Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.

Chest X-ray (CXR) imaging plays a pivotal role in the diagnosis and prognosis of viral pneumonia. However, distinguishing COVID-19 CXRs from other viral infections remains challenging due to highly similar radiographic features. Most existing deep learning (DL) models focus on differentiating COVID-...

Full description

Saved in:
Bibliographic Details
Main Authors: Nastaran Enshaei, Arash Mohammadi, Farnoosh Naderkhani, Nick Daneman, Rawan Abu Mughli, Reut Anconina, Ferco H Berger, Robert Andrew Kozak, Samira Mubareka, Ana Maria Villanueva Campos, Keshav Narang, Thayalasuthan Vivekanandan, Adrienne Kit Chan, Philip Lam, Nisha Andany, Anastasia Oikonomou
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0328061
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849684770325266432
author Nastaran Enshaei
Arash Mohammadi
Farnoosh Naderkhani
Nick Daneman
Rawan Abu Mughli
Reut Anconina
Ferco H Berger
Robert Andrew Kozak
Samira Mubareka
Ana Maria Villanueva Campos
Keshav Narang
Thayalasuthan Vivekanandan
Adrienne Kit Chan
Philip Lam
Nisha Andany
Anastasia Oikonomou
author_facet Nastaran Enshaei
Arash Mohammadi
Farnoosh Naderkhani
Nick Daneman
Rawan Abu Mughli
Reut Anconina
Ferco H Berger
Robert Andrew Kozak
Samira Mubareka
Ana Maria Villanueva Campos
Keshav Narang
Thayalasuthan Vivekanandan
Adrienne Kit Chan
Philip Lam
Nisha Andany
Anastasia Oikonomou
author_sort Nastaran Enshaei
collection DOAJ
description Chest X-ray (CXR) imaging plays a pivotal role in the diagnosis and prognosis of viral pneumonia. However, distinguishing COVID-19 CXRs from other viral infections remains challenging due to highly similar radiographic features. Most existing deep learning (DL) models focus on differentiating COVID-19 from community-acquired pneumonia (CAP) rather than other viral pneumonias and often overlook baseline CXRs, missing the critical window for early detection and intervention. Moreover, manual severity scoring of COVID-19 CXRs by radiologists is subjective and time-intensive, highlighting the need for automated systems. This study introduces a DL system for distinguishing COVID-19 from other viral pneumonias on baseline CXRs acquired within three days of PCR testing, and for automated severity scoring of COVID-19 CXRs. The system was developed using a dataset of 2,547 patients (808 COVID-19, 936 non-COVID viral pneumonia, and 803 normal cases) and validated externally on several publicly accessible datasets. Compared to four experienced radiologists, the model achieved higher diagnostic accuracy (76.4% vs. 71.8%) and enhanced COVID-19 identification (F1-score: 74.1% vs. 61.3%), with an AUC of 93% for distinguishing between viral pneumonia and normal cases, and 89.8% for differentiating COVID-19 from other viral pneumonias. The severity-scoring module exhibited a high Pearson correlation of 93% and a low mean absolute error (MAE) of 2.35 compared to the radiologists' consensus. External validation on independent public datasets confirmed the model's generalizability. Subgroup analyses stratified by patient age, sex, and severity levels further demonstrated consistent performance, supporting the system's robustness across diverse clinical populations. These findings suggest that the proposed DL system could assist radiologists in the early diagnosis and severity assessment of COVID-19 from baseline CXRs, particularly in resource-limited settings.
format Article
id doaj-art-b3742be7f8204ad6982e8a013f42d059
institution DOAJ
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-b3742be7f8204ad6982e8a013f42d0592025-08-20T03:23:22ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032806110.1371/journal.pone.0328061Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.Nastaran EnshaeiArash MohammadiFarnoosh NaderkhaniNick DanemanRawan Abu MughliReut AnconinaFerco H BergerRobert Andrew KozakSamira MubarekaAna Maria Villanueva CamposKeshav NarangThayalasuthan VivekanandanAdrienne Kit ChanPhilip LamNisha AndanyAnastasia OikonomouChest X-ray (CXR) imaging plays a pivotal role in the diagnosis and prognosis of viral pneumonia. However, distinguishing COVID-19 CXRs from other viral infections remains challenging due to highly similar radiographic features. Most existing deep learning (DL) models focus on differentiating COVID-19 from community-acquired pneumonia (CAP) rather than other viral pneumonias and often overlook baseline CXRs, missing the critical window for early detection and intervention. Moreover, manual severity scoring of COVID-19 CXRs by radiologists is subjective and time-intensive, highlighting the need for automated systems. This study introduces a DL system for distinguishing COVID-19 from other viral pneumonias on baseline CXRs acquired within three days of PCR testing, and for automated severity scoring of COVID-19 CXRs. The system was developed using a dataset of 2,547 patients (808 COVID-19, 936 non-COVID viral pneumonia, and 803 normal cases) and validated externally on several publicly accessible datasets. Compared to four experienced radiologists, the model achieved higher diagnostic accuracy (76.4% vs. 71.8%) and enhanced COVID-19 identification (F1-score: 74.1% vs. 61.3%), with an AUC of 93% for distinguishing between viral pneumonia and normal cases, and 89.8% for differentiating COVID-19 from other viral pneumonias. The severity-scoring module exhibited a high Pearson correlation of 93% and a low mean absolute error (MAE) of 2.35 compared to the radiologists' consensus. External validation on independent public datasets confirmed the model's generalizability. Subgroup analyses stratified by patient age, sex, and severity levels further demonstrated consistent performance, supporting the system's robustness across diverse clinical populations. These findings suggest that the proposed DL system could assist radiologists in the early diagnosis and severity assessment of COVID-19 from baseline CXRs, particularly in resource-limited settings.https://doi.org/10.1371/journal.pone.0328061
spellingShingle Nastaran Enshaei
Arash Mohammadi
Farnoosh Naderkhani
Nick Daneman
Rawan Abu Mughli
Reut Anconina
Ferco H Berger
Robert Andrew Kozak
Samira Mubareka
Ana Maria Villanueva Campos
Keshav Narang
Thayalasuthan Vivekanandan
Adrienne Kit Chan
Philip Lam
Nisha Andany
Anastasia Oikonomou
Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.
PLoS ONE
title Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.
title_full Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.
title_fullStr Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.
title_full_unstemmed Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.
title_short Differentiation of COVID-19 from other types of viral pneumonia and severity scoring on baseline chest radiographs: Comparison of deep learning with multi-reader evaluation.
title_sort differentiation of covid 19 from other types of viral pneumonia and severity scoring on baseline chest radiographs comparison of deep learning with multi reader evaluation
url https://doi.org/10.1371/journal.pone.0328061
work_keys_str_mv AT nastaranenshaei differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT arashmohammadi differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT farnooshnaderkhani differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT nickdaneman differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT rawanabumughli differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT reutanconina differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT fercohberger differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT robertandrewkozak differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT samiramubareka differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT anamariavillanuevacampos differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT keshavnarang differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT thayalasuthanvivekanandan differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT adriennekitchan differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT philiplam differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT nishaandany differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation
AT anastasiaoikonomou differentiationofcovid19fromothertypesofviralpneumoniaandseverityscoringonbaselinechestradiographscomparisonofdeeplearningwithmultireaderevaluation