Comparative performance of lung cancer risk models to define lung screening eligibility in the United Kingdom

Abstract

Background The National Health Service England (NHS) classifies individuals as eligible for lung cancer screening using two risk prediction models, PLCOm2012 and Liverpool Lung Project-v2 (LLPv2). However, no study has compared the performance of lung cancer risk models in the UK. Methods We analysed current and former smokers aged 40–80 years in the UK Biobank (N = 217,199), EPIC-UK (N = 30,813), and Generations Study (N = 25,777). We quantified model calibration (ratio of expected to observed cases, E/O) and discrimination (AUC). Results Risk discrimination in UK Biobank was best for the Lung Cancer Death Risk Assessment Tool (LCDRAT, AUC = 0.82, 95% CI = 0.81–0.84), followed by the LCRAT (AUC = 0.81, 95% CI = 0.79–0.82) and the Bach model (AUC = 0.80, 95% CI = 0.79–0.81). Results were similar in EPIC-UK and the Generations Study. All models overestimated risk in all cohorts, with E/O in UK Biobank ranging from 1.20 for LLPv3 (95% CI = 1.14–1.27) to 2.16 for LLPv2 (95% CI = 2.05–2.28). Overestimation increased with area-level socioeconomic status. In the combined cohorts, USPSTF 2013 criteria classified 50.7% of future cases as screening eligible. The LCDRAT and LCRAT identified 60.9%, followed by PLCOm2012 (58.3%), Bach (58.0%), LLPv3 (56.6%), and LLPv2 (53.7%). Conclusion In UK cohorts, the ability of risk prediction models to classify future lung cancer cases as eligible for screening was best for LCDRAT/LCRAT, very good for PLCOm2012, and lowest for LLPv2. Our results highlight the importance of validating prediction tools in specific countries.

The Future of Lung Cancer Screening: Current Challenges and Research Priorities

“…Several multi-variable risk-prediction models to assess the risk of developing lung cancer have been developed with the aim to increase pre-test probability and thereby improve the effectiveness of screening. Both the modified Liverpool Lung Project (LLP v2 ) 8 and US Prostate, Lung, Colorectal and Ovarian (PLCO) models 9 have been shown to have greater sensitivity for lung cancer detection (compared with the original USPSTF 2013 criteria) 10 and have been used to shape selection criteria for clinical trials.…”

Baseline computed tomography screening and blood microRNA predict lung cancer risk and define adequate intervals in the BioMILD trial

“…Considering the entire cohort, the median age was 60 (IQR: 55-64) years, and 39.3% were female. Most of the participants were current smokers (79.2%), with a median of 42 pack-years (IQR: [35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51][52]. A total of 2973 (72.2%) volunteers met the NLST eligibility requirements.…”

“…In fact, the unexpectedly high negative predictive value of LDCT, as achieved by the use of a higher cutoff size for solid nodules, limits the utility of MSC in individuals who J o u r n a l P r e -p r o o f undergo CT. The observed LC incidence at 3 years was so low (<1%) among CT negative participants, regardless of MSC, that they would not even be eligible for LDCT screening according to the current recommendations (36)(37)(38), which justifies less intense (triennial) monitoring.…”

Design and methodological considerations for biomarker discovery and validation in the Integrative Analysis of Lung Cancer Etiology and Risk (INTEGRAL) Program

“…An initial analysis in the harmonized dataset compared the performance of lung cancer risk models in the United Kingdom. 35 We have defined a priority to facilitate sharing of the LC3 harmonized database, with the vision that it will serve as a resource for future research on lung cancer. We are currently establishing a legal and technical infrastructure that will allow investigators outside of the LC3 consortium to request permission to remotely access and analyze the data in a secure computing environment.…”

“…An initial analysis in the harmonized dataset compared the performance of lung cancer risk models in the United Kingdom. 35…”