DecisionDx®-Melanoma Data at SDPA and Dermato-Onco2026 Support the Test's Ability to Refine Risk Assessment Beyond AJCC Staging

The analyses separated melanoma patients into groups with different five-year survival outcomes, including patients with thin tumors.

Rhea-AI Summary

Castle Biosciences (CSTL) announced new DecisionDx-Melanoma study data assessing mortality and recurrence risk beyond conventional melanoma staging at two conferences.

In 750 patients with thin T1a melanomas, nearly 12% received increased- or highest-risk results. Five-year melanoma-specific survival was 97.1% for lowest-risk results, versus 88.1% for increased-risk and 86.2% for highest-risk results (p<0.001).

A separate study of 1,726 stage I–III patients evaluated i31-ROR, an algorithm combining gene-expression results with clinical and tumor features. Five-year recurrence-free survival was 92.5% versus 54.2% for low- versus high-risk results; survival without distant spread was 94.7% versus 68.3%, and melanoma-specific survival was 98.4% versus 81.6% (all p<0.001). Castle said the findings support individualized follow-up and surveillance. Presentations are scheduled at SDPA and Dermato-Onco2026.

Positive

• Minor pointNearly 12% of 750 T1a patients received increased- or highest-risk results, identifying elevated mortality risk.
• Minor pointFive-year melanoma-specific survival separated T1a risk groups: 97.1%, 88.1% and 86.2%, from lowest to highest risk (p<0.001).
• Minor pointi31-ROR distinguished five-year recurrence more accurately than AJCC staging in the 1,726-patient study.
• Minor pointFive-year recurrence-free survival was 92.5% for low-risk versus 54.2% for high-risk i31-ROR results (p<0.001).
• Minor pointFive-year survival without distant spread was 94.7% for low-risk versus 68.3% for high-risk results (p<0.001).
• Minor pointFive-year melanoma-specific survival was 98.4% for low-risk versus 81.6% for high-risk i31-ROR results (p<0.001).

Negative

• None.

Key Figures

Thin T1a melanoma cohort: 750 patients Elevated-risk results: 88 of 750 patients Five-year melanoma-specific survival: 97.1% vs. 88.1% vs. 86.2% +4 more

Thin T1a melanoma cohort

750 patients

Study of patients with thin T1a cutaneous melanomas

Elevated-risk results

88 of 750 patients

T1a patients classified as Class 1B/2A or Class 2B

Five-year melanoma-specific survival

97.1% vs. 88.1% vs. 86.2%

Class 1A vs. Class 1B/2A vs. Class 2B; p<0.001

Stage I–III melanoma cohort

1,726 patients

i31-ROR study across 49 U.S. sites

Five-year recurrence-free survival

92.5% vs. 54.2%

Low-risk vs. high-risk i31-ROR results; p<0.001

Five-year distant metastasis-free survival

94.7% vs. 68.3%

Low-risk vs. high-risk i31-ROR results; p<0.001

Five-year melanoma-specific survival

98.4% vs. 81.6%

Low-risk vs. high-risk i31-ROR results; p<0.001

Historical Context

1 past event · Latest: Sep 30

1 event

1. Sep 30

   clinical data

   24h Move

   -0.8%

   EADV study reported DecisionDx-Melanoma recurrence-risk separation, including five-year RFS differences by risk class.

24h Move is the share-price change in the day after each event; other market factors may also have contributed.

Key Terms

gene expression profile, recurrence-free survival, distant metastasis-free survival, clinicopathologic

4 terms

gene expression profile medical

"combines an independently validated 31-gene expression profile (GEP) score"

A gene expression profile is a snapshot of which genes in a cell or tissue are switched on and how strongly they are producing their products, like a theater marquee showing which plays are running and how popular each is. For investors, these profiles matter because they can indicate whether a drug or diagnostic is likely to work, reveal which patient groups will benefit, and reduce development time and risk—factors that influence a biotech company’s value and commercial prospects.

recurrence-free survival medical

"Five-year recurrence-free survival was 92.5% among patients with low-risk"

Recurrence-free survival is the length of time after a treatment during which a patient shows no return of disease. It’s used in clinical trials to measure how well a therapy prevents the illness from coming back — think of it like the time a repaired roof stays leak-free. For investors, longer recurrence-free survival suggests a treatment is more effective, which can improve chances of regulatory approval, commercial uptake, and long-term revenue.

distant metastasis-free survival medical

"Identified significant differences in distant metastasis-free survival (DMFS)"

