Prediction Models for Lung Cancer Screening

(PASI Trial)

Recruiting at 3 trial locations

Overseen By Nichole T Tanner, MD MS BS

Age: Any Age

Sex: Any

Trial Phase: Academic

Sponsor: VA Office of Research and Development

Disqualifiers: Previous screening, Lung cancer diagnosis, others

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

Compensation: Varies

Number of Visits: Unknown

23520 Participants Needed

Trial Summary

What is the purpose of this trial?

Lung cancer is responsible for more deaths in the United States than breast, prostate and colon cancer combined and is the number one cancer killer of Veterans. This is because lung cancer is usually diagnosed when the disease has spread, and cure is less likely. Lung cancer screening (LCS) finds cancer at an earlier stage when it is curable, yet only 20% of eligible Veterans have been screened. Uptake is even lower among Black Veterans despite higher lung cancer risk. Using prediction models to identify high-benefit people for whom LCS should be encouraged improves efficiency and reduces disparities. Moreover, it is more patient-centered as shared decision-making conversations can be tailored with personalized information. The US Preventive Services Task Force has called for research to demonstrate that prediction-augmented LCS can be feasibly implemented at the point-of-care. The investigators propose for VA to lead this effort with a large-scale pragmatic clinical trial to show that prediction-augmented LCS is both feasible and improves LCS uptake.

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 data supports the effectiveness of the treatment Prediction Augmented Screening Initiative for lung cancer screening?

The research suggests that risk prediction models, which are part of the Prediction Augmented Screening Initiative, can improve decision-making in lung cancer screening by identifying individuals at high risk more effectively. These models have been validated and shown to help select individuals for screening, potentially reducing lung cancer mortality. ^{1 2 3 4 5}

Is the Prediction Models for Lung Cancer Screening generally safe for humans?

The research articles focus on the effectiveness and performance of prediction models for lung cancer screening, but they do not provide specific safety data for humans. ^{6 7 8 9 10}

How does this treatment differ from other lung cancer screening methods?

This treatment is unique because it uses prediction models based on low-dose computed tomography (CT) imaging and deep learning algorithms to improve the accuracy and consistency of lung cancer screening, reducing false positives and negatives compared to traditional methods. ^{1 4 11 12 13}

Research Team

Nichole Tanner, MD

Principal Investigator

Ralph H. Johnson VA Medical Center, Charleston, SC

Eligibility Criteria

This trial is for individuals eligible for lung cancer screening, particularly focusing on Veterans who are at high risk but have low screening rates. It aims to improve early detection in this group, with an emphasis on reducing disparities and increasing uptake among Black Veterans.

Inclusion Criteria

I am 50-80 years old, have a 20 pack-year smoking history, and either currently smoke or quit less than 15 years ago.

Predicted benefit calculated using LYFS-CTVA model exceeds a stringent high-benefit threshold of life-year gains with annual LCS, as recommended in the 2021 CHEST LCS guidelines

Veterans assigned a PCP at a participating site and who meet inclusion criteria at any point during the study timeframe will be enrolled into the trial. There will be two paths to patient inclusion:

Exclusion Criteria

Veterans who have previously undergone lung cancer screening

I am a veteran diagnosed with lung cancer.

Veterans who do not meet the eligibility criteria outlined above

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Implementation of prediction-augmented lung cancer screening using primary care-facing informatics tools and LCS team population management tools

169 weeks

Quarterly visits (in-person or virtual)

Follow-up

Participants are monitored for lung cancer detection rates, uptake among high-benefit Veterans, and complications from invasive procedures

3 years

Quarterly assessments

Treatment Details

Interventions

• Prediction Augmented Screening Initiative

Trial Overview The study tests whether using prediction models alongside population management tools can increase the efficiency of lung cancer screenings (LCS) and encourage higher participation rates among Veterans.

Participant Groups

Group I: PCP facing tools plus LCS population management dashboard Experimental Treatment 2 Interventions

both interventions activated

Group II: PCP facing tools Experimental Treatment 2 Interventions

Suite of PCP facing tools activated

Group III: LCS team population management tools Experimental Treatment 2 Interventions

site-specific dashboard and proactive outreach toolkit

Group IV: Usual Care Active Control 1 Intervention

Usual care

Who Is Running the Clinical Trial?

VA Office of Research and Development

Lead Sponsor

Trials

1,691

Recruited

3,759,000+

References

1. United States pubmed.ncbi.nlm.nih.gov

Evaluation of Prediction Models for Identifying Malignancy in Pulmonary Nodules Detected via Low-Dose Computed Tomography. [2020]

2. Switzerland pubmed.ncbi.nlm.nih.gov

Applying Risk Prediction Models to Optimize Lung Cancer Screening: Current Knowledge, Challenges, and Future Directions. [2022]

3. England pubmed.ncbi.nlm.nih.gov

External validation and recalibration of the Brock model to predict probability of cancer in pulmonary nodules using NLST data. [2021]

4. United States pubmed.ncbi.nlm.nih.gov

Quantitative Emphysema on Low-Dose CT Imaging of the Chest and Risk of Lung Cancer and Airflow Obstruction: An Analysis of the National Lung Screening Trial. [2022]

5. Ireland pubmed.ncbi.nlm.nih.gov

A risk prediction model for selecting high-risk population for computed tomography lung cancer screening in China. [2022]

6. United States pubmed.ncbi.nlm.nih.gov

Development of an Electronic Health Record-Based Algorithm for Predicting Lung Cancer Screening Eligibility in the Population-Based Research to Optimize the Screening Process Lung Research Consortium. [2023]

7. United States pubmed.ncbi.nlm.nih.gov

Deep Learning to Optimize Candidate Selection for Lung Cancer CT Screening: Advancing the 2021 USPSTF Recommendations. [2022]

8. United States pubmed.ncbi.nlm.nih.gov

A Comparative Modeling Analysis of Risk-Based Lung Cancer Screening Strategies. [2021]

9. England pubmed.ncbi.nlm.nih.gov

The decision to biopsy in a lung cancer screening program: Potential impact of risk calculators. [2020]

10. Germany pubmed.ncbi.nlm.nih.gov

Predictive Accuracy of the PanCan Lung Cancer Risk Prediction Model -External Validation based on CT from the Danish Lung Cancer Screening Trial. [2022]

11. United States pubmed.ncbi.nlm.nih.gov

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. [2022]

12. China pubmed.ncbi.nlm.nih.gov

Performance of various risk prediction models in a large lung cancer screening cohort in Gdańsk, Poland-a comparative study. [2022]

13. England pubmed.ncbi.nlm.nih.gov

Predicting the future risk of lung cancer: development, and internal and external validation of the CanPredict (lung) model in 19·67 million people and evaluation of model performance against seven other risk prediction models. [2023]