DecisionDx-Melanoma GEP Test Accurately Predicts SLN Positivity and Refines Recurrence Risk Assessment, New Data Shows

Castle Biosciences has shared new evidence supporting the clinical value of its DecisionDx-Melanoma gene expression profile (GEP) test in predicting sentinel lymph node (SLN) positivity and refining recurrence risk assessment in patients with cutaneous melanoma (CM).¹ The findings, presented in 2 oral sessions at the 2nd European Congress on Dermato-Oncology (ECDO) in Paris earlier this week, highlight the test’s ability to guide more precise SLN biopsy (SLNB) decisions and improve prognostic accuracy beyond traditional clinicopathologic factors.

“DecisionDx-Melanoma continues to demonstrate strong performance in helping physicians make more informed, risk-aligned decisions about sentinel lymph node biopsy,” said J. Michael Guenther, MD, presenting author for both studies and surgical oncologist at St. Elizabeth Physicians in Edgewood, Kentucky. “These new data reinforce how the test can accurately identify patients with a low likelihood of sentinel node positivity who can safely consider forgoing the procedure, as well as those who remain at risk of recurrence even when their node is negative. Together, the findings highlight how DecisionDx-Melanoma can support more precise surgical planning and ongoing patient management.”¹

Abstract Data

In the first ECDO presentation, Guenther reported results from a prospective, multicenter trial comparing DecisionDx-Melanoma’s i31-SLNB algorithm with the widely used Melanoma Institute Australia (MIA) nomogram. The study demonstrated significantly improved overall discriminative performance for i31-SLNB compared with the MIA nomogram (AUC 0.74 vs. 0.61; p = 0.001). Notably, the algorithm more accurately categorized patients at both low (<5%) and high (>10%) predicted risk.

Among patients predicted by i31-SLNB to have <5% SLN positivity risk, the actual positivity rate was only 2.6%, well below the guideline cutoff. In comparison, the MIA’s low-risk group had an observed positivity rate of 5.8%, surpassing the 5% threshold and potentially exposing more patients to unnecessary SLNB. For patients with predicted risk >10%, the actual positivity rate reached 21.4% with i31-SLNB versus 13.8% with the MIA tool, indicating superior ability to identify those most likely to benefit from SLNB.

The second oral presentation focused on a multicenter study of 810 early-stage melanoma patients with negative SLNB results. The analysis showed that the 31-GEP component of DecisionDx-Melanoma is an independent predictor of 5-year recurrence risk. Patients with a high-risk Class 2B result had significantly worse five-year recurrence-free survival compared with both Class 1A and Class 1B/2A groups (p < 0.001). When DecisionDx-Melanoma results were added to American Joint Committee on Cancer (AJCC) staging, prognostic accuracy improved significantly (ANOVA χ² = 7.75; p = 0.02).

The Growing Impact of DecisionDx-Melanoma

SLNB remains a critical tool for staging and treatment planning in CM, but current decision-making relies heavily on Breslow thickness and ulceration, which can be imprecise. Although SLNB is recommended when the probability of SLN positivity exceeds 5%, up to 88% of biopsies are negative, and approximately 16% of SLN-negative patients still experience recurrence within 5 years.² This discrepancy underscores the need for more individualized biologic risk assessment.

DecisionDx-Melanoma is a validated GEP test for patients with stage I to III CM, designed to enhance risk stratification by combining molecular insights with clinical features. The test provides 2 outputs: a personalized risk of SLN positivity and an individualized recurrence/metastasis risk estimate. By combining tumor biology with key clinicopathologic variables, the test provides a personalized risk profile designed to support SLNB decision-making, surveillance planning, and referral considerations. The US Food and Drug Administration granted Breakthrough Device designation in July.

References

1. New Data Confirms Performance of DecisionDx®-Melanoma to Identify Patients with Less Than Five Percent Risk of Sentinel Lymph Node Positivity. News release. Globe Newswire. Published November 14, 2025. Accessed November 19, 2025. https://www.globenewswire.com/news-release/2025/11/14/3188185/0/en/New-Data-Confirms-Performance-of-DecisionDx-Melanoma-to-Identify-Patients-with-Less-Than-Five-Percent-Risk-of-Sentinel-Lymph-Node-Positivity.html

2. Chen J, Xu Y, Zhou Y, Wang Y, Zhu H, Shi Y. Prognostic role of sentinel lymph node biopsy for patients with cutaneous melanoma: A retrospective study of surveillance, epidemiology, and end-result population-based data. Oncotarget 2016;7(29):45671–7