The Vancouver Lung Cancer Risk Prediction Model: Assessment by Using a Subset of the National Lung Screening Trial Cohort.
White CS, Dharaiya E, Campbell E, Boroczky L
Purpose To assess the likelihood of malignancy among a subset of nodules in the National Lung Screening Trial (NLST) by using a risk calculator based on nodule and patient characteristics. Materials and Methods All authors received approval for use of NLST data. An institutional review board exemption and a waiver for informed consent were granted to the author with an academic appointment. Nodule characteristics and patient attributes with regard to benign and malignant nodules in the NLST were applied to a nodule risk calculator from a group in Vancouver, Canada. Patient populations and their nodule characteristics were compared between the NLST and Vancouver cohorts. Multiple thresholds were tested to distinguish benign nodules from malignant nodules. An optimized threshold value was used to determine positive and negative predictive values, and a full logistic regression model was applied to the NLST data set. Results Sufficient data were available for 4431 nodules (4315 benign nodules and 116 malignant nodules) from the NLST data set. The NLST and Vancouver data sets differed in that the former included fewer nodules per study, fewer nonsolid nodules, and more nodule spiculation and emphysema. A composite risk score threshold of 10% was determined to be optimal, demonstrating sensitivity, specificity, positive predictive value, and negative predictive value of 85.3%, 93.9%, 27.4%, and 99.6%, respectively. The receiver operating characteristic curve for the full regression model applied to the NLST database demonstrated an area under the receiver operating characteristic curve of 0.963 (95% confidence interval: 0.945, 0.974). Conclusion Application of an NLST data subset to the Vancouver risk calculator yielded a high discriminant value, which supports the use of a risk calculator method as a valuable approach to distinguish between benign and malignant nodules. © RSNA, 2016 Online supplemental material is available for this article.