Castle Biosciences’ Study on DecisionDx-Melanoma Tool Demonstrates Ability to Predict Which Patients Should Receive Sentinel Node Biopsy

Cutaneous melanoma (CM), a potentially lethal skin cancer, often poses a challenge for healthcare professionals when determining the necessity of sentinel lymph node biopsy (SLNB) in patients. If melanoma has metastasized to the lymph nodes, it requires surgical removal of the lymph nodes and much more significant therapy where localized melanoma is typically treated simply by resection. Castle Biosciences, Inc. (Nasdaq: CSTL), a personalized medicine company has announced new research showcasing the superiority of its DecisionDx®-Melanoma test over a predictive tool developed at the Memorial Sloan Kettering Cancer Center (MSKCC) in assessing the risk of sentinel lymph node (SLN) positivity in CM patients. The study is now available online in Anticancer Research.

Dr. Michael Tassavor, a board-certified dermatologist and fellowship-trained Mohs surgeon, and one of the study’s authors, highlighted the significance of this research, stating, “Nearly 90% of patients receive a negative result after undergoing the sentinel lymph node biopsy (SLNB) procedure, indicating there is a significant need for more precise methods to identify which patients can safely forego the surgery and still experience good outcomes.” DecisionDx-Melanoma, he emphasized, has the potential to address this need by providing accurate predictions of a patient’s risk of positive SLN, thereby facilitating informed discussions between clinicians and patients and instilling confidence in decisions to avoid surgery when the patient’s risk is low. While the medical risks around sentinel node biopsy are low, it is a painful invasive procedure for patients to undergo. Additionally, given the low positive rate, sentinel node biopsy represents a significant cost to the healthcare system. A study published in Surgery found the average cost of a sentinel node biopsy procedure was between $10,096 to $15,223 and the study questioned the appropriateness of SLDBs for patients with thin melanomas.

The study evaluated the performance of two tools in assessing patients at low and high risk of SLN positivity. The first was the DecisionDx-Melanoma Test which employs advanced algorithms to integrate a patient’s clinical and pathologic factors with tumor biology including 31 gene expression targets, and offers a personalized risk prediction for SLN positivity, melanoma recurrence, and metastasis. The second was the MSKCC Nomogram a predictive tool developed by the Memorial Sloan Kettering Cancer Center, this tool uses logistic regression and relies solely on clinical and pathologic factors to predict the risk of SLN positivity. The study analyzed 465 patients with T1-T2 tumors who had previously undergone SLNB. The analysis involved the application of both DecisionDx-Melanoma and the MSKCC nomogram. The National Comprehensive Cancer Network (NCCN) guidelines were used as a reference, and a risk prediction of less than 5% indicated low risk for SLN positivity, enabling patients to safely avoid SLNB. The true-to-false-negative ratio was evaluated based on this 5% risk threshold.

The DecisionDx-Melanoma test yielded a true-to-false-negative ratio of 36:1 (108/3). This means that for every 100 patients who opted out of SLNB based on the test’s results, only 2.7 would have had a positive SLN. This ratio comfortably falls below the 5% low-risk threshold set by NCCN. In contrast, the MSKCC nomogram resulted in a 9:1 true-to-false-negative ratio, indicating that for every 100 patients avoiding SLNB using the nomogram, 10 would have had a positive SLN. DecisionDx-Melanoma also demonstrated superior accuracy in predicting SLN positivity, with higher sensitivity (95% vs. 81%) and negative predictive value (97% vs. 90%) than the MSKCC nomogram. The study holds particular significance for patients with T1 tumors, where the decision to perform SLNB is less clear. In such cases, utilizing the DecisionDx-Melanoma test could have reduced the number of SLNBs by 43.7% compared to standard NCCN guidance while maintaining a low false-negative rate.

DecisionDx-Melanoma has already been validated to identify patients with less than a 5% risk of a positive SLN, suggesting that these patients may safely consider avoiding SLNB. The study’s results not only reinforce this validation but also underscore that DecisionDx-Melanoma surpasses the MSKCC nomogram in identifying low-risk SLN positivity patients.