New Data Confirms Performance of DecisionDx®-Melanoma to Identify Patients with Less Than Five Percent Risk of Sentinel Lymph Node Positivity

Second study to be presented at the 2nd European Congress on Dermato-Oncology demonstrates DecisionDx-Melanoma can identify patients with a negative sentinel lymph node who have a higher risk of poor outcomes

FRIENDSWOOD, Texas, Nov. 14, 2025 (GLOBE NEWSWIRE) -- Castle Biosciences, Inc. (Nasdaq: CSTL), a company improving health through innovative tests that guide patient care, today announced new data demonstrating the clinical value of its DecisionDx-Melanoma test in improving sentinel lymph node (SLN) biopsy (SLNB) decision making and enhancing recurrence risk prediction in patients with cutaneous melanoma (CM). The data will be featured in two oral presentations at the 2nd European Congress on Dermato-Oncology (ECDO), taking place Nov. 17–18, 2025, in Paris, France.

“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, M.D., 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.”

SLNB helps stage patients with CM by determining whether cancer cells have spread beyond the primary tumor site, information that can help guide prognosis and treatment decisions. Current guidelines recommend considering SLNB when the estimated probability of a positive node exceeds 5%. Traditionally, that estimate is driven primarily by Breslow thickness and ulceration, which are key pathologic components used in staging. However, up to 88% of SLNB procedures yield negative results, and as many as 16% of SLN-negative patients still experience disease recurrence within five years, underscoring the need for tools that better identify who is likely to have a positive node and who may remain at risk despite a negative result.1,2

DecisionDx-Melanoma helps address this clinical challenge. The test uses tumor biology to generate a personalized class result from an independently validated gene-expression-profiling (GEP) score. The report also includes two distinct integrated algorithms: i31-SLNB, which predicts likelihood of SLN positivity, and i31-ROR, which assesses recurrence risk. By combining the GEP score with select clinicopathologic features, DecisionDx-Melanoma provides a comprehensive, personalized risk assessment to support more informed patient management decisions, such as consideration of SLNB.

Guenther will present both oral presentations at ECDO 2025:

Abstract 153: The i31-SLNB for cutaneous melanoma outperforms the clinicopathologic-only MIA nomogram at identifying patients at low risk of having a positive sentinel lymph node biopsy: A prospective, multicenter study

• Session 3: Short Presentations Young Investigators
• Session Date: Monday, November 17
• Session Time: 11:45 a.m.-12:15 p.m. Central European Time
• Summary: New data from this prospective, multicenter study show that DecisionDx-Melanoma’s i31-SLNB algorithm more precisely predicts SLN positivity compared to the Melanoma Institute Australia (MIA) nomogram, which estimates a patient’s likelihood of SLN positivity based solely on clinical and pathologic risk factors. The i31-SLNB demonstrated significantly greater discriminative performance than the MIA nomogram (AUC=0.74 vs. 0.61; p=0.001), reflecting superior sensitivity and specificity, and more accurately identified patients at both low (10%) risk of SLN positivity. Patients predicted by the i31-SLNB to have less than 5% risk had an actual SLN positivity rate of only 2.6%, compared to 5.8% in patients classified as low risk by the MIA tool. These findings show that the i31-SLNB more accurately identifies patients who could safely avoid the procedure, while the MIA nomogram’s low-risk group exceeded the 5% threshold. Conversely, among patients predicted to have greater than 10% risk, the actual SLN positivity rate was 21.4% with the i31-SLNB versus 13.8% with MIA, demonstrating that the i31-SLNB more effectively identifies those truly at higher risk. By integrating tumor biology with clinical and pathologic features, the i31-SLNB is designed to provide critical guidance to help physicians determine which patients should undergo, and which may safely forgo, an SLNB procedure. This personalized approach can help reduce unnecessary surgeries and associated risks while supporting more informed, risk-aligned care for patients with melanoma.

Abstract 140: The 31-gene expression profile is an independent predictor of poor 5-year outcomes and identifies high-risk cutaneous melanoma in patients with a negative sentinel lymph node

• Session 8: Short Presentations Young Investigators
• Session Date: Tuesday, November 18
• Session Time: 1:30-2:15 p.m. Central European Time
• Summary: New data from a multicenter study of 810 patients with early-stage (stage I–II), SLN-negative CM, meaning no cancer cells were found in the lymph node, show that the DecisionDx-Melanoma test (31-GEP) is an independent predictor of recurrence and significantly improves risk prediction beyond American Joint Committee on Cancer (AJCC) staging alone. Patients with a high-risk (Class 2B) test result had markedly lower five-year recurrence-free survival than those with Class 1A or Class 1B/2A results (p