Efficacy of Risk Prediction Models and Thresholds to Select Patients for Lung Cancer Screening.
Richard J SmithThurairajah VijayaharanVictoria LinehanZhuolu SunJean Hai Ein YongScott HarrisHensley H MariathasRick BhatiaPublished in: Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes (2022)
Purpose Screening for lung cancer is recommended to reduce lung cancer mortality, but there is no consensus on patient selection for screening in Canada. Risk prediction models are more efficacious than the screening recommendations of the Canadian Task Force on Preventive Health Care (CTFPHC), but it remains to be determined which model and threshold are optimal. Methods We retrospectively applied the PLCO m2012 , PLCO all2014 and LLPv2 risk prediction models to 120 lung cancer patients from a Canadian province, at risk thresholds of ≥ 1.51% and ≥ 2.00%, to determine screening eligibility at time of diagnosis. OncoSim modelling was used to compare these risk thresholds. Results Sensitivities of the risk prediction models at a threshold of ≥ 1.51% were similar with 93 (77.5%), 96 (80.0%), and 97 (80.8%) patients selected for screening, respectively. The PLCO m2012 and PLCO all2014 models selected significantly more patients for screening at a ≥ 1.51% threshold. The OncoSim simulation model estimated that the ≥ 1.51% threshold would detect 4 more cancers per 100 000 people than the ≥ 2.00% threshold. All risk prediction models, at both thresholds, achieved greater sensitivity than CTFPHC recommendations, which selected 56 (46.7%) patients for screening. Conclusion Commonly considered lung cancer screening risk thresholds (≥1.51% and ≥2.00%) are more sensitive than the CTFPHC 30-pack-years criterion to detect lung cancer. A lower risk threshold would achieve a larger population impact of lung cancer screening but would require more resources. Patients with limited or no smoking history, young patients, and patients with no history of COPD may be missed regardless of the model chosen.