metricas
covid
Radiología (English Edition) Prognostic value of the extent of affected lung parenchyma in COVID-19 pneumonia...
Journal Information
Vol. 67. Issue 5.
(September - October 2025)
Visits
22
Vol. 67. Issue 5.
(September - October 2025)
Original articles
Prognostic value of the extent of affected lung parenchyma in COVID-19 pneumonia patients: Visual estimation versus automatic quantification by artificial intelligence
Valor pronóstico de la extensión del parénquima pulmonar afectado en la neumonía COVID-19: estimación visual versus cuantificación automática por inteligencia artificial
Visits
22
I. Soriano Aguaderoa,
Corresponding author
isoriano@unav.es

Corresponding author.
, A. Ezponda Casajúsb, A. Paternain Nuinb, M. Vidorretac, G. Bastarrika Alemañb
a Servicio de Radiodiagnóstico, Hospital Universitario de Navarra, Pamplona, Navarra, Spain
b Servicio de Radiodiagnóstico, Clínica Universidad de Navarra, Pamplona, Navarra, Spain
c Siemens Healthcare, Madrid, Spain
This item has received
Article information
Abstract
Full Text
Bibliography
Download PDF
Statistics
Figures (5)
Show moreShow less
Tables (4)
Table 1. Demographic, clinical, laboratory and treatment characteristics of all patients.
Tables
Table 2. Demographic, clinical, laboratory and treatment features for all patients per prognostic group.
Tables
Table 3. Role of variables significantly differing between prognostic groups in predicting ICU admission or death. Univariate logistic regression analysis.
Tables
Table 4. Comparison of prognostic models using multivariate logistic regression analysis.
Tables
Show moreShow less
Abstract
Objective

To compare the prognostic impact of the extent of lung disease detected on computed tomography (CT) when assessed visually by an expert radiologist compared to automatically by an artificial intelligence (AI) system in patients with COVID-19 pneumonia.

Material and methods

A retrospective study of patients with clinical suspicion of COVID-19 pneumonia which assessed the extent of lung involvement visually and by AI. Patients were divided into poor (death/ICU) and good (discharge) prognosis groups. Univariate and multivariate analyses (logistic regression) were performed on the variables that demonstrated significant differences between both groups.

Results

Patients with a poor prognosis more frequently had greater lung involvement visually (stages 3–4; 37.5% vs 14.3%; p = 0.001) and by AI (stages 3–4; 35% vs 6.2%; p < 0.001). The radiologist-AI agreement correlation coefficient was excellent (0.905; p < 0.001). High blood pressure (OR 4.26; p < 0.001), alterations in levels of creatinine (OR 5.63; p < 0.001), lactate dehydrogenase (OR 11.69; p < 0.001) and D-dimer (OR 5.68; p < 0.001), and the extent of affected lung parenchyma assessed visually (stage 1vs4 OR 10.36; p = 0.001) and by AI (stage 1vs4 OR 25; p = 0.001) were the variables with the greatest prognostic impact in the univariate analysis. The multivariate analysis models considering the extent assessed visually and by AI did not demonstrate any significant differences (AUC 0.876 vs 0.870; p = 0.278).

Conclusion

The extent of affected lung parenchyma on CT images demonstrates prognostic value both on their own and in conjunction with clinical factors and blood levels in patients with COVID-19 pneumonia. No significant differences were observed between the radiologist&apos;s visual estimate and the AI-based automatic detection system used in this study.

Keywords:
Computed tomography
Chest CT
Artificial intelligence
COVID-19
Prognosis
Resumen
Objetivo

Comparar el impacto pronóstico de la extensión de la enfermedad pulmonar en tomografía computarizada (TC) valorada de forma visual por un radiólogo experto y de manera automática por un sistema de inteligencia artificial (IA) en pacientes con neumonía COVID-19.

Material y métodos

Estudio retrospectivo que incluyó pacientes con sospecha clínica de neumonía COVID-19 y valoración visual y por IA de la extensión de la afectación pulmonar. Se dividió a los pacientes en grupos de mal (fallecimiento/UCI) y buen pronóstico (alta). Se realizaron análisis uni y multivariante (regresión logística) de las variables que demostraron diferencias significativas entre ambos grupos.

Resultados

Los pacientes de mal pronóstico presentaron más frecuentemente una mayor extensión de la afectación pulmonar de manera visual (estadios 3–4; 37,5% vs 14,3%;p = 0,001) y estimada por la IA (estadios 3–4; 35% vs 6,2%;p < 0,001). El coeficiente de correlación de concordancia radiólogo-IA fue excelente (0,905;p < 0,001). La hipertensión arterial (OR 4,26;p < 0,001), las alteraciones analíticas de creatinina (OR 5,63;p < 0,001), lactato-deshidrogenasa (OR 11,69;p < 0,001) y dímero D (OR 5,68;p < 0,001) y la extensión del parénquima pulmonar afectado valorados visualmente (estadio 1vs4 OR 10,36;p = 0,001) y por la IA (estadio 1vs4 OR 25;p = 0,001) fueron las variables con mayor impacto pronóstico en el análisis univariante. Los modelos de análisis multivariante considerando la extensión valorada visualmente y por la IA no demostraron diferencias significativas entre ellos (AUC 0,876 vs 0,870;p = 0,278).

Conclusión

La valoración de la extensión del parénquima pulmonar afectado en las imágenes de TC, aislada y en conjunto con factores clínicos y analíticos, demuestra valor pronóstico en pacientes con neumonía COVID-19. No se observaron diferencias significativas entre la estimación visual del radiólogo y el sistema de detección automática basado en IA empleado en este estudio.

Palabras clave:
Tomografía computarizada
TC torácica
Inteligencia artificial
COVID-19
Pronóstico

Article

These are the options to access the full texts of the publication Radiología (English Edition)
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”
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