Predicting a metachronous cutaneous squamous cell carcinoma: a competing-risk model based on nationwide linked registries.

BACKGROUND

following a first cutaneous squamous cell carcinoma (CSCC), approximately one-third of patients develop new primaries, escalating their risk of metastasis and poor outcomes. However, current follow-up strategies lack risk stratification, representing a critical gap in patient management.

OBJECTIVE

to develop and validate a prognostic model to quantify individualized absolute risk of a first metachronous CSCC after an index tumor, accurately accounting for the high competing risk of mortality in this typically elderly population.

METHODS

we conducted a nationwide, population-based cohort study of 11,737 patients with a first histologically confirmed CSCC (Netherlands Cancer Registry, 2007-2008) with up to 10 years of follow-up. Subsequent tumors were identified via linkage to the Automated National Pathological Anatomy Archive (Palga). A Fine-Gray competing-risk model was developed using routinely available clinical and pathological predictors. Model performance was assessed 10-fold cross-validation, quantifying discrimination (time-dependent area under the receiving operator characteristic curve [AUCt]) and calibration. Clinical utility was evaluated using Decision Curve Analysis (DCA) and tertile risk stratification.

RESULTS

during follow-up, 3,288 (28%) developed a first metachronous CSCC. Key predictors included markers of cumulative UV-exposure (included AK history, ≥5 prior BCCs), and chronic lymphocytic leukaemia/small lymphocytic leukaemia (CLL/SLL). Male sex and presence of synchronous CSCC at baseline were also associated with higher risk. While discrimination was modest (cross-validated 5-year AUCt: 0.64), the model demonstrated excellent calibration across all predictor subgroups. DCA showed modest net benefit for predicted probabilities between 18% and 45%. Risk stratification into tertiles revealed a nearly five-fold acceleration: the high-risk tertile reached a 15% cumulative incidence in 1.4 years, compared to 6.9 years for the low-risk tertile.

CONCLUSIONS

this competing-risk model provides individualized, well-calibrated absolute risk estimates for a first metachronous CSCC. Based on routinely available clinical features, it offers insight into how established predictors shape risk in this high-susceptibility population and quantifies relative risk acceleration. External validation and the identification of novel predictors are necessary to further refine the model and support personalized surveillance strategies.