AI analysis of chest X-rays to identify people at high lung cancer risk for CT screening
Deep Learning Using Routine Chest X-Rays and Electronic Medical Record Data to Identify High Risk Patients for Lung Cancer Screening CT
This project tests whether an AI that flags people at high 6-year lung cancer risk from chest X-rays can increase CT screening in adults 50–77 who currently or formerly smoked.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 1500 (estimated) |
| Ages | 50 Years to 77 Years |
| Sex | All |
| Sponsor | Massachusetts General Hospital Academic / other |
| Locations | 1 site (Boston, Massachusetts) |
| Trial ID | NCT06910956 on ClinicalTrials.gov |
What this trial studies
The trial randomizes eligible outpatients to usual care or to an intervention where the CXR-LC AI analyzes recent PA chest X‑rays and alerts providers when a patient has high 6‑year lung cancer risk. When alerted, providers are prompted to discuss lung cancer screening CT eligibility; patients flagged as high-risk who do not meet Medicare/USPSTF pack‑year or quit‑date criteria may be offered research CT. Eligible participants are 50–77‑year‑old current or former smokers with a PA chest radiograph within the past two years and a scheduled outpatient visit, while those with recent chest CT, signs/symptoms of lung cancer, or prior lung cancer are excluded. The primary outcome is whether CT screening participation increases within 6 months after the baseline visit.
Who should consider this trial
Good fit: Ideal candidates are 50–77‑year‑old current or former smokers who have had a PA chest X‑ray within the past two years and a scheduled outpatient visit at the participating clinic.
Not a fit: People with recent chest CT, active symptoms or history of lung cancer, or those outside the age and smoking criteria are unlikely to benefit from this intervention.
Why it matters
Potential benefit: If successful, the tool could increase screening referrals and help detect lung cancers earlier by prompting clinicians to discuss CT screening.
How similar studies have performed: Retrospective studies suggest chest X‑ray AI can stratify lung cancer risk, but prospective trials using provider alerts to increase screening participation remain limited.
Eligibility criteria
Show full inclusion / exclusion criteria
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.
Where this trial is running
Boston, Massachusetts
- Massachusetts General Hospital — Boston, Massachusetts, United States (Recruiting)
Study contacts
- Study coordinator: Michael T Lu, MD, MPH
- Email: mlu@mgh.harvard.edu
- Phone: 617-726-1255
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.