A retrospective validation study of three models to estimate the probability of malignancy in patients with small pulmonary nodules from a tertiary oncology follow-up centre.

AIM

To estimate the probability of malignancy in small pulmonary nodules (PNs) based on clinical and radiological characteristics in a non-screening population that includes patients with a prior history of malignancy using three validated models.

MATERIALS AND METHODS

Retrospective data on clinical and radiological characteristics was collected from the medical records of 702 patients (379 men, 323 women; range 19-94 years) with PNs ≤12 mm in diameter at a single centre. The final diagnosis was compared to the probability of malignancy calculated by one of three models (Mayo, VA, and McWilliams). Model accuracy was assessed by receiver operating characteristics (ROC). The models were calibrated by comparing predicted and observed rates of malignancy.

RESULTS

The area under the ROC curve (AUC) was highest for the McWilliams model (0.82; 95% confidence interval [CI]: 0.78-0.91) and lowest for the Mayo model (0.58; 95% CI: 0.55-0.59). The VA model had an AUC of (0.62; 95% CI: 0.47-0.64). Performance of the models was significantly lower than that in the published literature.

CONCLUSIONS

The accuracy of the three models is lower in a non-screening population with a high prevalence of prior malignancy compared to the papers that describe their development. To the authors' knowledge, this is the largest study to validate predictive models for PNs in a non-screening clinically referred patient population, and has potential implications for the implementation of predictive models.