Observational Study
Copyright ©The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Clin Cases. Apr 26, 2023; 11(12): 2716-2728
Published online Apr 26, 2023. doi: 10.12998/wjcc.v11.i12.2716
Severe/critical COVID-19 early warning system based on machine learning algorithms using novel imaging scores
Qiu-Yu Li, Zhuo-Yu An, Zi-Han Pan, Zi-Zhen Wang, Yi-Ren Wang, Xi-Gong Zhang, Ning Shen
Qiu-Yu Li, Zi-Han Pan, Ning Shen, Department of Respiratory and Critical Care Medicine, Peking University Third Hospital, Beijing 100191, China
Zhuo-Yu An, Yi-Ren Wang, Department of Education, Peking University People’s Hospital, Beijing 100044, China
Zi-Zhen Wang, Department of Education, China-Japan Friendship Hospital, Beijing 100029, China
Xi-Gong Zhang, Department of Education, Beijing Jishuitan Hospital, Beijing 100096, China
Author contributions: Li QY and An ZY reviewed the literature and contributed to manuscript drafting and revising, both contributed equally to this manuscript, and considered as co-first authors; Pan ZH, Wang ZZ, Wang YR, Zhang XG, Shen N contributed to making a revision to the manuscript; Li QY also contributed to conceptualization, methodology, and funding acquisition; Li QY, An ZY and Zhang XG contributed equally to this paper; all authors issued final approval for the version to be submitted.
Supported by National Natural Science Foundation of China, No. 81900641; and the Research Funding of Peking University, BMU2021MX020 and BMU2022MX008.
Institutional review board statement: This study was reviewed and approved by the Ethics Committee of Peking University Third Hospital (IRB00006761-M2020054 and IRB00006761-M2020055).
Conflict-of-interest statement: The authors declare that they have no conflicts of interest with the contents of this article.
Data sharing statement: No additional data are available.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Ning Shen, MD, Chief Doctor, Department of Respiratory and Critical Care Medicine, Peking University Third Hospital, No. 49 Huayuan North Road, Haidian District, Beijing 100191, China. shenning1972@126.com
Received: November 1, 2022
Peer-review started: November 1, 2022
First decision: January 30, 2023
Revised: February 12, 2023
Accepted: March 17, 2023
Article in press: March 17, 2023
Published online: April 26, 2023
Processing time: 171 Days and 22.5 Hours
Abstract
BACKGROUND

Early identification of severe/critical coronavirus disease 2019 (COVID-19) is crucial for timely treatment and intervention. Chest computed tomography (CT) score has been shown to be a significant factor in the diagnosis and treatment of pneumonia, however, there is currently a lack of effective early warning systems for severe/critical COVID-19 based on dynamic CT evolution.

AIM

To develop a severe/critical COVID-19 prediction model using a combination of imaging scores, clinical features, and biomarker levels.

METHODS

This study used an improved scoring system to extract and describe the chest CT characteristics of COVID-19 patients. The study also took into consideration the general clinical indicators such as dyspnea, oxygen saturation, alternative lengthening of telomeres (ALT), and androgen suppression treatment (AST), which are commonly associated with severe/critical COVID-19 cases. The study employed lasso regression to evaluate and rank the significance of different disease characteristics.

RESULTS

The results showed that blood oxygen saturation, ALT, IL-6/IL-10, combined score, ground glass opacity score, age, crazy paving mode score, qsofa, AST, and overall lung involvement score were key factors in predicting severe/critical COVID-19 cases. The study established a COVID-19 severe/critical early warning system using various machine learning algorithms, including XGBClassifier, Logistic Regression, MLPClassifier, RandomForestClassifier, and AdaBoost Classifier. The study concluded that the prediction model based on the improved CT score and machine learning algorithms is a feasible method for early detection of severe/critical COVID-19 evolution.

CONCLUSION

The findings of this study suggest that a prediction model based on improved CT scores and machine learning algorithms is effective in detecting the early warning signals of severe/critical COVID-19.

Keywords: COVID-19; Clinical prediction model; Electron computed tomography; Machine learning

Core Tip: The computed tomography (CT) score is a relatively objective and clinically accessible semiquantitative assessment tool for patients with coronavirus disease 2019 (COVID-19). The CT scores of common, severe, and critically ill patients showed different trends, and there were differences between the groups of patients as the disease progressed. Patients who are recovering from the disease can be monitored via CT at reduced intervals to reduce their radiation exposure and financial burden. The 2 wk CT scores of the patients were important for predicting disease deterioration in hospitalized patients who have an average admission severity rating. The qSOFA score, aspartate aminotransferase, oxygenation, and dyspnea were important for the prediction of severe/critical COVID-19 disease.