The length of time after treatment during which a patient shows no return of cancer in distant organs or sites; it measures how long the disease stays confined rather than spreading to places like the liver, lungs or bones. Investors watch this endpoint because it signals a therapy’s ability to prevent dangerous recurrence, influences regulatory approval and market value, and helps predict long-term patient benefit—like timing how long a repaired dam holds back floodwater.

clinicopathologic medical

"with clinicopathologic (CP) factors"

Relating to or based on both the clinical presentation of a patient (symptoms, signs, medical history, imaging and laboratory tests) and the pathologic examination of tissue or organs (microscopic, gross, or post-mortem findings). A clinicopathologic statement, diagnosis, or correlation links what was observed in the patient with what was seen under the microscope or at autopsy; it requires both clinical data and pathological evidence and does not denote a single test or measurement.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

SDPA analysis demonstrates DecisionDx-Melanoma can identify higher-risk patients within a traditionally low-risk population with thin melanomas

 Dermato-Onco2026 analysis supports the test's ability to provide individualized five-year recurrence-risk estimates in stage I–III melanoma

FRIENDSWOOD, Texas, Nov. 11, 2026 /PRNewswire/ -- Castle Biosciences, Inc. (Nasdaq: CSTL), a company improving health through innovative tests that guide patient care, today announced it will present new data on DecisionDx-Melanoma at the Society of Dermatology Physician Associates (SDPA) 24^th Annual Fall Dermatology Conference, taking place Nov. 11-15, 2026, in Hollywood, Florida, and the 3^rd European Congress on Dermato-Oncology (Dermato-Onco2026), taking place Nov. 12-13, 2026, in Rotterdam, The Netherlands.

More precise assessment of a patient's risk of melanoma recurrence or death can help clinicians tailor follow-up and surveillance to each patient's individual needs. The analyses being presented evaluate DecisionDx-Melanoma, Castle's CP+GEP test that combines an independently validated 31-gene expression profile (GEP) score with clinicopathologic (CP) factors. The studies assess the test's ability to identify patients with thin T1a tumors at elevated risk of melanoma-specific mortality and the performance of its i31-ROR algorithm, which is designed to provide individualized five-year recurrence-risk estimates. Together, the data reinforce the value of combining tumor biology with CP factors to refine risk assessment beyond American Joint Committee on Cancer (AJCC) staging and inform more personalized, risk-aligned patient care.

"A thin melanoma may be reassuring, but these findings remind us that some of those patients still face a higher risk of dying from their disease," said study author Harrison Nguyen, M.D., MBA, MPH, board-certified dermatologist at Harrison Dermatology and Research Group in Missouri City, Texas. "The additional prognostic information provided by DecisionDx-Melanoma can help us explain to patients why we may recommend closer follow-up, even when their tumor's traditional features appear favorable."

SDPA: Identifying Higher-Risk Patients with Thin Melanomas

Castle's data at SDPA will be shared in a digital poster, which may be viewed directly through the official conference app.

ePoster Title: The 31-gene expression profile test identifies patients with AJCC T1a (<0.8 mm) cutaneous melanoma at increased risk of 5-year melanoma-specific mortality

• First author: Harrison Nguyen, M.D., MBA, MPH, FAAD

Summary: This study evaluated 750 patients with thin T1a cutaneous melanomas (<0.8 mm), a tumor category traditionally considered low risk under AJCC staging, who were diagnosed between 2013 to 2019 and had at least five years of follow-up or died from their disease. The study linked DecisionDx-Melanoma results from patients tested in clinical care with survival outcomes recorded in the National Cancer Institute's Surveillance, Epidemiology, and End Results (SEER) Program registries. The analysis demonstrated that DecisionDx-Melanoma:

• Identified higher-risk patients in approximately 1 in 8 cases: Nearly 12% of patients with T1a tumors (88 of 750) received a Class 1B/2A (increased-risk, n=59) or Class 2B (highest-risk, n=29) result, identifying a subset of patients with elevated melanoma-specific mortality risk despite having thin primary tumors.
• Significantly stratified five-year melanoma-specific survival (MSS): Survival was 97.1% for patients with Class 1A (lowest-risk) results, compared with 88.1% for patients with Class 1B/2A (increased-risk) results and 86.2% for patients with Class 2B (highest-risk) results (p<0.001). Patients with higher-risk classes had similar survival rates to patients with T2b tumors (82.4%) or stage IIA melanoma (85.1%).

These findings demonstrate that patients with thin T1a melanomas can have different biological risk profiles and outcomes. DecisionDx-Melanoma can help identify those at elevated risk who may benefit from increased surveillance or more proactive management, providing additional insight into each patient's prognosis to guide more individualized, risk-aligned care.

