Using AI on Chest X-Rays and Medical Records to Find High-Risk Patients for Lung Cancer Screening CT
Led by Massachusetts General Hospital · Updated on 2026-05-11
1500
Participants Needed
1
Research Sites
N/A
Total Duration
AI-Summary
What this Trial Is About
Researchers are studying whether an artificial intelligence AI tool that alerts healthcare providers about patients at high risk for lung cancer based on chest X-ray images can increase participation in lung cancer screening using CT scans. The study focuses on patients aged 50 to 77 who currently or formerly smoked. It aims to see if the AI alert improves lung cancer screening CT participation within six months after a baseline outpatient visit.
Participants will be randomly assigned to one of two groups an intervention group where providers receive an alert to discuss lung cancer screening CT eligibility based on the AI tool CXR-LC, and a non-intervention group without this alert. The study compares these groups to determine if the alert increases lung cancer screening CT participation. Some patients identified as high risk by the AI but not meeting Medicare or USPSTF criteria may be offered lung screening CT as part of the research.
During the study, participants will have their lung cancer screening CT completion tracked within six months after their outpatient visit. Researchers will also monitor for suspicious lung nodules during this period. The study involves scheduled outpatient appointments and recent chest X-rays taken within two years. The total participation timeline includes these assessments and outcome measurements over six months following the baseline visit.
CONDITIONS
Brief Title
Deep Learning Using Chest X-Rays to Identify High Risk Patients for Lung Cancer Screening CT
Research Team
M
Michael T Lu, MD, MPH
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match. Sign up to get personalized trial recommendations delivered to your inbox.
This table compares participation in this trial with other options available for this condition. The information is drawn from published research and the trial’s study details and is provided for educational purposes only.
Factors
CXR‑LC alert
No alert
USPSTF LDCT screening
What it is
An AI tool that flags high‑risk patients based on chest X‑ray (CXR‑LC) and alerts the provider to discuss lung cancer screening CT.
Usual care without any AI‑based alert.
Annual low‑dose CT (LDCT) screening of high‑risk adults per USPSTF guidelines (ages 50–80 with smoking history).
Role in trial
Investigational arm where AI prompt may increase discussion and completion of CT screening.
Control arm with standard process and no alert delivered.
Represents typical guideline‑based screening offered to eligible patients in regular clinical practice.
Primary use
To identify patients at high lung cancer risk using CXR‑LC and prompt CT screening discussion.
To measure baseline CT screening rates without AI‑based prompts.
To screen asymptomatic high‑risk adults annually using LDCT to detect early lung cancer.
How it is performed
Provider receives an alert based on AI analysis of a recent chest X‑ray to consider CT screening.
No alert is triggered; provider proceeds as usual.
Annual low‑dose CT scan performed according to guideline criteria.
Evidence status
Evaluation ongoing; trial will measure completion of CT screening within 6 months of visit.
Baseline CT screening rates serve as comparator but evidence from trial not yet available.
Annual LDCT screening has demonstrated moderate net benefit in reducing lung cancer mortality in high‑risk adults.
Important risks
Risks depend on subsequent CT; includes radiation exposure and potential false positives inherent to LDCT screening.
Risks associated only with CT if performed per usual practice; same as standard screening risks.
LDCT screening can lead to false positives, overdiagnosis, and radiation exposure.
Important limitations
Effectiveness depends on provider following alert; impact on actual screening completion not yet known.
Does not actively prompt screening; reflects baseline behavior which may be low in uptake.
Not evaluated in this trial; implementation depends on guideline adherence and access to LDCT.
Disclaimer: This comparison is created with the help of artificial intelligence(AI) and may contain errors or missing information. It is not medical advice and does not mean one option is better or safer than another. Clinical trials are still being studied, and joining a trial is your choice. Please consult your healthcare professional before making any decisions.
Who Can Participate
Age: 50Years - 77Years
All Genders
Eligibility Criteria
You may qualify if you...
Scheduled outpatient appointment with participating provider
Age between 50 and 77 years
Current or former smoker potentially eligible for lung screening based on Medicare guidelines
Clinical indication for chest CT beyond lung cancer screening
Your Study Journey
Screening
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Surveillance
Duration - 6 months
Participants are monitored to identify high risk for lung cancer using chest X-rays and electronic medical record data.
1 visit during this period
How is the study designed?
Study Type
INTERVENTIONAL
Masking
DOUBLE
Allocation
RANDOMIZED
Model
PARALLEL
Primary Purpose
SCREENING
Number of Arms
2
Similar Trials
Using 3-D Virtual Lung Resection to Predict Lung Function After VATS Surgery for Non-Small Cell Lung Cancer
Developing Advanced 4D-MRI Imaging to Improve Radiation Therapy for Lung and Liver Cancer
Including Healthy Adult Volunteers for Imaging Research
Evaluation of 68Ga-SorB PETCT Imaging for Diagnosing Sortilin-Expressing Solid Tumors in Adults with Melanoma, Liver, Lung, Pancreatic, Breast, or Ovarian Cancer
A Clinical and Biological Database Study of Lung Cancer Patients Receiving Standard Treatments
Study on Causes and Impact of Vulnerability in Adult Men With Serious Diseases Including Cancer and Fractures
Feasibility Study of MRI-Guided Stereotactic Ablative Radiotherapy for Abdominal and Lung Tumors
Phase 12 Study of 3H-10000 Infusion for Adults with Unresectable or Metastatic Lung or Stomach Cancer
AI-Based PETCT Imaging for Detailed Lung Cancer Subtyping and Genetic Mutation Prediction
A Study Testing Mobile Health Technology to Improve Lung Cancer Screening Among Adults Aged 50 to 77
Phase I Study of Cardunizumab Combined with Pulsed Low-dose Rate Radiation for Recurrent Lung, Esophageal, and Cervical Cancers
Have more questions? Get in touch with our team for quick support
Published Research Related To This Trial
Deep Learning Using Chest Radiographs to Identify High-Risk Smokers for Lung Cancer Screening Computed Tomography: Development and Validation of a Prediction Model.