Machine learning to predict risk from chest radiographs and clinical factors
Principal Investigator
Name
Michael Lu
Degrees
M.D., M.P.H.
Institution
The General Hospital Corporation d/b/a Massachusetts General Hospital
Position Title
Co-Director, Cardiovascular Imaging Research Center
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-383
Initial CDAS Request Approval
Dec 29, 2017
Title
Machine learning to predict risk from chest radiographs and clinical factors
Summary
Heart disease and cancer are the two most common causes of death in the developed world. NLST participants underwent screening chest radiography; analysis of these chest radiographs may be useful to predict incident morbidity and mortality. The goal of this proposal is to use machine learning to predict the risk of cancer, heart disease, and death from chest radiographs and other clinical information available in the NLST. Whether this approach is additive to existing risk prediction models will be assessed via questionnaire data about patient risk factors and medical history.
Aims
1) To predict cancer, heart disease, and death from chest radiographs using machine learning.
2) To compare the performance of this approach to existing risk prediction tools.
Collaborators
Parastou Eslami (Harvard)
Borek Foldyna (Harvard)
Udo Hoffmann (Harvard)
Alexander Ivanov (Harvard)
Chintan Parmar (Harvard)
Roman Zeleznik (Harvard)
Related Publications
-
Association of a Deep Learning Estimation of Chest Imaging Age With Survival in Patients With Non-Small Cell Lung Cancers Undergoing Radiation.
Perni S, Raghu V, Guthier CV, Weiss J, Huynh E, Hosny A, Fite E, Christiani D, Aerts H, Lu M, Mak RH
Int J Radiat Oncol Biol Phys. 2021 Nov 1; Volume 111 (Issue 3S): Pages S114 PUBMED -
Deep Learning to Estimate Biological Age From Chest Radiographs.
Raghu VK, Weiss J, Hoffmann U, Aerts HJWL, Lu MT
JACC Cardiovasc Imaging. 2021 Mar 10 PUBMED -
Deep Learning Using Chest Radiographs to Identify High-Risk Smokers for Lung Cancer Screening Computed Tomography: Development and Validation of a Prediction Model.
Lu MT, Raghu VK, Mayrhofer T, Aerts HJWL, Hoffmann U
Ann. Intern. Med. 2020 Sep 1 PUBMED -
Deep Learning to Assess Long-term Mortality From Chest Radiographs.
Lu MT, Ivanov A, Mayrhofer T, Hosny A, Aerts HJWL, Hoffmann U
JAMA Netw Open. 2019 Jul 3; Volume 2 (Issue 7): Pages e197416 PUBMED