At SDPA, Castle will also present an ePoster titled "Clinical Utility of the 487-Gene Expression Profile Test for Atopic Dermatitis in a Private Practice Setting," featuring a case series with outcome data evaluating the use of AdvanceAD-Tx™ in 17 patients with moderate-to-severe atopic dermatitis (AD).

Dermato-Onco2026: Individualized Five-Year Recurrence-Risk Assessment

Castle's data at Dermato-Onco2026 will be shared in an oral presentation as well as a digital poster, which may be viewed in the E-Poster Gallery during the conference.

Abstract Title: The i31-ROR stratifies patients with cutaneous melanoma by high and low 5-year recurrence risk to better inform management decisions

• Abstract Number: 137
• Session #9: Short Presentations Young Investigators
• Date and Time: Friday, Nov. 13, 1:50–2:00 p.m. Central European Time

Summary: This study evaluated 1,726 patients with stage I–III cutaneous melanoma from 49 U.S. sites, representing one of Castle's largest retrospective melanoma cohorts. All patients underwent DecisionDx-Melanoma testing between 2013 and 2018 as part of their clinical care, providing a large, real-world dataset to evaluate the test's ability to predict patient outcomes.

The study focused on i31-ROR, one of DecisionDx-Melanoma's integrated algorithms, which is designed to combine the test's GEP class score with CP factors to provide an individualized five-year recurrence-risk estimate. This study suggests that DecisionDx-Melanoma can give clinicians a patient-specific risk estimate beyond the population-based risk associated with a broad staging category, helping inform how closely an individual patient should be followed.

The study demonstrated that DecisionDx-Melanoma's i31-ROR algorithm:

• Predicted five-year recurrence more accurately than AJCC staging: The i31-ROR better distinguished patients who experienced recurrence within five years from those who did not, supporting the value of individualized recurrence-risk assessment.
• Distinguished patients with low and high recurrence risk: Five-year recurrence-free survival was 92.5% among patients with low-risk i31-ROR results versus 54.2% among those with high-risk results (p<0.001).
• Identified significant differences in distant metastasis-free survival (DMFS) and MSS: Patients with low-risk i31-ROR results had five-year DMFS of 94.7%, compared with 68.3% for those with high-risk results (p<0.001). Five-year MSS was 98.4% for patients with low-risk results versus 81.6% for those with high-risk results (p<0.001).

These findings support the use of DecisionDx-Melanoma's individualized five-year recurrence-risk estimates to guide risk-aligned clinical decisions, including patient follow-up and surveillance.

About DecisionDx-Melanoma
DecisionDx-Melanoma is a gene expression profile (GEP) test designed to analyze tumor biology to deliver a personalized risk assessment for patients with stage I–III cutaneous melanoma, enhancing risk stratification beyond American Joint Committee on Cancer (AJCC) staging alone. By combining molecular insights with select clinicopathologic features, the test provides two distinct outputs: a personalized risk of sentinel lymph node (SLN) positivity and a personalized risk of recurrence and/or metastasis. This clinically actionable information is designed to help guide risk-aligned patient management decisions, including SLN biopsy consideration, follow-up intensity, imaging, and referrals.

DecisionDx-Melanoma is supported by 58 peer-reviewed publications, including prospective studies and meta-analyses, and was developed in collaboration with more than 100 leading U.S. institutions. The test has been clinically validated in more than 10,000 patient samples, ordered more than 260,000 times since launch, and has been shown to be associated with improved patient survival. Learn more at www.CastleBiosciences.com.

About AdvanceAD-Tx
AdvanceAD-Tx is a non-invasive gene expression profile (GEP) test designed to guide systemic treatment decisions for patients aged 12 years and older with moderate-to-severe atopic dermatitis (AD). Using RNA expression data from lesional skin scraping samples—no biopsy required—the test evaluates 487 genes across 12 inflammatory and cutaneous biology pathways to reveal the underlying immune biology driving an individual patient's disease. The test classifies patients into one of two molecular profiles: a Janus Kinase (JAK) Inhibitor Responder Profile or a T helper type 2 (Th2) Molecular Profile.

The prospective, clinical validation study showed that the test identifies a subset of patients with a JAK Inhibitor Responder Profile who experience significantly greater clinical benefit—including improved and faster skin clearance (EASI-90), reduced itch, fewer flares and better quality of life by three months— when treated with a JAK inhibitor therapy compared to those treated with a Th2-targeted therapy. AdvanceAD-Tx provides clinicians with objective, molecular-based insights to help personalize systemic treatment decisions and improve care for patients. Learn more at https://castlebiosciences.com/tests/therapy-guidance/advancead-tx/overview. 

