Deep Learning to Estimate Biological Age From Chest Radiographs

V.K. Raghu; J. Weiss; U. Hoffmann; H.J.W.L. Aerts; M.T. Lu

doi:10.1016/j.jcmg.2021.01.008

Deep Learning to Estimate Biological Age From Chest Radiographs

V.K. Raghu^*, J. Weiss, U. Hoffmann, H.J.W.L. Aerts, M.T. Lu

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

246 Downloads (Pure)

Abstract

OBJECTIVES The goal of this study was to assess whether a deep learning estimate of age from a chest radiograph image (CXR-Age) can predict longevity beyond chronological age. BACKGROUND Chronological age is an imperfect measure of longevity. Biological age, a measure of overall health, may improve personalized care. This paper proposes a new way to estimate biological age using a convolutional neural network that takes as input a CXR image and outputs a chest x-ray age (in years) as a measure of long-term mortality risk. METHODS CXR-Age was developed using CXR from 116,035 individuals and validated in 2 held-out testing sets: 1) 75% of the CXR arm of PLCO (Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial) (N = 40,967); and 2) the CXR arm of NLST (National Lung Screening Trial) (N = 5,414). CXR-Age was compared to chronological age and a multivariable regression model of chronological age, risk factors, and radiograph findings to predict all-cause and cardiovascular mortality with a maximum 23 years and 13 years of follow-up, respectively. The primary outcome was observed mortality; results are provided for the testing datasets only. RESULTS In the PLCO testing dataset, a 5-year increase in CXR-Age carried a higher risk of all-cause mortality than a 5-year increase in chronological age (CXR-Age hazard ratio [HR]: 2.26 [95% confidence interval (CI): 2.24 to 2.29] vs. chronological age HR: 1.77 [95% CI: 1.75 to 1.78]; p < 0.001). A similar pattern was found for cardiovascular mortality (CXR-Age cause-specific HR: 2.45 per 5 years [95% CI: 2.34 to 2.56] vs. chronological age HR: 1.82 per 5 years [95% CI: 1.74 to 1.90]). Similar results were seen for both outcomes in the NLST external testing dataset. Adding CXR-Age to the multivariable model resulted in significant improvements for predicting both outcomes in both testing datasets (p < 0.001 for all comparisons). CONCLUSIONS Based on a CXR image, CXR-Age predicted long-term all-cause and cardiovascular mortality. (J Am Coll Cardiol Img 2021;14:2226-2236 ) (c) 2021 by the American College of Cardiology Foundation.

Original language	English
Pages (from-to)	2226-2236
Number of pages	11
Journal	JACC-Cardiovascular Imaging
Volume	14
Issue number	11
DOIs	https://doi.org/10.1016/j.jcmg.2021.01.008
Publication status	Published - 1 Nov 2021

Keywords

biological age
cardiovascular risk prediction
chest radiographs
deep learning
LUNG-CANCER MORTALITY
TASK-FORCE
RISK
CLASSIFICATION
PROSTATE

Access to Document

10.1016/j.jcmg.2021.01.008Licence: Free access - publisher

Full TextFinal published version, 1.72 MBLicence: Taverne

Cite this

@article{e603259220c241298d6f2a613117bff8,

title = "Deep Learning to Estimate Biological Age From Chest Radiographs",

abstract = "OBJECTIVES The goal of this study was to assess whether a deep learning estimate of age from a chest radiograph image (CXR-Age) can predict longevity beyond chronological age. BACKGROUND Chronological age is an imperfect measure of longevity. Biological age, a measure of overall health, may improve personalized care. This paper proposes a new way to estimate biological age using a convolutional neural network that takes as input a CXR image and outputs a chest x-ray age (in years) as a measure of long-term mortality risk. METHODS CXR-Age was developed using CXR from 116,035 individuals and validated in 2 held-out testing sets: 1) 75% of the CXR arm of PLCO (Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial) (N = 40,967); and 2) the CXR arm of NLST (National Lung Screening Trial) (N = 5,414). CXR-Age was compared to chronological age and a multivariable regression model of chronological age, risk factors, and radiograph findings to predict all-cause and cardiovascular mortality with a maximum 23 years and 13 years of follow-up, respectively. The primary outcome was observed mortality; results are provided for the testing datasets only. RESULTS In the PLCO testing dataset, a 5-year increase in CXR-Age carried a higher risk of all-cause mortality than a 5-year increase in chronological age (CXR-Age hazard ratio [HR]: 2.26 [95% confidence interval (CI): 2.24 to 2.29] vs. chronological age HR: 1.77 [95% CI: 1.75 to 1.78]; p < 0.001). A similar pattern was found for cardiovascular mortality (CXR-Age cause-specific HR: 2.45 per 5 years [95% CI: 2.34 to 2.56] vs. chronological age HR: 1.82 per 5 years [95% CI: 1.74 to 1.90]). Similar results were seen for both outcomes in the NLST external testing dataset. Adding CXR-Age to the multivariable model resulted in significant improvements for predicting both outcomes in both testing datasets (p < 0.001 for all comparisons). CONCLUSIONS Based on a CXR image, CXR-Age predicted long-term all-cause and cardiovascular mortality. (J Am Coll Cardiol Img 2021;14:2226-2236 ) (c) 2021 by the American College of Cardiology Foundation.",

