View in EDS

Validation of a Deep Learning-Based Model to Predict Lung Cancer Risk Using Chest Radiographs and Electronic Medical Record Data.

Saved in:
Bibliographic Details
Title: Validation of a Deep Learning-Based Model to Predict Lung Cancer Risk Using Chest Radiographs and Electronic Medical Record Data.
Authors: Raghu VK; Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts.; Program for Artificial Intelligence in Medicine, Brigham and Women's Hospital & Harvard Medical School, Boston, Massachusetts., Walia AS; Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts., Zinzuwadia AN; Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts., Goiffon RJ; Division of Abdominal Imaging, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts., Shepard JO; Division of Thoracic Imaging and Intervention, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts., Aerts HJWL; Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts.; Program for Artificial Intelligence in Medicine, Brigham and Women's Hospital & Harvard Medical School, Boston, Massachusetts.; Department of Radiology and Nuclear Medicine, CARIM School for Cardiovascular Diseases and GROW School for Oncology and Reproduction, Maastricht University, the Netherlands., Lennes IT; Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts., Lu MT; Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts.; Program for Artificial Intelligence in Medicine, Brigham and Women's Hospital & Harvard Medical School, Boston, Massachusetts.
Source: JAMA network open [JAMA Netw Open] 2022 Dec 01; Vol. 5 (12), pp. e2248793. Date of Electronic Publication: 2022 Dec 01.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: American Medical Association Country of Publication: United States NLM ID: 101729235 Publication Model: Electronic Cited Medium: Internet ISSN: 2574-3805 (Electronic) Linking ISSN: 25743805 NLM ISO Abbreviation: JAMA Netw Open Subsets: MEDLINE
Imprint Name(s): Original Publication: Chicago, IL : American Medical Association, [2018]-
MeSH Terms: Lung Neoplasms*/diagnostic imaging , Lung Neoplasms*/epidemiology , Deep Learning*, Humans ; Male ; Female ; Aged ; United States ; Middle Aged ; Early Detection of Cancer ; Electronic Health Records ; Medicare
Abstract: Importance: Lung cancer screening with chest computed tomography (CT) prevents lung cancer death; however, fewer than 5% of eligible Americans are screened. CXR-LC, an open-source deep learning tool that estimates lung cancer risk from existing chest radiograph images and commonly available electronic medical record (EMR) data, may enable automated identification of high-risk patients as a step toward improving lung cancer screening participation.
Objective: To validate CXR-LC using EMR data to identify individuals at high-risk for lung cancer to complement 2022 US Centers for Medicare & Medicaid Services (CMS) lung cancer screening eligibility guidelines.
Design, Setting, and Participants: This prognostic study compared CXR-LC estimates with CMS screening guidelines using patient data from a large US hospital system. Included participants were persons who currently or formerly smoked cigarettes with an outpatient posterior-anterior chest radiograph between January 1, 2013, and December 31, 2014, with no history of lung cancer or screening CT. Data analysis was performed between May 2021 and June 2022.
Exposures: CXR-LC lung cancer screening eligibility (previously defined as having a 3.297% or greater 12-year risk) based on inputs (chest radiograph image, age, sex, and whether currently smoking) extracted from the EMR.
Main Outcomes and Measures: 6-year incident lung cancer.
Results: A total of 14 737 persons were included in the study population (mean [SD] age, 62.6 [6.8] years; 7154 [48.5%] male; 204 [1.4%] Asian, 1051 [7.3%] Black, 432 [2.9%] Hispanic, 12 330 [85.2%] White) with a 2.4% rate of incident lung cancer over 6 years (361 patients with cancer). CMS eligibility could be determined in 6277 patients (42.6%) using smoking pack-year and quit-date from the EMR. Patients eligible by both CXR-LC and 2022 CMS criteria had a high rate of lung cancer (83 of 974 patients [8.5%]), higher than those eligible by 2022 CMS criteria alone (5 of 177 patients [2.8%]; P < .001). Patients eligible by CXR-LC but not 2022 CMS criteria also had a high 6-year incidence of lung cancer (121 of 3703 [3.3%]). In the 8460 cases (57.4%) where CMS eligibility was unknown, CXR-LC eligible patients had a 5-fold higher rate of lung cancer than ineligible (127 of 5177 [2.5%] vs 18 of 2283 [0.5%]; P < .001). Similar results were found in subgroups, including female patients and Black persons.
