Clinical Report: Can Proteomics Refine Lung Screening?

Overview

The INTEGRAL-Risk model, utilizing 13 circulating protein biomarkers, shows improved short-term lung cancer risk prediction compared to existing models, capturing a higher percentage of lung cancer cases within one year. This suggests significant potential for refining eligibility for low-dose computed tomography screening, which could lead to earlier detection and better outcomes.

Background

Lung cancer remains a leading cause of cancer-related mortality, necessitating effective screening strategies. Current guidelines primarily rely on smoking history and demographic factors, which may exclude high-risk individuals. The development of biomarker-based models like INTEGRAL-Risk could enhance early detection and improve screening outcomes, especially given that lung cancer accounts for a substantial percentage of cancer deaths.

Data Highlights

Key Findings

• The INTEGRAL-Risk model had an AUC of 0.88 for predicting lung cancer within 1 year.
• It captured 85% of lung cancer cases within 1 year, outperforming PLCOm2012 (70%) and USPSTF 2021 criteria (63%).
• Subgroup analyses indicated higher discrimination among Asian, non-Hispanic Black, and non-Hispanic White participants.
• The model improved risk classification for individuals ineligible under USPSTF 2021 criteria.
• Discriminative performance decreased over longer follow-up periods, with AUCs of 0.84 at 2 years and 0.81 at 3 years.
• Recalibration may be necessary for clinical implementation due to underprediction in certain racial groups.
• Quasi-NNS refers to the quasi-number needed to screen to classify one lung cancer case as eligible.

Clinical Implications

The INTEGRAL-Risk model may enhance the identification of high-risk individuals for lung cancer screening, potentially leading to earlier detection and improved outcomes. However, further validation and recalibration are essential before clinical adoption.

Conclusion

The INTEGRAL-Risk model represents a promising advancement in lung cancer risk assessment, warranting further research to confirm its utility in clinical practice.

Related Resources & Content

1. Zahed H, et al., JAMA, 2023 -- Biomarker-Based Eligibility for Lung Cancer Screening: Validation of the Protein-Based INTEGRAL-Risk Model
2. Kennedy, et al., Nature Communications, 2022 -- Report Examines Imaging Approach With Potential to Detect Lung Cancer at the Cellular Level
3. Kearney, et al., Annals of Internal Medicine, 2024 -- Can Alternative Criteria Help Identify Patients Who May Benefit From Lung Cancer Screening?
4. US Preventive Services Taskforce, 2022 -- Recommendation: Lung Cancer: Screening
5. European Radiology — Advantages and Disadvantages of Reporting Incidental Findings in Lung Cancer Screening Programs
6. European Journal of Preventive Cardiology — Assessing Proteomic Approaches for Heart Failure Prediction in Dysglycaemic Patients: Are We Prepared to Rely on This Technology?
7. Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening
8. Advantages and Disadvantages of Reporting Incidental Findings in Lung Cancer Screening Programs
9. Recommendation: Lung Cancer: Screening | United States Preventive Services Taskforce
10. Biomarker-Based Eligibility for Lung Cancer Screening: Validation of the Protein-Based INTEGRAL-Risk Model | Lung Cancer | JAMA | JAMA Network