In this study, researchers compared the performance of a lung cancer risk-prediction model based on a panel of selected circulating protein biomarkers to a traditional risk-prediction model and current US screening criteria. According to findings, lung cancer risk assessment may be improved by using a panel of circulating protein biomarkers, which may also be used to define eligibility for computed tomography screening.

Methods

• Researchers developed a biomarker risk score based on four proteins: cancer antigen 125, carcinoembryonic antigen, cytokeratin-19 fragment, and the precursor form of surfactant protein B.
• For developing this risk score, they used pre-diagnostic samples from 108 ever-smoking patients with lung cancer that was diagnosed within 1 year after blood collection and samples from 216 smoking-matched control participants from the CARET cohort.
• Subsequently, biomarker scores were blindly validated using absolute risk estimates among 63 ever-smoking patients with lung cancer that was diagnosed within 1 year after blood collection and 90 matched control participants from 2 large European population-based cohorts—EPIC and NSHDS.
• They assessed model validity in discriminating between future lung cancer cases and controls.
• They weighted discrimination estimates to reflect the background populations of EPIC and NSHDS validation studies (area under the receiver-operating characteristics curve [AUC], sensitivity, and specificity).

Results

• Findings revealed that an AUC of 0.83 (95% CI, 0.76-0.90) was yielded by an integrated risk prediction model that combined smoking exposure with the biomarker score vs 0.73 (95% CI, 0.64-0.82) by a model based on smoking exposure alone (P=0.003 for difference in AUC) in the validation study of 63 ever-smoking patients with lung cancer and 90 matched control participants.
• The observed sensitivity of the integrated risk prediction (biomarker) model vs the smoking model was 0.63 vs 0.43, respectively, at an overall specificity of 0.83, based on the US Preventive Services Task Force screening criteria.
• Conversely, a specificity of 0.95 was yielded by the integrated risk prediction model vs 0.86 for the smoking model, at an overall sensitivity of 0.42, based on the US Preventive Services Task Force screening criteria.