Castle Biosciences' DecisionDx®-Melanoma Test Significantly Improves Risk Prediction Within AJCC Stages to Support Personalized, Risk-Aligned Management of Cutaneous Melanoma, Data to Be Presented at AAD 2026

Rhea-AI Summary

Castle Biosciences (Nasdaq: CSTL) will present SEER-linked data at AAD 2026 showing that the DecisionDx-Melanoma 31-gene expression profile significantly stratifies five-year melanoma-specific survival within AJCC stages and T categories.

In 1,868 patients (2013–2019), Class 1A versus 2B outcomes differed markedly (T1: 96.7% vs 70.0%; Stage IIB–III: 87.4% vs 48.5%), supporting more personalized, risk-aligned management.

Positive

• Large registry cohort: analysis of 1,868 SEER-linked patients (2013–2019)
• T1 survival split: five-year MSS 96.7% (Class 1A) vs 70.0% (Class 2B)
• Stage IIB–III split: five-year MSS 87.4% (low-risk) vs 48.5% (high-risk)
• Supports management changes: may inform escalated care for higher-risk and reduced interventions for lower-risk patients

Negative

• Retrospective registry design: SEER-linked observational analysis, not a randomized prospective trial
• Peer-review pending: full abstract available at AAD and JAAD supplement publication expected Fall 2026

Key Figures

SEER-linked patients: 1,868 patients SEER sites: 22 sites Follow-up period: 2013–2019 +5 more

8 metrics

SEER-linked patients 1,868 patients Cutaneous melanoma cohort linked to SEER registries

SEER sites 22 sites Registry data sources for DecisionDx-Melanoma analysis

Follow-up period 2013–2019 Years of SEER-linked patient data

T1 low-risk MSS 96.7% Five-year melanoma-specific survival, Class 1A T1 tumors

T1 high-risk MSS 70.0% Five-year melanoma-specific survival, Class 2B T1 tumors

Stage IIB–III low-risk MSS 87.4% Five-year MSS for low-risk DecisionDx-Melanoma results

Stage IIB–III high-risk MSS 48.5% Five-year MSS for high-risk DecisionDx-Melanoma results

Significance level p<0.05 Log-rank test for MSS stratification across subgroups

Market Reality Check

Price: $24.70 Vol: Volume 448,549 vs 20-day ...

normal vol

$24.70 Last Close

Volume Volume 448,549 vs 20-day average 391,638 (relative volume 1.15). normal

Technical Shares at $24.70, trading below 200-day MA $27.78 and 44.22% below 52-week high $44.28.

Peers on Argus

CSTL was down 2.26% while key peers showed mixed moves: FLGT -0.97%, CDNA -2.89%...

CSTL was down 2.26% while key peers showed mixed moves: FLGT -0.97%, CDNA -2.89%, PSNL -2.66%, MYGN 0%, NEO +1.7%. The pattern suggests stock-specific pressure rather than a uniform sector move.

Historical Context

5 past events · Latest: Mar 13 (Positive)

Pattern 5 events

Date	Event	Sentiment	Move	Catalyst
Mar 13	Clinical study data	Positive	+0.9%	Prospective study showed i31-SLNB identified patients below 5% SLN risk.
Mar 09	Clinical results update	Positive	-0.4%	Largest multicenter study confirmed 2.6% nodal positivity in low-risk group.
Mar 04	Conference presentation	Positive	-0.9%	SSO 2026 data presentation on i31-SLNB identifying patients avoiding SLNB.
Mar 03	HQ opening	Positive	+2.2%	Announced grand opening of new Friendswood headquarters supporting growth.
Feb 26	Earnings results	Positive	-7.3%	Reported 2025 revenue of $344.2M exceeding guidance with strong test growth.

Pattern Detected

Recent positive clinical and corporate updates often led to modest or mixed price reactions, with one earnings beat accompanied by a notable decline.

Recent Company History

Over the past months, Castle Biosciences highlighted multiple advances for DecisionDx-Melanoma and solid 2025 financial results. Clinical updates in early March 2026 around the i31-SLNB algorithm showed low sentinel lymph node positivity and strong recurrence-free survival, with small price moves. The Feb 26, 2026 earnings release reported $344.2M 2025 revenue and strong test volume growth but saw a -7.25% reaction. Today’s AAD presentation continues the theme of expanding evidence for DecisionDx-Melanoma’s risk stratification.

Market Pulse Summary

This announcement adds robust real-world support for DecisionDx-Melanoma, showing significant five-y...

Analysis

This announcement adds robust real-world support for DecisionDx-Melanoma, showing significant five-year melanoma-specific survival stratification across 1,868 SEER-linked patients and multiple AJCC stages. It extends a series of recent clinical publications and conference presentations focused on more precise risk assessment in cutaneous melanoma. In context with solid 2025 revenue performance and ongoing insider selling disclosures, investors may watch for how additional clinical uptake, future guideline interactions, and subsequent data releases shape Castle’s longer-term trajectory.

Key Terms

log-rank test

1 terms

log-rank test medical

"...MSS was 87.4% for low-risk versus 48.5% for high-risk results (log-rank test; p<0.05)."

A log-rank test is a statistical method used to compare how long subjects in two or more groups take to experience a specific event, such as time until death, relapse, or device failure. For investors it matters because it helps determine whether one treatment or product truly outperforms another over time—similar to checking whether one brand of lightbulb consistently lasts longer than another—information that can influence regulatory decisions, market potential, and valuations.

AI-generated analysis. Not financial advice.

