Risk models may improve lung cancer screening
Analysis found no single prediction model optimized screening eligibility, sensitivity, and efficiency across all racial and ethnic groups.
By
Olivia Anderson
August 24, 2026
Clinical Scorecard: Risk models may improve lung cancer screening
At a Glance
Category Detail
Condition Lung Cancer Screening Key Mechanisms Risk-based screening strategies may enhance efficiency and reduce disparities across racial and ethnic groups. Target Population US adults aged 50 to 80 years with a smoking history Care Setting Lung cancer screening programs
Key Highlights
Study evaluated 16 lung cancer risk prediction models among over 641,000 participants. Existing models showed substantial underestimation of risk in non-Hispanic Black participants. Risk-based strategies improved screening efficiency compared to USPSTF criteria. Models incorporating race and ethnicity as predictors had better calibration across groups. No single strategy optimized all performance measures equally well. Guideline-Based Recommendations
Diagnosis
Utilize risk prediction models to assess lung cancer risk in diverse populations. Management
Implement risk-based screening strategies to enhance screening efficiency. Monitoring & Follow-up
Continuously evaluate model performance across different racial and ethnic groups. Risks
Underrepresentation of minority groups in studies may affect model applicability. Patient & Prescribing Data
Diverse US population including Asian, Hispanic, non-Hispanic Black, and non-Hispanic White individuals.
Risk-based models may improve screening outcomes but require further optimization.
Clinical Best Practices
Incorporate race and ethnicity in risk prediction models for lung cancer screening. Regularly assess and refine screening strategies to minimize disparities. Related Resources & Content
