Optimizing treatment approaches for patients with cutaneous melanoma by integrating clinical and pathologic features with the 31-gene expression profile test

Abstract

Background: Many patients with low-stage cutaneous melanoma will experience tumor recurrence, metastasis, or death, and many higher staged patients will not.

Objective: To develop an algorithm by integrating the 31-gene expression profile test with clinicopathologic data for an optimized, personalized risk of recurrence (integrated 31 risk of recurrence [i31-ROR]) or death and use i31-ROR in conjunction with a previously validated algorithm for precise sentinel lymph node positivity risk estimates (i31-SLNB) for optimized treatment plan decisions.

Methods: Cox regression models for ROR were developed (n = 1581) and independently validated (n = 523) on a cohort with stage I-III melanoma. Using National Comprehensive Cancer Network cut points, i31-ROR performance was evaluated using the midpoint survival rates between patients with stage IIA and stage IIB disease as a risk threshold.

Results: Patients with a low-risk i31-ROR result had significantly higher 5-year recurrence-free survival (91% vs 45%, P < .001), distant metastasis-free survival (95% vs 53%, P < .001), and melanoma-specific survival (98% vs 73%, P < .001) than patients with a high-risk i31-ROR result. A combined i31-SLNB/ROR analysis identified 44% of patients who could forego sentinel lymph node biopsy while maintaining high survival rates (>98%) or were restratified as being at a higher or lower risk of recurrence or death.

Limitations: Multicenter, retrospective study.

Conclusion: Integrating clinicopathologic features with the 31-GEP optimizes patient risk stratification compared to clinicopathologic features alone.

Keywords: 31-GEP; AJCC; Cox regression; NCCN; SLNB; artificial intelligence; cutaneous melanoma; gene expression profile; i31-GEP; neural networks; risk of recurrence.