Conclusions and Relevance: Using routine chest radiographs and other data automatically extracted from the EMR, CXR-LC identified high-risk individuals who may benefit from lung cancer screening CT.
References: Health Aff (Millwood). 2011 Dec;30(12):2310-7. (PMID: 22147858)
Ann Am Thorac Soc. 2017 Aug;14(8):1320-1325. (PMID: 28406708)
Arch Intern Med. 2010 Mar 22;170(6):560-5. (PMID: 20308643)
NPJ Digit Med. 2022 Apr 8;5(1):47. (PMID: 35396454)
Control Clin Trials. 2000 Dec;21(6 Suppl):251S-272S. (PMID: 11189683)
JAMA. 2021 Mar 09;325(10):962-970. (PMID: 33687470)
N Engl J Med. 2020 Feb 6;382(6):503-513. (PMID: 31995683)
Radiology. 2022 Oct;305(1):209-218. (PMID: 35699582)
Health Serv Res. 2020 Apr;55(2):170-177. (PMID: 31930738)
J Natl Compr Canc Netw. 2018 Apr;16(4):412-441. (PMID: 29632061)
J Med Internet Res. 2021 Aug 3;23(8):e26256. (PMID: 34342588)
BMJ. 2016 Jan 25;352:i6. (PMID: 26810254)
JAMA Oncol. 2022 Mar 01;8(3):374-382. (PMID: 35024781)
J Natl Cancer Inst. 2021 Aug 2;113(8):1044-1052. (PMID: 33176362)
J Natl Cancer Inst. 2015 Jan 31;107(3):. (PMID: 25638255)
N Engl J Med. 2011 Aug 4;365(5):395-409. (PMID: 21714641)
BMC Health Serv Res. 2019 Oct 22;19(1):737. (PMID: 31640678)
Chest. 2013 May;143(5 Suppl):e78S-e92S. (PMID: 23649455)
J Med Imaging (Bellingham). 2020 Jan;7(1):016502. (PMID: 32064302)
JAMA Oncol. 2019 Sep 01;5(9):1318-1324. (PMID: 31246249)
JAMA Intern Med. 2020 Mar 1;180(3):463-466. (PMID: 31841583)
Transl Lung Cancer Res. 2018 Jun;7(3):243-253. (PMID: 30050763)
CA Cancer J Clin. 2021 May;71(3):209-249. (PMID: 33538338)
Chest. 2022 Jan;161(1):248-256. (PMID: 34252436)
JAMA. 2011 Nov 2;306(17):1865-73. (PMID: 22031728)
J Am Med Inform Assoc. 2022 Apr 13;29(5):779-788. (PMID: 35167675)
Diagn Progn Res. 2019 Oct 04;3:18. (PMID: 31592444)
Radiology. 2019 Feb;290(2):278-287. (PMID: 30620258)
JAMA Oncol. 2017 Sep 1;3(9):1278-1281. (PMID: 28152136)
Ann Intern Med. 2012 Aug 21;157(4):294-5. (PMID: 22910942)
Ann Intern Med. 2020 Nov 3;173(9):704-713. (PMID: 32866413)
JAMA Intern Med. 2017 Mar 1;177(3):399-406. (PMID: 28135352)
Psychometrika. 1947 Jun;12(2):153-7. (PMID: 20254758)
Br J Gen Pract. 2010 Mar;60(572):e121-7. (PMID: 20202355)
Lancet Respir Med. 2021 Jul;9(7):689-691. (PMID: 33965004)
Ann Am Thorac Soc. 2020 Apr;17(4):399-405. (PMID: 32017612)
Control Clin Trials. 2000 Dec;21(6 Suppl):273S-309S. (PMID: 11189684)
Am J Respir Crit Care Med. 2021 Aug 15;204(4):445-453. (PMID: 33823116)
N Engl J Med. 2006 Jan 26;354(4):333-42. (PMID: 16436765)
CA Cancer J Clin. 2019 May;69(3):184-210. (PMID: 30875085)
Entry Date(s): Date Created: 20221228 Date Completed: 20221230 Latest Revision: 20230202
Update Code: 20250114
PubMed Central ID: PMC9857639
DOI: 10.1001/jamanetworkopen.2022.48793
PMID: 36576736
Database: MEDLINE
Be the first to leave a comment!
You must be logged in first