What type of study is this?

This is a Systematic Review study (also classified as: Meta-Analysis).

September 17, 2025Open Access

Risk prediction for lung cancer screening: a systematic review and meta-regression

Key Points

Moderate to excellent discrimination was observed for lung cancer risk prediction models, ranging from AUC 0.70 to >0.90.
Of the 1987 reviewed records, 68 models met criteria, with 41 focused on screening selection and 27 on nodule classification.
Machine learning and deep learning methods are increasingly common in risk prediction modeling, showing promise over traditional approaches.
Inconsistent calibration and limited external validation among models challenge their clinical integration and use.

Abstract

Abstract Background Lung cancer (LC) is the leading cause of cancer mortality, often diagnosed at advanced stages. Screening reduces mortality in high-risk individuals, but its efficiency can improve with pre- and post-screening risk stratification. With recent LC screening guideline updates in Europe and the US, numerous novel risk prediction models have emerged since the last systematic review of such models. We reviewed risk-based models for selecting candidates for CT screening, and post-CT stratification. Methods We systematically reviewed Embase and MEDLINE (2020–2024), identifying studies proposing new LC risk models for screening selection or nodule classification. Data extraction included study design, population, model type, risk horizon, and internal/external validation metrics. In addition, we performed an exploratory meta-regression of AUCs to assess whether sample size, model class, validation type, and biomarker use were associated with discrimination. Results Of 1987 records, 68 were included: 41 models were for screening selection (20 without biomarkers, 21 with), and 27 for nodule classification. Regression-based models predominated, though machine learning and deep learning approaches were increasingly common. Discrimination ranged from moderate (AUC≈0.70) to excellent (>0.90), with biomarker and imaging-enhanced models often outperforming traditional ones. Model calibration was inconsistently reported, and fewer than half underwent external validation. Meta-regression suggested that, among pre-screening models, larger sample sizes were modestly associated with higher AUC. Conclusion 75 models had been identified prior to 2020, we found 68 models since. This reflects growing interest in personalized LC screening. While many demonstrate strong discrimination, inconsistent calibration and limited external validation hinder clinical adoption. Future efforts should prioritize improving existing models rather than developing new ones, transparent evaluation, cost-effectiveness analysis, and real-world implementation.

Read Full Paperexternally

Demander à l'IA

Bookmark

View Full Paper