai, Yan5,6; Hu, Yahua7; Huang, Yuanyi8; Yu, Xiangrong9; Liu, Sibin8; Qiu, Xiaoming7; Lu, Ligong10; Wang, Meiyun5,6; Zha, Yunfei3; Tian, Jie1,4
Source PublicationIEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
ISSN2168-2194
2021-04-27
Volume25Issue:7Pages:2353-2362
Abstract

Objective: Coronavirus disease 2019 (COVID-19) has caused considerable morbidity and mortality, especially in patients with underlying health conditions. A precise prognostic tool to identify poor outcomes among such cases is desperately needed.

Methods: Total 400 COVID-19 patients with underlying health conditions were retrospectively recruited from 4 centers, including 54 dead cases (labeled as poor outcomes) and 346 patients discharged or hospitalized for at least 7 days since initial CT scan. Patients were allocated to a training set (n = 271), a test set (n = 68), and an external test set (n = 61). We proposed an initial CT-derived hybrid model by combining a 3D-ResNet10 based deep learning model and a quantitative 3D radiomics model to predict the probability of COVID-19 patients reaching poor outcome. The model performance was assessed by area under the receiver operating characteristic curve (AUC), survival analysis, and subgroup analysis.

Results: The hybrid model achieved AUCs of 0.876 (95% confidence interval: 0.752-0.999) and 0.864 (0.766-0.962) in test and external test sets, outperforming other models. The survival analysis verified the hybrid model as a significant risk factor for mortality (hazard ratio, 2.049 [1.462-2.871], P < 0.001) that could well stratify patients into high-risk and low-risk of reaching poor outcomes (P < 0.001).

Conclusion: The hybrid model that combined deep learning and radiomics could accurately identify poor outcomes in COVID-19 patients with underlying health conditions from initial CT scans. The great risk stratification ability could help alert risk of death and allow for timely surveillance plans.

KeywordCOVID-19 deep learning radiomics prognosis computed tomography
DOI10.1109/JBHI.2021.3076086
WOS KeywordSELECTION ; PREDICT
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Mathematical & Computational Biology ; Medical Informatics
WOS SubjectComputer Science, Information Systems ; Computer Science, Interdisciplinary Applications ; Mathematical & Computational Biology ; Medical Informatics
WOS IDWOS:000678341200001
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Sub direction classification医学影像处理与分析
Citation statistics
Cited Times:18[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/45647
Collection中国科学院分子影像重点实验室
Corresponding AuthorZha, Yunfei; Tian, Jie
Affiliation1.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Wuhan Univ, Renmin Hosp, Dept Radiol, Wuhan 430060, Peoples R China
4.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Beijing 100191, Peoples R China
5.Zhengzhou Univ, Henan Prov Peoples Hosp, Dept Med Imaging, Zhengzhou 450003, Peoples R China
6.Zhengzhou Univ, Peoples Hosp, Zhengzhou 450003, Peoples R China
7.Hubei Polytech Univ, Affiliated Hosp, Huangshi Cent Hosp, Edong Healthcare Grp,Dept Radiol, Huangshi 435000, Hubei, Peoples R China
8.Jingzhou Cent Hosp, Dept Radiol, Jingzhou 434020, Peoples R China
9.Jinan Univ, Zhuhai Peoples Hosp, Zhuhai Hosp, Dept Med Imaging, Zhuhai 519000, Peoples R China
10.Jinan Univ, Zhuhai Hosp, Zhuhai Precis Med Ctr, Zhuhai Intervent Med Ctr, Zhuhai 519000, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Wang, Siwen,Dong, Di,Li, Liang,et al. A Deep Learning Radiomics Model to Identify Poor Outcome in COVID-19 Patients With Underlying Health Conditions: A Multicenter Study[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2021,25(7):2353-2362.
APA Wang, Siwen.,Dong, Di.,Li, Liang.,Li, Hailin.,Bai, Yan.,...&Tian, Jie.(2021).A Deep Learning Radiomics Model to Identify Poor Outcome in COVID-19 Patients With Underlying Health Conditions: A Multicenter Study.IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,25(7),2353-2362.
MLA Wang, Siwen,et al."A Deep Learning Radiomics Model to Identify Poor Outcome in COVID-19 Patients With Underlying Health Conditions: A Multicenter Study".IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 25.7(2021):2353-2362.
Files in This Item: Download All
File Name/Size DocType Version Access License
A_Deep_Learning_Radi(3142KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Siwen]'s Articles
[Dong, Di]'s Articles
[Li, Liang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Siwen]'s Articles
[Dong, Di]'s Articles
[Li, Liang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Siwen]'s Articles
[Dong, Di]'s Articles
[Li, Liang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A_Deep_Learning_Radiomics_Model_to_Identify_Poor_Outcome_in_COVID-19_Patients_With_Underlying_Health_Conditions_A_Multicenter_Study.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.