(ChemotherapyAdvisor) – Risk model predicts lung cancer better than smoking duration or family history, according to an international team of researchers. This conclusion is based on a study entitled “Predictive Accuracy of the Liverpool Lung Project Risk Model for Stratifying Patients for Computed Tomography Screening for Lung Cancer: A Case–Control and Cohort Validation Study,” which was published online in the Annals of Internal Medicine on August 21.

The LLP model, which calculates an individual’s chance of developing lung cancer within the next 5 years by factoring in demographics such as smoking duration, previous diagnosis of pneumonia, occupational exposure to asbestos, and more, can also be used to select high-risk individuals for prevention and control programs. The LLP model produces an area under the receiver-operating characteristic curve (AUC).  

In this international, case-control and prospective cohort study, the investigators aimed to validate a prediction model of lung cancer to guide the appropriate referral of patients for computed tomography (CT) screening. To meet this aim, the investigators calculated 5-year absolute risks for lung cancer as predicted by the Liverpool Lung Project (LLP) risk model in order to demonstrate its capability to stratify patients for CT screening. Data were also obtained from European Early Lung Cancer (EUELC) and Harvard case-control studies and the LLP population-based prospective cohort (LLPC) study.  

Continue Reading

The model was very effective at predicting risk in both the Harvard (AUC, 0.76 [95% CI, 0.75–0.78]) and the LLPC (AUC, 0.82 [CI, 0.80–0.85]) studies, but only modestly effective in the EUELC (AUC, 0.67 [CI, 0.64–0.69]) study. Further evaluation of the LLP risk model indicated that it is better than “smoking duration or family history alone in stratifying high-risk patients for lung cancer CT screening,” the investigators reported.

“Validation of the LLP risk model in three independent external data sets demonstrated good discrimination and evidence of predicted benefits for stratifying patients for lung cancer CT screening, but further studies are needed to prospectively evaluate model performance and evaluate the optimal population risk thresholds for initiating lung cancer screening,” the investigators concluded.