AI Tool for Lung Cancer Screening

Overseen By Michael T Lu, MD, MPH

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Massachusetts General Hospital

Disqualifiers: Lung cancer, Recent chest CT, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

1500 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests a new AI tool, CXR-LC, designed to help doctors identify patients at high risk for lung cancer using chest x-rays. The main goal is to determine if this tool encourages more people to undergo a lung cancer screening CT (a detailed scan of the lungs) within six months. Researchers will compare two groups: one where doctors receive an alert to discuss screening and one where they do not. This trial suits current or former smokers aged 50 to 77 who have had a chest x-ray in the last two years. As an unphased trial, it offers participants the chance to contribute to innovative research that could enhance early lung cancer detection.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this AI tool is safe for lung cancer screening?

Research has shown that the CXR-LC tool, an AI system, predicts lung cancer risk from chest X-rays. It aids doctors in determining who might need further lung cancer screening. Studies have found this tool to be more effective at identifying potential cases compared to other methods.

As a software tool, CXR-LC does not carry direct health risks like drug side effects. It analyzes X-ray images to assess cancer risk. No reports of negative effects have been directly linked to using this AI tool in the studies reviewed. The tool alerts doctors, who then decide on the next steps for screening.

Overall, using CXR-LC appears safe for patients. It provides doctors with more information to help them make better screening decisions. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the AI Tool for Lung Cancer Screening because it uses advanced artificial intelligence to analyze chest X-rays more effectively than traditional methods. Unlike standard screenings, which rely heavily on human interpretation, this AI tool can quickly and accurately identify potential signs of lung cancer, potentially leading to earlier detection. This could make a significant difference in patient outcomes by catching the disease at a more treatable stage.

What evidence suggests that this AI tool is effective for improving lung cancer screening CT participation?

Research has shown that chest X-ray (CXR) screening can greatly improve lung cancer outcomes. Studies have found that CXR screening links to better survival rates and a noticeable decrease in lung cancer deaths. Specifically, it can lower lung cancer deaths by about 18% to 36%, depending on the study. While low-dose CT (computed tomography) scans are usually more effective than CXR for early detection, CXR remains better than not screening at all. This trial tests the AI tool, CXR-LC, as an intervention to alert healthcare providers about patients at high risk, potentially increasing the number of people screened for lung cancer. ^{5 6 7 8 9}

Are You a Good Fit for This Trial?

This trial is for people aged 50-77 who currently smoke or used to smoke and might be eligible for lung screening according to Medicare guidelines. They must have a scheduled outpatient appointment with a participating provider and a recent chest x-ray.

Inclusion Criteria

I have an upcoming appointment with a participating doctor.

I've had a chest X-ray within the last 2 years.

I am between 50 and 77 years old and have a history of smoking.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Providers receive alerts to discuss lung cancer screening CT eligibility with high-risk patients based on CXR-LC AI tool

6 months

Follow-up

Participants are monitored for lung cancer screening CT participation

6 months

What Are the Treatments Tested in This Trial?

Interventions

• CXR-LC

Trial Overview The study tests an AI tool (CXR-LC) that alerts doctors about patients at high risk of lung cancer based on chest x-rays, aiming to see if it increases participation in lung cancer screening CTs six months after the initial visit.

How Is the Trial Designed?

Group I: Intervention Experimental Treatment 1 Intervention

Group II: Non-Intervention Active Control 1 Intervention

Who Is Running the Clinical Trial?

Massachusetts General Hospital

Lead Sponsor

Trials

3,066

Recruited

13,430,000+

Harvard Risk Management Foundation

Collaborator

Trials

7

Recruited

31,100+

Citations

1. ncbi.nlm.nih.gov ncbi.nlm.nih.gov/books/NBK534580/

Clinical effectiveness outcome data - NCBI Bookshelf Clinical effectiveness outcome data - Low-dose computed tomography for lung cancer screening in high-risk populations: a systematic review and economic ...

2. journal.chestnet.org journal.chestnet.org/article/S0012-3692(16)36466-2/fulltext

Chest X-ray (CXR) Screening Improves Outcomes in Lung ... CXR screening was associated with a highly significant survival advantage not attributable to overdiagnosis and a significant reduction in the number of ...

3. nature.com nature.com/articles/s41467-025-63471-6

A comparative analysis of heterogeneity in lung cancer ... Screening was effective for adenocarcinoma and OTH, reducing mortality by 17.8–23.0% (medians NELSON&NLST) and 24.5–35.5% (medians NELSON&NLST), ...

4. acsjournals.onlinelibrary.wiley.com acsjournals.onlinelibrary.wiley.com/doi/full/10.3322/caac.21811

Screening for lung cancer: 2023 guideline update from the ... ... LDCT substantially outperformed CXR in the detection of small, resectable lung cancers. ... cancer mortality reduction by LDCT screening—results ...

5. ascopubs.org ascopubs.org/doi/10.1200/JCO.2016.34.15_suppl.e18246

Comparative effectiveness of lung cancer screening by ... 5-year OS was superior with CXR, 25% vs.18% (p < 0.001). Conclusions: CT screening is superior to CXR, while CXR screening is superior to no ...

6. pubmed.ncbi.nlm.nih.gov pubmed.ncbi.nlm.nih.gov/32866413/

Deep Learning Using Chest Radiographs to Identify High-Risk ... When compared in equal-sized screening populations, CXR-LC was more sensitive than CMS eligibility in the PLCO data set (74.9% vs. 63.8%; P = ...

7. uspreventiveservicestaskforce.org uspreventiveservicestaskforce.org/uspstf/recommendation/lung-cancer-screening

Recommendation: Lung Cancer: Screening The USPSTF recommends annual screening for lung cancer with LDCT in adults aged 50 to 80 years who have at least a 20 pack-year smoking history.

8. clinicaltrials.gov clinicaltrials.gov/study/NCT06910956

Deep Learning Using Chest X-Rays to Identify High Risk ... 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. Participant ...

9. jamanetwork.com jamanetwork.com/journals/jamanetworkopen/fullarticle/2799952

Validation of a Deep Learning–Based Model to Predict ... CXR-LC, an open-source deep learning tool that estimates lung cancer risk from existing chest radiograph images and commonly available ...