keywords = "biological age, cardiovascular risk prediction, chest radiographs, deep learning, LUNG-CANCER MORTALITY, TASK-FORCE, RISK, CLASSIFICATION, PROSTATE",

author = "V.K. Raghu and J. Weiss and U. Hoffmann and H.J.W.L. Aerts and M.T. Lu",

note = "Funding Information: This work was supported by the National Academy of Medicine Healthy Longevity Grand Challenge (2000011734). A graphics processing unit used for this research was donated to Dr Lu as an unrestricted gift through the Nvidia Corporation Academic Program. Original data collection for the ACRIN 6654 trial (NLST) was supported by National Cancer Institute Cancer Imaging Program grants. Dr Lu is supported by American Heart Association grants 18UNPG34030172 and 810966; has common stock in Nvidia and Advanced Micro Devices; reports research funding as a co-investigator to Massachusetts General Hospital from Kowa Company Limited and Medimmune/AstraZeneca; and received personal fees from PQBypass unrelated to this work. Dr Hoffmann is supported by an NIH grant (5K24HL113128); has received research support on behalf of his institution from Duke University (Abbott), HeartFlow, Kowa Company Limited, and MedImmune/AstraZeneca; and has received consulting fees from Duke University (NIH) and Recor Medical unrelated to this research. Dr Raghu is supported by NIH grant T32HL076136; and has common stock in Nvidia, Alphabet, and Apple. Dr Aerts has received personal fees from Sphera, Genospace, and Onc. AI outside the submitted work. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. Publisher Copyright: {\textcopyright} 2021 American College of Cardiology Foundation",

year = "2021",

month = nov,

day = "1",

doi = "10.1016/j.jcmg.2021.01.008",

language = "English",

volume = "14",

pages = "2226--2236",

journal = "JACC-Cardiovascular Imaging",

issn = "1936-878X",

publisher = "Elsevier Science",

number = "11",

}

TY - JOUR

T1 - Deep Learning to Estimate Biological Age From Chest Radiographs

AU - Raghu, V.K.

AU - Weiss, J.

AU - Hoffmann, U.

AU - Aerts, H.J.W.L.

AU - Lu, M.T.

N1 - Funding Information: This work was supported by the National Academy of Medicine Healthy Longevity Grand Challenge (2000011734). A graphics processing unit used for this research was donated to Dr Lu as an unrestricted gift through the Nvidia Corporation Academic Program. Original data collection for the ACRIN 6654 trial (NLST) was supported by National Cancer Institute Cancer Imaging Program grants. Dr Lu is supported by American Heart Association grants 18UNPG34030172 and 810966; has common stock in Nvidia and Advanced Micro Devices; reports research funding as a co-investigator to Massachusetts General Hospital from Kowa Company Limited and Medimmune/AstraZeneca; and received personal fees from PQBypass unrelated to this work. Dr Hoffmann is supported by an NIH grant (5K24HL113128); has received research support on behalf of his institution from Duke University (Abbott), HeartFlow, Kowa Company Limited, and MedImmune/AstraZeneca; and has received consulting fees from Duke University (NIH) and Recor Medical unrelated to this research. Dr Raghu is supported by NIH grant T32HL076136; and has common stock in Nvidia, Alphabet, and Apple. Dr Aerts has received personal fees from Sphera, Genospace, and Onc. AI outside the submitted work. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. Publisher Copyright: © 2021 American College of Cardiology Foundation

