metricas
covid
Enfermedades Infecciosas y Microbiología Clínica (English Edition) Factors associated with glucocorticoid dosing in treating patients with noncriti...
Journal Information
Vol. 43. Issue 7.
Pages 402-410 (August - September 2025)
Share
Download PDF
More article options
Visits
38
Vol. 43. Issue 7.
Pages 402-410 (August - September 2025)
Original article
Factors associated with glucocorticoid dosing in treating patients with noncritical COVID-19 pneumonia: Insights from an artificial intelligence-based CT imaging analysis
Factores asociados con la dosificación de glucocorticoides en el tratamiento de pacientes con neumonía por COVID-19 no crítica: perspectivas basadas en un análisis de imágenes de tomografía computarizada impulsado por inteligencia artificial
Visits
38
Jie Wanga, Chang Hea, Yu Shia, Kunkai Sua, Zhihui Huangb, Songli Duc, Xukun Lid, Wei Wua,
Corresponding author
1198042@zju.edu.cn

Corresponding authors.
, Jifang Shenga,
Corresponding author
jifang_sheng@zju.edu.cn

Corresponding authors.
a Zhejiang University First Affiliated Hospital State Key Laboratory for Diagnosis and Treatment of Severe Infectious Diseases, Hangzhou, Zhejiang, China
b Anji County People's Hospital, Huzhou, Zhejiang, China
c Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada
d Artificial Intelligence Lab, Hangzhou AiSmartVision Co., Ltd., Hangzhou, Zhejiang, China
This item has received
Article information
Abstract
Full Text
Bibliography
Download PDF
Statistics
Figures (6)
Show moreShow less
Tables (2)
Table 1. Baseline characteristics of hospitalized patients with COVID-19 pneumonia.
Tables
Table 2. Baseline laboratory test and CT imaging characteristics of low-dose (≤40mg) and high-dose (>40mg) groups in the training set.
Tables
Show moreShow less
Additional material (1)
Abstract
Objective

Glucocorticoids are vital in treating COVID-19, but standard dosage for noncritical patients remain controversial. To determine the optimal glucocorticoid dosage for noncritical COVID-19 patients, we analyzed factors influencing dosage and developed a predictive model.

Methods

We retrospectively analyzed 273 noncritical COVID-19 pneumonia patients underwent pulmonary CT and treated with glucocorticoids in a tertiary hospital (12/2022–01/2023). Patients were divided into low and high glucocorticoid dosage groups based on a daily 40mg methylprednisolone or equivalent. Artificial intelligence (AI)-based deep learning was utilized to assess pulmonary CT images for accurate lesion area, which then analyzed through multivariable logistic regression to explore their correlation with glucocorticoid dosage. A predictive model was developed and validated for dosage prediction.

Results

The primary analysis included 243 patients, with 168 in the training set and 75 in the validation set. High-dose treatment was administered to 139 patients (82.7%) and low-dose to 29 patients (17.3%) in the training cohort. A predictive model incorporating normally inflated ratio, ground-glass opacity (GGO) ratio, and consolidation ratio accurately predicted selection of high- or low-dose, in both training (AUC=0.803) and validation cohorts (AUC=0.836), respectively. In 30 patients with post-CT adjusted dosages, the predicted dosages highly matched with the actual adjusted dosages.

Conclusion

Glucocorticoid dosages for noncritical COVID-19 pneumonia treatment are influenced by pulmonary CT features. Our predictive model can predict glucocorticoid dosage, however, should be validated by larger, prospective studies.

Keywords:
COVID-19 pneumonia
Glucocorticoid
Pulmonary CT
Artificial intelligence
Abbreviations:
ICU
GGO
WHO
AI
DSC
BMI
ROC
ML
DL
CNN
WBC
PLT
L%
N%
CRP
PCT
ESR
ALT
AST
TB
TG
ALB
Cr
BUN
CK
hsTNI
GLU
Resumen
Objetivo

Los glucocorticoides son esenciales en el tratamiento de la COVID-19, pero la dosificación estándar para pacientes no críticos sigue siendo controvertida. Para determinar la dosificación óptima, analizamos los factores que influyen en ella y desarrollamos un modelo predictivo.

Métodos

Analizamos retrospectivamente a 273 pacientes con neumonía por COVID-19 no crítica tratados con glucocorticoides en un hospital terciario (de diciembre de 2022 a enero de 2023). Se dividieron en grupos de dosis baja y alta, según una dosis diaria de 40mg de metilprednisolona o equivalente. Se utilizó aprendizaje profundo basado en inteligencia artificial (IA) para analizar imágenes pulmonares y evaluar el área de lesión, correlacionada con la dosificación mediante regresión logística multivariable.

Resultados

Incluimos 243 pacientes: 168 en entrenamiento y 75 en validación. El 82,7% recibió dosis altas y el 17,3% dosis bajas. Un modelo predictivo basado en la proporción de inflamación normal, opacidad en vidrio esmerilado y consolidación predijo con precisión dosis altas o bajas (AUC=0,803 en entrenamiento, AUC=0,836 en validación). En 30 pacientes con dosis ajustadas post-TC las predicciones coincidieron con las dosis reales.

Conclusión

Las dosis de glucocorticoides están influenciadas por características pulmonares en la TC. El modelo predictivo es prometedor, pero requiere validación en estudios más amplios.

Palabras clave:
Neumonía por COVID-19
Glucocorticoides
TC pulmonar
Inteligencia artificial

Article

These are the options to access the full texts of the publication Enfermedades Infecciosas y Microbiología Clínica (English Edition)
Member

Socio de la Sociedad Española de Enfermedades Infecciosas y Microbiología Clínica

Para acceder a la revista

Es necesario que lo haga desde la zona privada de la web de la SEIMC, clique aquí

Para realizar los cursos formativos

La actividad estará abierta para socios de la SEIMC. IMPORTANTE, recuerde que requiere registro previo gratuito. Empezar aquí

Subscriber
Subscriber

If you already have your login data, please click here .

If you have forgotten your password you can you can recover it by clicking here and selecting the option “I have forgotten my password”
Subscribe
Subscribe to

Enfermedades Infecciosas y Microbiología Clínica (English Edition)

Purchase
Purchase article

Purchasing article the PDF version will be downloaded

Purchase now
Contact
Phone for subscriptions and reporting of errors
From Monday to Friday from 9 a.m. to 6 p.m. (GMT + 1) except for the months of July and August which will be from 9 a.m. to 3 p.m.
Calls from Spain
932 415 960
Calls from outside Spain
+34 932 415 960
E-mail
Article options
Tools
Supplemental materials