Deep Learning Using Chest X-Rays to Identify High Risk Patients for Lung Cancer Screening CT

Deep Learning Using Routine Chest X-Rays and Electronic Medical Record Data to Identify High Risk Patients for Lung Cancer Screening CT

The goal of this clinical trial is to evaluate whether an AI tool that alerts providers to patients at high 6-year risk of lung cancer based on their chest x-ray images will improve lung cancer screening CT participation. The main question it aims to answer is: Does the AI tool improve lung cancer screening CT participation at 6 months after the baseline outpatient visit?

The intervention is an alert to the provider to discuss lung cancer screening CT eligibility, for patients considered at high risk of lung cancer based on CXR-LC AI tool. Intervention and non-intervention arms will be compared to determine if lung cancer screening CT participation increases.

Individuals who are considered high-risk by the tool, but who do not meet the Medicare/USPSTF pack-year or quit-date lung screening eligibility criteria may be offered research lung screening CT.

Study Overview

• Status: Recruiting
• Conditions: Lung Cancer; Deep Learning; Early Cancer Detection; Health Screening
• Intervention / Treatment: Other: CXR-LC

• Study Type: Interventional
• Enrollment (Estimated): 1500
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Michael T Lu, MD, MPH; Phone Number: 617-726-1255; Email: mlu@mgh.harvard.edu

Study Locations

• United States
  • Massachusetts
    • Boston, Massachusetts, United States, 02114
      • Recruiting
      • Massachusetts General Hospital
      • Contact: Michael T Lu, MD, MPH; Phone Number: 617-724-9729; Email: mlu@mgh.harvard.edu

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Major Inclusion Criteria:

• Scheduled outpatient appointment with participating provider.
• 50- to 77-year-old who currently or formerly smoked, to include persons potentially eligible for lung screening based on Medicare guidelines.
• Recent (within 2 years) PA chest radiograph.

Exclusion Criteria:

• History or signs/symptoms of lung cancer. Recent (within 2 years) chest CT. Clinical indication for chest CT beyond lung cancer screening.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Double

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention	Other: CXR-LC; Alert to provider to discuss lung cancer screening CT eligibility, for patients considered at high risk of lung cancer based on CXR-LC AI tool.
No Intervention: Non-Intervention

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion completing Lung Cancer screening CT in 6 months after visit	To assess impact on lung cancer screening CT participation (defined as completing lung cancer screening CT) in the 6 months after the baseline visit.	6 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Suspicious lung nodules	Suspicious lung nodules (Lung-RADS 4a or greater, including lung nodules ≥8 mm in diameter) identified on CT or diagnosed lung cancer.	6 months

Collaborators and Investigators

• Sponsor: Massachusetts General Hospital
• Collaborators: Harvard Risk Management Foundation

Publications and helpful links

General Publications

• Lu MT, Raghu VK, Mayrhofer T, Aerts HJWL, Hoffmann U. Deep Learning Using Chest Radiographs to Identify High-Risk Smokers for Lung Cancer Screening Computed Tomography: Development and Validation of a Prediction Model. Ann Intern Med. 2020 Nov 3;173(9):704-713. doi: 10.7326/M20-1868. Epub 2020 Sep 1.
• Lee JH, Lee D, Lu MT, Raghu VK, Park CM, Goo JM, Choi SH, Kim H. Deep Learning to Optimize Candidate Selection for Lung Cancer CT Screening: Advancing the 2021 USPSTF Recommendations. Radiology. 2022 Oct;305(1):209-218. doi: 10.1148/radiol.212877. Epub 2022 Jun 14.
• Raghu VK, Walia AS, Zinzuwadia AN, Goiffon RJ, Shepard JO, Aerts HJWL, Lennes IT, Lu MT. Validation of a Deep Learning-Based Model to Predict Lung Cancer Risk Using Chest Radiographs and Electronic Medical Record Data. JAMA Netw Open. 2022 Dec 1;5(12):e2248793. doi: 10.1001/jamanetworkopen.2022.48793.

Study record dates

Study Major Dates

• Study Start (Actual): May 20, 2025
• Primary Completion (Estimated): July 1, 2027
• Study Completion (Estimated): July 1, 2027

Study Registration Dates

• First Submitted: March 28, 2025
• First Submitted That Met QC Criteria: March 28, 2025
• First Posted (Actual): April 4, 2025

Study Record Updates

• Last Update Posted (Actual): May 11, 2026
• Last Update Submitted That Met QC Criteria: May 6, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Keywords: AI; Deep learning; Chest x-ray
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Respiratory Tract Diseases; Lung Diseases; Respiratory Tract Neoplasms; Thoracic Neoplasms; Lung Neoplasms
• Other Study ID Numbers: 2023P002872; 2025P002902 (Other Identifier: Mass General Hospital)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No