Deep learning to estimate lung disease mortality from chest radiographs

Jakob Weiss; Vineet K Raghu; Dennis Bontempi; David C Christiani; Raymond H Mak; Michael T Lu; Hugo J W L Aerts

doi:10.1038/s41467-023-37758-5

Deep learning to estimate lung disease mortality from chest radiographs

Nat Commun. 2023 May 16;14(1):2797. doi: 10.1038/s41467-023-37758-5.

Authors

Jakob Weiss^#^{1

2

3

4}, Vineet K Raghu^#^{1

4}, Dennis Bontempi^{1

5}, David C Christiani^{6

7}, Raymond H Mak^{1

2}, Michael T Lu^{1

4}, Hugo J W L Aerts^{8

9

10

11}

Affiliations

¹ Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Harvard Institutes of Medicine, 77 Avenue Louis Pasteur, Boston, MA, 02115, USA.
² Department of Radiation Oncology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, 75 Francis Street and 450 Brookline Avenue, Boston, MA, 02115, USA.
³ Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Hugstetter Str. 55, 79106, Freiburg, Germany.
⁴ Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, 165 Cambridge Street, 02114, Boston, USA.
⁵ Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Universiteitssingel 40, 6229 ER, Maastricht, The Netherlands.
⁶ Department of Environmental Health, Harvard T.H. Chan School of Public Health, 655 Huntington Ave., Boston, MA, 02115, USA.
⁷ Pulmonary and Critical Care Division, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Boston, MA, 02114, USA.
⁸ Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Harvard Institutes of Medicine, 77 Avenue Louis Pasteur, Boston, MA, 02115, USA. Hugo_Aerts@DFCI.harvard.edu.
⁹ Department of Radiation Oncology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, 75 Francis Street and 450 Brookline Avenue, Boston, MA, 02115, USA. Hugo_Aerts@DFCI.harvard.edu.
¹⁰ Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, 165 Cambridge Street, 02114, Boston, USA. Hugo_Aerts@DFCI.harvard.edu.
¹¹ Pulmonary and Critical Care Division, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Boston, MA, 02114, USA. Hugo_Aerts@DFCI.harvard.edu.

^# Contributed equally.

Abstract

Prevention and management of chronic lung diseases (asthma, lung cancer, etc.) are of great importance. While tests are available for reliable diagnosis, accurate identification of those who will develop severe morbidity/mortality is currently limited. Here, we developed a deep learning model, CXR Lung-Risk, to predict the risk of lung disease mortality from a chest x-ray. The model was trained using 147,497 x-ray images of 40,643 individuals and tested in three independent cohorts comprising 15,976 individuals. We found that CXR Lung-Risk showed a graded association with lung disease mortality after adjustment for risk factors, including age, smoking, and radiologic findings (Hazard ratios up to 11.86 [8.64-16.27]; p < 0.001). Adding CXR Lung-Risk to a multivariable model improved estimates of lung disease mortality in all cohorts. Our results demonstrate that deep learning can identify individuals at risk of lung disease mortality on easily obtainable x-rays, which may improve personalized prevention and treatment strategies.

Publication types

Research Support, Non-U.S. Gov't
Research Support, N.I.H., Extramural

MeSH terms

Deep Learning*
Humans
Lung / diagnostic imaging
Lung Diseases* / diagnostic imaging
Radiography, Thoracic / methods
Thorax

Abstract

Publication types

MeSH terms

Grants and funding