About Castle Biosciences
Castle Biosciences (Nasdaq: CSTL) is a leading diagnostics company improving health through innovative tests that guide patient care. With a primary focus in dermatologic and gastroenterological disease, we develop personalized, clinically actionable solutions that help improve disease management and patient outcomes.

We put people first—empowering patients and clinicians and informing care decisions through rigorous science and advanced molecular tests that support more confident treatment planning. To learn more, visit www.CastleBiosciences.com and connect with us on LinkedIn, Instagram, Facebook and X. 

DecisionDx-Melanoma, DecisionDx-CMSeq, i31-SLNB, i31-ROR, DecisionDx-SCC, MyPath Melanoma, AdvanceAD-Tx, TissueCypher, Esopredict, DecisionDx-UM, DecisionDx-PRAME and DecisionDx-UMSeq are trademarks of Castle Biosciences, Inc.

Forward-Looking Statements
This press release contains forward-looking statements within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended, which are subject to the "safe harbor" created by those sections. These forward-looking statements include, but are not limited to, statements concerning: DecisionDx-Melanoma's ability to (i) identify patients with thin T1a melanomas at elevated risk of melanoma-specific mortality, (ii) stratify recurrence risk and provide prognostic information beyond traditional staging and, through its i31-ROR algorithm, provide individualized five-year recurrence-risk estimates for patients with stage I–III melanoma, (iii) inform risk-aligned patient management decisions, including sentinel lymph node biopsy consideration, follow-up intensity, surveillance, imaging, referrals and more proactive management, including for patients with early-stage disease whose higher risk may not be fully captured by staging alone, and (iv) provide personalized assessments of sentinel lymph node positivity and recurrence and/or metastasis risk; AdvanceAD-Tx's ability to guide systemic therapy selection to improve outcomes for patients with AD; and the ability of Castle's tests and solutions to inform care decisions, support treatment planning and improve disease management and patient outcomes. The words "believe," "can," "may," "support," "designed to," "help," "will," "should" and similar expressions are intended to identify forward-looking statements, although not all forward-looking statements contain these identifying words. We may not actually achieve the plans, intentions or expectations disclosed in our forward-looking statements, and you should not place undue reliance on our forward-looking statements. Actual results or events could differ materially from the plans, intentions and expectations disclosed in the forward-looking statements that we make. These forward-looking statements involve risks and uncertainties that could cause our actual results to differ materially from those in the forward-looking statements, including, without limitation: subsequent study or trial results and findings may contradict earlier study or trial results and findings or may not support the results obtained in these studies, including with respect to the discussion of our tests in this press release; actual application of our tests may not provide the aforementioned benefits to patients; and the risks set forth under the heading "Risk Factors" in our Annual Report on Form 10-K for the year ended December 31, 2025, and our subsequent Quarterly Reports on Form 10-Q, each as filed or to be filed with the SEC, and in our other filings with the SEC. The forward-looking statements are applicable only as of the date on which they are made, and we do not assume any obligation to update any forward-looking statements, except as may be required by law.

Investor Contact:
Camilla Zuckero
czuckero@castlebiosciences.com

Media Contact:
Allison Marshall
amarshall@castlebiosciences.com

View original content to download multimedia:https://www.prnewswire.com/news-releases/decisiondx-melanoma-data-at-sdpa-and-dermato-onco2026-support-the-tests-ability-to-refine-risk-assessment-beyond-ajcc-staging-302935721.html

SOURCE Castle Biosciences, Inc.

FAQ

AI-generated questions and answers. How Rhea-AI works. Not financial advice.

What did Castle Biosciences' DecisionDx-Melanoma study find in patients with thin melanomas?

DecisionDx-Melanoma identified increased- or highest-risk results in 88 of 750 patients with T1a melanomas measuring <0.8 mm. Five-year melanoma-specific survival was 97.1% for Class 1A lowest-risk results, 88.1% for Class 1B/2A increased-risk results and 86.2% for Class 2B highest-risk results (p<0.001).

What did Castle Biosciences' i31-ROR study show about melanoma recurrence risk?

Five-year recurrence-free survival was 92.5% for patients with low-risk i31-ROR results versus 54.2% for those with high-risk results (p<0.001). The algorithm also distinguished patients who experienced recurrence within five years from those who did not more accurately than AJCC staging.

How were Castle Biosciences' DecisionDx-Melanoma study populations selected?

The thin-melanoma study included patients diagnosed between 2013 and 2019 with at least five years of follow-up or death from their disease, linking clinical test results to SEER registry survival outcomes. The retrospective i31-ROR study included stage I–III patients from 49 U.S. sites tested during clinical care between 2013 and 2018.