Customer Service: 866-788-9007

Integrating Clinicopathologic Features with the 31-GEP Optimizes Patient Risk-Stratification Compared to Clinicopathologic Features Alone

A recent publication in the Journal of the American Academy of Dermatology (JAAD) highlights the development and validation of an AI algorithm integrating clinicopathological features with a 31-gene expression profile. Titled “Optimizing treatment approaches for patients with cutaneous melanoma by integrating clinical and pathologic features with the 31-gene expression profile test” this study aimed to validate this approach to then provide optimized, personalized risk of recurrence (i31-ROR).


Key Results:

  • Importantly, relative to the validated i31-GEP SLNB algorithm that was validated to optimize prediction of SLN status, a different algorithm with the continuous 31-GEP score with different clinicopathologic factors was needed to optimize predictions for risk of recurrence.
  • Patients with a low-risk i31-ROR result had significantly higher 5-year recurrence-free (91% vs. 45%, P<.001), distant metastasis-free (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 SLNB while maintaining high survival rates (>98%) or were re-stratified as being at a higher or lower risk of recurrence or death.


Both the i31-ROR personalized risk of recurrence result and i31-SLNB are currently provided on the DecisionDx™-Melanoma report.


Figure shows a combined approach for complete patient prognostics. Patients receive an i31-sentinel lymph node biopsy (SLNB) result and are then analyzed by the i31-risk of recurrence (ROR). Based on the i31-SLNB and i31-ROR combined analysis, clinicians can combine these data with their clinical experience to provide more comprehensive patient care.

Scroll to Top
Scroll to Top