Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network

Abstract Deep learning convolutional neural network (CNN) can predict mortality from chest radiographs, yet, it is unknown whether radiologists can perform the same task. Here, we investigate whether radiologists can visually assess image gestalt (defined as deviation from an unremarkable chest radi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jakob Weiss, Jana Taron, Zexi Jin, Thomas Mayrhofer, Hugo J. W. L. Aerts, Michael T. Lu, Udo Hoffmann
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/534f579e4e264f86b5feb58c8815d5f9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:534f579e4e264f86b5feb58c8815d5f9
record_format	dspace
spelling	oai:doaj.org-article:534f579e4e264f86b5feb58c8815d5f92021-12-02T18:51:28ZRadiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network10.1038/s41598-021-99107-02045-2322https://doaj.org/article/534f579e4e264f86b5feb58c8815d5f92021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-99107-0https://doaj.org/toc/2045-2322Abstract Deep learning convolutional neural network (CNN) can predict mortality from chest radiographs, yet, it is unknown whether radiologists can perform the same task. Here, we investigate whether radiologists can visually assess image gestalt (defined as deviation from an unremarkable chest radiograph associated with the likelihood of 6-year mortality) of a chest radiograph to predict 6-year mortality. The assessment was validated in an independent testing dataset and compared to the performance of a CNN developed for mortality prediction. Results are reported for the testing dataset only (n = 100; age 62.5 ± 5.2; male 55%, event rate 50%). The probability of 6-year mortality based on image gestalt had high accuracy (AUC: 0.68 (95% CI 0.58–0.78), similar to that of the CNN (AUC: 0.67 (95% CI 0.57–0.77); p = 0.90). Patients with high/very high image gestalt ratings were significantly more likely to die when compared to those rated as very low (p ≤ 0.04). Assignment to risk categories was not explained by patient characteristics or traditional risk factors and imaging findings (p ≥ 0.2). In conclusion, assessing image gestalt on chest radiographs by radiologists renders high prognostic accuracy for the probability of mortality, similar to that of a specifically trained CNN. Further studies are warranted to confirm this concept and to determine potential clinical benefits.Jakob WeissJana TaronZexi JinThomas MayrhoferHugo J. W. L. AertsMichael T. LuUdo HoffmannNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jakob Weiss Jana Taron Zexi Jin Thomas Mayrhofer Hugo J. W. L. Aerts Michael T. Lu Udo Hoffmann Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network
description	Abstract Deep learning convolutional neural network (CNN) can predict mortality from chest radiographs, yet, it is unknown whether radiologists can perform the same task. Here, we investigate whether radiologists can visually assess image gestalt (defined as deviation from an unremarkable chest radiograph associated with the likelihood of 6-year mortality) of a chest radiograph to predict 6-year mortality. The assessment was validated in an independent testing dataset and compared to the performance of a CNN developed for mortality prediction. Results are reported for the testing dataset only (n = 100; age 62.5 ± 5.2; male 55%, event rate 50%). The probability of 6-year mortality based on image gestalt had high accuracy (AUC: 0.68 (95% CI 0.58–0.78), similar to that of the CNN (AUC: 0.67 (95% CI 0.57–0.77); p = 0.90). Patients with high/very high image gestalt ratings were significantly more likely to die when compared to those rated as very low (p ≤ 0.04). Assignment to risk categories was not explained by patient characteristics or traditional risk factors and imaging findings (p ≥ 0.2). In conclusion, assessing image gestalt on chest radiographs by radiologists renders high prognostic accuracy for the probability of mortality, similar to that of a specifically trained CNN. Further studies are warranted to confirm this concept and to determine potential clinical benefits.
format	article
author	Jakob Weiss Jana Taron Zexi Jin Thomas Mayrhofer Hugo J. W. L. Aerts Michael T. Lu Udo Hoffmann
author_facet	Jakob Weiss Jana Taron Zexi Jin Thomas Mayrhofer Hugo J. W. L. Aerts Michael T. Lu Udo Hoffmann
author_sort	Jakob Weiss
title	Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network
title_short	Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network
title_full	Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network
title_fullStr	Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network
title_full_unstemmed	Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network
title_sort	radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/534f579e4e264f86b5feb58c8815d5f9
work_keys_str_mv	AT jakobweiss radiologistscanvisuallypredictmortalityriskbasedonthegestaltofchestradiographscomparabletoadeeplearningnetwork AT janataron radiologistscanvisuallypredictmortalityriskbasedonthegestaltofchestradiographscomparabletoadeeplearningnetwork AT zexijin radiologistscanvisuallypredictmortalityriskbasedonthegestaltofchestradiographscomparabletoadeeplearningnetwork AT thomasmayrhofer radiologistscanvisuallypredictmortalityriskbasedonthegestaltofchestradiographscomparabletoadeeplearningnetwork AT hugojwlaerts radiologistscanvisuallypredictmortalityriskbasedonthegestaltofchestradiographscomparabletoadeeplearningnetwork AT michaeltlu radiologistscanvisuallypredictmortalityriskbasedonthegestaltofchestradiographscomparabletoadeeplearningnetwork AT udohoffmann radiologistscanvisuallypredictmortalityriskbasedonthegestaltofchestradiographscomparabletoadeeplearningnetwork
_version_	1718377384791506944

Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network

Ejemplares similares