A Novel Model Using Serum Thymidine Kinase 1 and Low-dose Computed Tomography Parameters to Predict Three-year Lung Cancer Risk in People with Pulmonary Nodules: A Retrospective Study.

Abstract

This study was designed to develop a model of serum thymidine kinase 1 protein (STK1p) concentration in combination with low-dose computed tomography (LDCT) to predict the risk of benign pulmonary nodules progressing into lung cancer within three years in a large screening population. The study included a retrospective cohort of 6,841 individuals aged > 30 years who had LDCT-detected pulmonary nodules, but no cancer history or baseline cancer. The outcome was a lung cancer diagnosis recorded within three years after the first detection of pulmonary nodules. The adaptive least absolute shrinkage and selection operator was used to select candidate predictors and fit a logistic model. The model was validated internally by examining discrimination (area under the receiver operating characteristic curve (AUC), calibration (calibration plot)) and net benefit. A web application was developed based on the model. The results showed that the proportion of incident lung cancer cases was 0.79% (n=52). Predictors selected for the model were STK1p and three LDCT parameters (nodule size, type, and count). The AUC of the model was 0.91 (95% confidence interval (CI): 0.86, 0.96). The model had satisfactory discrimination at internal validation (AUC: 0.90 (0.84, 0.96)) and in subgroups (AUC=0.69-0.93). The high-risk group identified by the model exhibited a significantly higher three-year lung cancer risk than the low-risk group (odds ratio (OR): 66.03 (95% CI: 30.49, 162.98)). We concluded that the novel model of STK1p and LDCT parameters together can be used to accurately predict the three-year risk of lung cancer in people with pulmonary nodules.