PY - 2021/11/1

Y1 - 2021/11/1

N2 - OBJECTIVES The goal of this study was to assess whether a deep learning estimate of age from a chest radiograph image (CXR-Age) can predict longevity beyond chronological age. BACKGROUND Chronological age is an imperfect measure of longevity. Biological age, a measure of overall health, may improve personalized care. This paper proposes a new way to estimate biological age using a convolutional neural network that takes as input a CXR image and outputs a chest x-ray age (in years) as a measure of long-term mortality risk. METHODS CXR-Age was developed using CXR from 116,035 individuals and validated in 2 held-out testing sets: 1) 75% of the CXR arm of PLCO (Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial) (N = 40,967); and 2) the CXR arm of NLST (National Lung Screening Trial) (N = 5,414). CXR-Age was compared to chronological age and a multivariable regression model of chronological age, risk factors, and radiograph findings to predict all-cause and cardiovascular mortality with a maximum 23 years and 13 years of follow-up, respectively. The primary outcome was observed mortality; results are provided for the testing datasets only. RESULTS In the PLCO testing dataset, a 5-year increase in CXR-Age carried a higher risk of all-cause mortality than a 5-year increase in chronological age (CXR-Age hazard ratio [HR]: 2.26 [95% confidence interval (CI): 2.24 to 2.29] vs. chronological age HR: 1.77 [95% CI: 1.75 to 1.78]; p < 0.001). A similar pattern was found for cardiovascular mortality (CXR-Age cause-specific HR: 2.45 per 5 years [95% CI: 2.34 to 2.56] vs. chronological age HR: 1.82 per 5 years [95% CI: 1.74 to 1.90]). Similar results were seen for both outcomes in the NLST external testing dataset. Adding CXR-Age to the multivariable model resulted in significant improvements for predicting both outcomes in both testing datasets (p < 0.001 for all comparisons). CONCLUSIONS Based on a CXR image, CXR-Age predicted long-term all-cause and cardiovascular mortality. (J Am Coll Cardiol Img 2021;14:2226-2236 ) (c) 2021 by the American College of Cardiology Foundation.

AB - OBJECTIVES The goal of this study was to assess whether a deep learning estimate of age from a chest radiograph image (CXR-Age) can predict longevity beyond chronological age. BACKGROUND Chronological age is an imperfect measure of longevity. Biological age, a measure of overall health, may improve personalized care. This paper proposes a new way to estimate biological age using a convolutional neural network that takes as input a CXR image and outputs a chest x-ray age (in years) as a measure of long-term mortality risk. METHODS CXR-Age was developed using CXR from 116,035 individuals and validated in 2 held-out testing sets: 1) 75% of the CXR arm of PLCO (Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial) (N = 40,967); and 2) the CXR arm of NLST (National Lung Screening Trial) (N = 5,414). CXR-Age was compared to chronological age and a multivariable regression model of chronological age, risk factors, and radiograph findings to predict all-cause and cardiovascular mortality with a maximum 23 years and 13 years of follow-up, respectively. The primary outcome was observed mortality; results are provided for the testing datasets only. RESULTS In the PLCO testing dataset, a 5-year increase in CXR-Age carried a higher risk of all-cause mortality than a 5-year increase in chronological age (CXR-Age hazard ratio [HR]: 2.26 [95% confidence interval (CI): 2.24 to 2.29] vs. chronological age HR: 1.77 [95% CI: 1.75 to 1.78]; p < 0.001). A similar pattern was found for cardiovascular mortality (CXR-Age cause-specific HR: 2.45 per 5 years [95% CI: 2.34 to 2.56] vs. chronological age HR: 1.82 per 5 years [95% CI: 1.74 to 1.90]). Similar results were seen for both outcomes in the NLST external testing dataset. Adding CXR-Age to the multivariable model resulted in significant improvements for predicting both outcomes in both testing datasets (p < 0.001 for all comparisons). CONCLUSIONS Based on a CXR image, CXR-Age predicted long-term all-cause and cardiovascular mortality. (J Am Coll Cardiol Img 2021;14:2226-2236 ) (c) 2021 by the American College of Cardiology Foundation.

KW - biological age

KW - cardiovascular risk prediction

KW - chest radiographs

KW - deep learning

KW - LUNG-CANCER MORTALITY

KW - TASK-FORCE

KW - RISK

KW - CLASSIFICATION

KW - PROSTATE

U2 - 10.1016/j.jcmg.2021.01.008

DO - 10.1016/j.jcmg.2021.01.008

M3 - Article

C2 - 33744131

SN - 1936-878X

VL - 14

SP - 2226

EP - 2236

JO - JACC-Cardiovascular Imaging

JF - JACC-Cardiovascular Imaging

IS - 11

ER -