Severity-onset prediction of COVID-19 via artificial-intelligence analysis of multivariate factors

Progression to a severe condition remains a major risk factor for the COVID-19 mortality. Robust models that predict the onset of severe COVID-19 are urgently required to support sensitive decisions regarding patients and their treatments. In this study, we developed a multivariate survival model ba...

Full description

Saved in:
Bibliographic Details
Published in:Heliyon 2023-08, Vol.9 (8), p.e18764-e18764, Article e18764
Main Authors: Fu, Yu, Zeng, Lijiao, Huang, Pilai, Liao, Mingfeng, Li, Jialu, Zhang, Mingxia, Shi, Qinlang, Xia, Zhaohua, Ning, Xinzhong, Mo, Jiu, Zhou, Ziyuan, Li, Zigang, Yuan, Jing, Wang, Lifei, He, Qing, Wu, Qikang, Liu, Lei, Liao, Yuhui, Qiao, Kun
Format: Article
Language:English
Subjects:
Artificial-intelligence analysis
COVID-19
Severe disease onset prediction
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:Progression to a severe condition remains a major risk factor for the COVID-19 mortality. Robust models that predict the onset of severe COVID-19 are urgently required to support sensitive decisions regarding patients and their treatments. In this study, we developed a multivariate survival model based on early-stage CT images and other physiological indicators and biomarkers using artificial-intelligence analysis to assess the risk of severe COVID-19 onset. We retrospectively enrolled 338 adult patients admitted to a hospital in China (severity rate, 31.9%; mortality rate, 0.9%). The physiological and pathological characteristics of the patients with severe and non-severe outcomes were compared. Age, body mass index, fever symptoms upon admission, coexisting hypertension, and diabetes were the risk factors for severe progression. Compared with the non-severe group, the severe group demonstrated abnormalities in biomarkers indicating organ function, inflammatory responses, blood oxygen, and coagulation function at an early stage. In addition, by integrating the intuitive CT images, the multivariable survival model showed significantly improved performance in predicting the onset of severe disease (mean time-dependent area under the curve = 0.880). Multivariate survival models based on early-stage CT images and other physiological indicators and biomarkers have shown high potential for predicting the onset of severe COVID-19.
ISSN:2405-8440
2405-8440
DOI:10.1016/j.heliyon.2023.e18764