Data from 1,868 Surveillance, Epidemiology and End Results (SEER)-linked patients show DecisionDx-Melanoma significantly stratifies five-year melanoma-specific survival within American Joint Committee on Cancer (AJCC) stages and T categories, identifying patients whose mortality risk is substantially higher or lower than staging alone would predict

FRIENDSWOOD, Texas, March 27, 2026 /PRNewswire/ -- Castle Biosciences, Inc. (Nasdaq: CSTL), a company improving health through innovative tests that guide patient care, will present new data at the 2026 American Academy of Dermatology (AAD) Annual Meeting, taking place March 27–31 in Denver, demonstrating that its DecisionDx-Melanoma test refines mortality risk within AJCC stages for patients with cutaneous melanoma (CM). The data show that DecisionDx-Melanoma identifies clinically meaningful differences in mortality risk among patients within the same stage, which may help clinicians more confidently escalate care for higher-risk patients while avoiding unnecessary interventions in those at lower risk of poor outcomes.

"The findings being presented at AAD reinforce that staging alone does not tell the whole story," said Harrison Nguyen M.D., MBA, MPH, lead study author and double board-certified dermatologist and fellowship-trained Mohs micrographic surgeon. "Incorporating DecisionDx-Melanoma into routine risk assessment provides physicians with biologic information that complements staging and supports more personalized management decisions, helping to identify patients who may warrant closer monitoring or earlier intervention, while also recognizing those who may be safely managed less intensively."

Detailed findings from this analysis will be presented in the following poster at AAD:

• ePoster: 76747 – The 31-GEP provides actionable risk stratification of 5-year melanoma specific survival rates within AJCC subgroups
• Lead Author: Harrison Nguyen M.D., MBA, MPH, Harrison Dermatology & Research Group, Missouri City, Texas

This poster from Castle's ongoing collaboration leveraging data from the National Cancer Institute's SEER Program registries evaluates risk stratification using the DecisionDx-Melanoma test in patients with CM across T categories and AJCC stages.

Traditional AJCC staging groups biologically distinct tumors based on clinicopathologic features alone, which can underestimate or overestimate a patient's true risk of poor outcomes. In this analysis, registry data from 22 SEER sites were linked to data from patients with stage I–III CM who were clinically tested with the DecisionDx-Melanoma test and had at least five years of follow up or death from their disease (n=1,868; 2013–2019). The test significantly stratified five-year melanoma-specific survival (MSS) within T categories and AJCC substages. In patients with T1 tumors, five-year MSS was 96.7% for those with low-risk (Class 1A) results versus 70.0% for high-risk (Class 2B) results, and among patients with Stage IIB–III disease, MSS was 87.4% for low-risk versus 48.5% for high-risk results (log-rank test; p<0.05).

Overall, the data show that DecisionDx-Melanoma can identify patients at higher or lower risk than predicted by AJCC staging alone, including high-risk T1 (thin) tumors with mortality risk approaching that of thicker melanomas, while also distinguishing lower-risk patients who may be appropriate for less intensive follow-up. These findings support integrating DecisionDx-Melanoma with staging to inform more precise, risk-aligned management decisions for patients with CM.

Full abstract content will be available in the AAD online viewing portal and onsite at the viewing stations beginning at the start of the meeting. They will also be published online via the Journal of the American Academy of Dermatology (JAAD) supplement in Fall 2026. For more information regarding Castle's posters and its participation at AAD, please visit booth #3345.

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 more than 50 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 220,000 times since launch, and has been shown to be associated with improved patient survival. Learn more at www.CastleBiosciences.com.

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, 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: the ability of DecisionDx-Melanoma to (i) help clinicians more confidently escalate care for higher-risk patients while avoiding unnecessary interventions in those at lower risk of poor outcomes;(ii) identify patients at higher or lower risk than predicted by AJCC staging alone, including high-risk T1 (thin) tumors with mortality risk approaching that of thicker melanomas; and (iii) support more personalized management decisions by delivering a personalized risk assessment. The words "designed," "may", "can", and similar expressions are intended to identify forward 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 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 certain 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/castle-biosciences-decisiondx-melanoma-test-significantly-improves-risk-prediction-within-ajcc-stages-to-support-personalized-risk-aligned-management-of-cutaneous-melanoma-data-to-be-presented-at-aad-2026-302725368.html

SOURCE Castle Biosciences, Inc.

FAQ

What did Castle Biosciences (CSTL) report about DecisionDx-Melanoma at AAD 2026?

It reported that DecisionDx-Melanoma significantly stratifies five-year melanoma-specific survival within AJCC stages. According to Castle Biosciences, analysis of 1,868 SEER-linked patients (2013–2019) showed notable survival differences by test class within T categories and AJCC substages.

How did DecisionDx-Melanoma affect five-year survival for T1 tumors in the CSTL data?

The test showed a large survival difference for T1 tumors: 96.7% versus 70.0%. According to Castle Biosciences, Class 1A (low-risk) T1 patients had 96.7% five-year MSS versus 70.0% for Class 2B (high-risk) in the SEER-linked cohort.

What were the DecisionDx-Melanoma five-year MSS results for Stage IIB–III in the CSTL study?

Stage IIB–III patients showed five-year MSS of 87.4% for low-risk versus 48.5% for high-risk results. According to Castle Biosciences, this indicates substantial risk discrimination within the same AJCC stage in the 1,868-patient analysis.

How large and dated was the dataset Castle used for the DecisionDx-Melanoma AAD 2026 poster?

The dataset comprised 1,868 clinically tested patients linked to 22 SEER registries from 2013–2019. According to Castle Biosciences, inclusion required stage I–III CM testing and at least five years of follow-up or disease-specific death.

Will the full DecisionDx-Melanoma results from Castle (CSTL) be published and where?

Yes; the full abstract and poster will be available at AAD and published in JAAD supplement in Fall 2026. According to Castle Biosciences, the poster is ePoster 76747 and the full content will appear online and onsite at AAD viewing stations.