深度学习从胸部 X 光片中估算生物年龄。
Deep Learning to Estimate Biological Age From Chest Radiographs.
机构信息
Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA; Program for Artificial Intelligence in Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts, USA.
Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA; Program for Artificial Intelligence in Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts, USA; Department for Diagnostic and Interventional Radiology, University Hospital Freiburg, Germany.
出版信息
JACC Cardiovasc Imaging. 2021 Nov;14(11):2226-2236. doi: 10.1016/j.jcmg.2021.01.008. Epub 2021 Mar 17.
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.
目的
本研究旨在评估从胸部 X 射线图像（CXR）中深度学习估计的年龄（CXR-Age）是否可以预测超越实际年龄的长寿。
背景
实际年龄是衡量长寿的不完美指标。生物年龄是衡量整体健康状况的指标，可能会改善个性化护理。本文提出了一种使用卷积神经网络估计生物年龄的新方法，该网络将胸部 X 射线图像作为输入，并输出胸部 X 射线年龄（以年为单位），作为衡量长期死亡率风险的指标。
方法
使用来自 116035 个人的 CXR 开发了 CXR-Age，并在 2 个独立的测试集（PLCO 的 CXR 臂的 75%（N=40967）和 NLST 的 CXR 臂（N=5414））中进行了验证。将 CXR-Age 与实际年龄以及实际年龄、危险因素和射线照相发现的多变量回归模型进行比较，以分别预测最长 23 年和 13 年的全因和心血管死亡率。主要结果是观察到的死亡率；仅提供测试数据集的结果。
结果
在 PLCO 测试数据集，CXR-Age 每增加 5 岁，全因死亡率的风险高于实际年龄每增加 5 岁（CXR-Age 风险比[HR]：2.26[95%置信区间[CI]：2.24 至 2.29]比实际年龄 HR：1.77[95%CI：1.75 至 1.78]；p<0.001）。心血管死亡率也出现了类似的模式（CXR-Age 特定原因 HR：每 5 年增加 2.45[95%CI：2.34 至 2.56]比实际年龄 HR：每 5 年增加 1.82[95%CI：1.74 至 1.90]）。在 NLST 外部测试数据集的这两种结果中也观察到了类似的结果。在多变量模型中加入 CXR-Age 可显著改善两种结果在两个测试数据集的预测（所有比较的 p<0.001）。
结论
基于 CXR 图像，CXR-Age 预测了长期全因和心血管死亡率。
Zotero 插件