A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness

Purpose: The novel coronavirus pneumonia (COVID-19) has continually spread and mutated, requiring a patient risk stratification system to optimize medical resources and improve pandemic response. We aimed to develop a conformal prediction-based tri-light warning system for stratifying COVID-19 patie...

Full description

Saved in:
Bibliographic Details
Main Authors: Chuanjun Xu, Qinmei Xu, Li Liu, Mu Zhou, Zijian Xing, Zhen Zhou, Danyang Ren, Changsheng Zhou, Longjiang Zhang, Xiao Li, Xianghao Zhan, Olivier Gevaert, Guangming Lu
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:European Journal of Radiology Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352047724000583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122132507983872
author Chuanjun Xu
Qinmei Xu
Li Liu
Mu Zhou
Zijian Xing
Zhen Zhou
Danyang Ren
Changsheng Zhou
Longjiang Zhang
Xiao Li
Xianghao Zhan
Olivier Gevaert
Guangming Lu
author_facet Chuanjun Xu
Qinmei Xu
Li Liu
Mu Zhou
Zijian Xing
Zhen Zhou
Danyang Ren
Changsheng Zhou
Longjiang Zhang
Xiao Li
Xianghao Zhan
Olivier Gevaert
Guangming Lu
author_sort Chuanjun Xu
collection DOAJ
description Purpose: The novel coronavirus pneumonia (COVID-19) has continually spread and mutated, requiring a patient risk stratification system to optimize medical resources and improve pandemic response. We aimed to develop a conformal prediction-based tri-light warning system for stratifying COVID-19 patients, applicable to both original and emerging variants. Methods: We retrospectively collected data from 3646 patients across multiple centers in China. The dataset was divided into a training set (n = 1451), a validation set (n = 662), an external test set from Huoshenshan Field Hospital (n = 1263), and a specific test set for Delta and Omicron variants (n = 544). The tri-light warning system extracts radiomic features from CT (computed tomography) and integrates clinical records to classify patients into high-risk (red), uncertain-risk (yellow), and low-risk (green) categories. Models were built to predict ICU (intensive care unit) admissions (adverse cases in training/validation/Huoshenshan/variant test sets: n = 39/21/262/11) and were evaluated using AUROC ((area under the receiver operating characteristic curve)) and AUPRC ((area under the precision-recall curve)) metrics. Results: The dataset included 1830 men (50.2 %) and 1816 women (50.8 %), with a median age of 53.7 years (IQR [interquartile range]: 42–65 years). The system demonstrated strong performance under data distribution shifts, with AUROC of 0.89 and AUPRC of 0.42 for original strains, and AUROC of 0.77–0.85 and AUPRC of 0.51–0.60 for variants. Conclusion: The tri-light warning system can enhance pandemic responses by effectively stratifying COVID-19 patients under varying conditions and data shifts.
format Article
id doaj-art-c18272aff51b4df1a687f4c510bb6b87
institution Kabale University
issn 2352-0477
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series European Journal of Radiology Open
spelling doaj-art-c18272aff51b4df1a687f4c510bb6b872024-12-15T06:15:48ZengElsevierEuropean Journal of Radiology Open2352-04772024-12-0113100603A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparednessChuanjun Xu0Qinmei Xu1Li Liu2Mu Zhou3Zijian Xing4Zhen Zhou5Danyang Ren6Changsheng Zhou7Longjiang Zhang8Xiao Li9Xianghao Zhan10Olivier Gevaert11Guangming Lu12Department of Radiology, the Second Hospital of Nanjing, Nanjing University of Chinese Medicine, Nanjing 210003, ChinaDepartment of Biomedical Data Science (BMIR), Department of Medicine, Stanford University, Stanford, CA 94304, USADepartment of Computer Science, University of California Santa Cruz, Santa Cruze, CA 95064, USADepartment of Computer Science, Rutgers University, 110 Frelinghuysen Road, Piscataway, NJ 08854, USADepartment of Deepwise AI Lab, Deepwise Inc., Beijing, ChinaDepartment of Deepwise AI Lab, Deepwise Inc., Beijing, ChinaDepartment of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USADepartment of Medical Imaging, Jinling Hospital, Nanjing, Jiangsu, ChinaDepartment of Medical Imaging, Jinling Hospital, Nanjing, Jiangsu, ChinaDepartment of Medical Imaging, Jinling Hospital, Nanjing, Jiangsu, China; Corresponding authors.Department of Bioengineering, Stanford University, Stanford 94305, USA; Corresponding authors.Department of Biomedical Data Science (BMIR), Department of Medicine, Stanford University, Stanford, CA 94304, USA; Corresponding authors.Department of Medical Imaging, Jinling Hospital, Nanjing, Jiangsu, China; Corresponding authors.Purpose: The novel coronavirus pneumonia (COVID-19) has continually spread