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

Abel Jarell, Brian R. Gastman, Larry D. Dillon, Eddy C. Hsueh, Sebastian Podlipnik, Kyle R. Covington, Robert W. Cook, Christine N. Bailey, Ann P. Quick, Brian J. Martin, Sarah J. Kurley, Matthew S. Goldberg, Susana Puig

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

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.

Original languageEnglish
Pages (from-to)1312-1320
Number of pages9
JournalJournal of the American Academy of Dermatology
Volume87
Issue number6
DOIs
StatePublished - Dec 2022
Externally publishedYes

Keywords

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

Fingerprint

Dive into the research topics of 'Optimizing treatment approaches for patients with cutaneous melanoma by integrating clinical and pathologic features with the 31-gene expression profile test'. Together they form a unique fingerprint.

Cite this