Purpose: To establish a model to predict treatment outcome of periocular locally advanced basal cell carcinoma (POLA BCC) based on initial response to treatment with vismodegib (ErivedgeTM), a sonic hedgehog inhibitor. Design: Subgroup analysis of data from the STEVIE study database. Methods: Analysis of medical history, treatment protocol, and treatment outcome of POLA BCC tumours in a STEVIE study population of 244 POLA BCC patients treated with ≥1 dose of vismodegib. Results: A predictive model for complete response (CR) was established based on the initial treatment response. A cutoff value of 20% reduction in tumour size at 3 months of treatment identified the patients with a high probability (82.76%) to achieve CR. A second cutoff value of 67.7% reduction in tumour size at 6 months of treatment improved the prediction to a 95.42% probability of a CR outcome. Conclusions: A treatment model was constructed based on the prediction of a CR outcome and the initial response to vismodegib treatment at 3 and 6 months. The study result provide significant new insights can facilitate decision-making on treatment management according to tumour response in patients with POLA BCC.