In a study reported in the Journal of Clinical Oncology, Varey et al developed the Melanoma Institute Australia (MIA) calculator for predicting recurrence-free and overall survival in stage II melanoma and found that it outperformed modeling based on American Joint Committee on Cancer (AJCC)-8th edition melanoma staging.
Study Details
The study involved data on 3,220 patients from the MIA database diagnosed with clinical or pathologic stage II melanoma. Prediction models were developed using multivariate Cox regression analyses (MIA models) and externally validated using data sets from the United States and the Netherlands. Model performance was assessed using C-statistics and calibration plots and compared with Cox models based on AJCC-8th edition staging (stage models). The final MIA calculator for recurrence-free survival included: age, Breslow thickness, sex, ulceration, satellites, lymphovascular invasion, tumor-infiltrating lymphocytes, regression, sentinel node biopsy status, melanoma subtype, primary lesion site, and mitosis. The calculator for overall survival included: age, Breslow thickness, sex ulceration, tumor-infiltrating lymphocytes, sentinel node biopsy status, melanoma subtype, and mitosis.
Key Findings
For the MIA model vs the stage model, 5-year recurrence-free survival C-statistics were 0.70 vs 0.61 and 10-year recurrence-free survival C-statistics were 0.73 vs 0.60.
For the MIA model vs the stage model, 5-year overall survival C-statistics were 0.71 vs 0.62 and 10-year overall survival C-statistics were 0.75 vs 0.61.
In a U.S. cohort of 800 patients, for the MIA model vs the stage model, 5-year recurrence-free survival C-statistics were 70.6 vs 64.2 and 10-year recurrence-free survival C-statistics were 71.7 vs 63.3. C-statistics were 0.68 vs 0.62 for 5-year and 0.69 vs 0.58 for 10-year overall survival.
In a Dutch cohort of 8,612 patients, for the MIA model vs the stage model, 5-year recurrence-free survival C-statistics were 71.4 vs 64.3 and 10-year recurrence-free survival C-statistics were 73.7 vs 62.3. C-statistics were 0.77 vs 0.65 for 5-year and 0.80 vs 0.62 for 10-year overall survival.
The investigators concluded, “The MIA models offer accurate and personalized estimates of both recurrence-free survival and overall survival in patients with stage II melanoma even in the absence of pathological staging with sentinel node biopsy. These models were robust on external validations and may be used in everyday practice both with (ideally) and without performing sentinel node biopsy to identify high-risk patients for further management strategies. An online tool will be available at the MIA website (Risk Prediction Tools).”
Alexander H.R. Varey, MBChB, PhD, FRACS(Plast), FRCS(Plast), Department of Plastic Surgery, Westmead Hospital, Westmead, Australia, is the corresponding author for the Journal of Clinical Oncology article.
Disclosure: The study was supported by the Australian National Health and Medical Research Council and others. For full disclosures of the study authors, visit ascopubs.org.
