Dataset Information

Integrating 31-Gene Expression Profiling With Clinicopathologic Features to Optimize Cutaneous Melanoma Sentinel Lymph Node Metastasis Prediction.

ABSTRACT: National guidelines recommend sentinel lymph node biopsy (SLNB) be offered to patients with > 10% likelihood of sentinel lymph node (SLN) positivity. On the other hand, guidelines do not recommend SLNB for patients with T1a tumors without high-risk features who have < 5% likelihood of a positive SLN. However, the decision to perform SLNB is less certain for patients with higher-risk T1 melanomas in which a positive node is expected 5%-10% of the time. We hypothesized that integrating clinicopathologic features with the 31-gene expression profile (31-GEP) score using advanced artificial intelligence techniques would provide more precise SLN risk prediction.

Methods

An integrated 31-GEP (i31-GEP) neural network algorithm incorporating clinicopathologic features with the continuous 31-GEP score was developed using a previously reported patient cohort (n = 1,398) and validated using an independent cohort (n = 1,674).

Results

Compared with other covariates in the i31-GEP, the continuous 31-GEP score had the largest likelihood ratio (G² = 91.3, P < .001) for predicting SLN positivity. The i31-GEP demonstrated high concordance between predicted and observed SLN positivity rates (linear regression slope = 0.999). The i31-GEP increased the percentage of patients with T1-T4 tumors predicted to have < 5% SLN-positive likelihood from 8.5% to 27.7% with a negative predictive value of 98%. Importantly, for patients with T1 tumors originally classified with a likelihood of SLN positivity of 5%-10%, the i31-GEP reclassified 63% of cases as having < 5% or > 10% likelihood of positive SLN, for a more precise, personalized, and clinically actionable SLN-positive likelihood estimate.

Conclusion

These data suggest the i31-GEP could reduce the number of SLNBs performed by identifying patients with likelihood under the 5% threshold for performance of SLNB and improve the yield of positive SLNBs by identifying patients more likely to have a positive SLNB.

SUBMITTER: Whitman ED

PROVIDER: S-EPMC8457832 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Sentinel lymph node, the first node draining the primary tumor, is a key component of tumor microenvironment promoting immune tolerance. In melanoma, sentinel node is one of the most important prognostic factors and the most frequent site of regional metastasis. To unravel the immunomodulatory pathways that are triggered by melanoma cells in the draining node that allow tumor spreading, transcriptional profiles associated to disease progression were analyzed in archival sentinel node biopsies (SNB). Gene expression profiles of melanoma-positive and negative SNB selected to maximize the differences in terms of disease stage and course, revealed subgroups correlating with regional node involvement and disease progression within positive biopsies. Transcriptional profiles revealed that genes showing differential expression between tumor-positive SNB with/without disease progression were mainly related to inflammatory response and that were mostly down regulated in patients with poor prognosis. TNFRSF8 encoding CD30 showing up regulation in SNB from patients with progressing disease displayed higher expression by immunohistochemical staining compared to SNB from non progressing patients. Subpopulations of CD30 positive CD4/CD8 double negative and CD4 Foxp3/PD-1 CD147 positive T cells were identified by flow cytometry analysis in metastatic nodes, suggesting a potential role of regulatory and tolerogenic T cells in melanoma progression. Cutaneous melanoma patients undergoing SNB biopsy in 2001-2004 with available 5M-bM-^@M-^Syear follow-up clinical data were selected. Data relative to 752 cases was extracted, 80% (n= 603) with a negative SNB and 20% (n=149) with SNB positivity for melanoma metastases. The latter underwent regional lymphadenectomy by CLND and 30% (n=44) resulted positive for melanoma metastases at non-sentinel regional lymph nodes while 70% (n=105) resulted negative. Analysis of follow-up data showed that disease recurrence at 5 yrs occurred in 9% SNB negative patients, 14% of the patients with positive SNB resulting negative at CLND, and in 57% of the patients with positive SNB resulting positive at CLND, consistent to the range of previously reported rates (Santinami M 2009, Balch CM 2009). In order to exploit gene expression profiles to unravel molecular modifications occurring in SNB from patients with progressing disease we selected two groups of cases representing the extremes of the survey, i.e. patients positive at CLND (stage IIIB-C) recurring within 5 years follow-up (SNB-PP), and patients negative at CLND (stage IIIA-B) and non-relapsing at 5 years (SNB-PN). In addition, a group of negative SNB patients without disease recurrence at 5 years was selected and analysed for comparison as tumor negative SNB (SNB-N).