and mutated, requiring a patient risk stratification system to optimize medical resources and improve pandemic response. We aimed to develop a conformal prediction-based tri-light warning system for stratifying COVID-19 patients, applicable to both original and emerging variants. Methods: We retrospectively collected data from 3646 patients across multiple centers in China. The dataset was divided into a training set (n = 1451), a validation set (n = 662), an external test set from Huoshenshan Field Hospital (n = 1263), and a specific test set for Delta and Omicron variants (n = 544). The tri-light warning system extracts radiomic features from CT (computed tomography) and integrates clinical records to classify patients into high-risk (red), uncertain-risk (yellow), and low-risk (green) categories. Models were built to predict ICU (intensive care unit) admissions (adverse cases in training/validation/Huoshenshan/variant test sets: n = 39/21/262/11) and were evaluated using AUROC ((area under the receiver operating characteristic curve)) and AUPRC ((area under the precision-recall curve)) metrics. Results: The dataset included 1830 men (50.2 %) and 1816 women (50.8 %), with a median age of 53.7 years (IQR [interquartile range]: 42–65 years). The system demonstrated strong performance under data distribution shifts, with AUROC of 0.89 and AUPRC of 0.42 for original strains, and AUROC of 0.77–0.85 and AUPRC of 0.51–0.60 for variants. Conclusion: The tri-light warning system can enhance pandemic responses by effectively stratifying COVID-19 patients under varying conditions and data shifts.http://www.sciencedirect.com/science/article/pii/S2352047724000583COVID-19 pandemicMulti-modal artificial intelligenceRisk stratificationConformal predictionMulti-center study
spellingShingle Chuanjun Xu
Qinmei Xu
Li Liu
Mu Zhou
Zijian Xing
Zhen Zhou
Danyang Ren
Changsheng Zhou
Longjiang Zhang
Xiao Li
Xianghao Zhan
Olivier Gevaert
Guangming Lu
A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness
European Journal of Radiology Open
COVID-19 pandemic
Multi-modal artificial intelligence
Risk stratification
Conformal prediction
Multi-center study
title A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness
title_full A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness
title_fullStr A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness
title_full_unstemmed A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness
title_short A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness
title_sort tri light warning system for hospitalized covid 19 patients credibility based risk stratification for future pandemic preparedness
topic COVID-19 pandemic
Multi-modal artificial intelligence
Risk stratification
Conformal prediction
Multi-center study
url http://www.sciencedirect.com/science/article/pii/S2352047724000583
work_keys_str_mv AT chuanjunxu atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT qinmeixu atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT liliu atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT muzhou atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT zijianxing atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT zhenzhou atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT danyangren atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT changshengzhou atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT longjiangzhang atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT xiaoli atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT xianghaozhan atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT oliviergevaert atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT guangminglu atrilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT chuanjunxu trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT qinmeixu trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT liliu trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT muzhou trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT zijianxing trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT zhenzhou trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT danyangren trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT changshengzhou trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT longjiangzhang trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT xiaoli trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT xianghaozhan trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT oliviergevaert trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness
AT guangminglu trilightwarningsystemforhospitalizedcovid19patientscredibilitybasedriskstratificationforfuturepandemicpreparedness