Skip to Main Content

Rimm Lab Validates Objective Prognostic Marker in Patients With Early-stage Melanoma

July 22, 2022

A recent study from the Rimm Lab in the Department of Pathology at Yale School of Medicine has shown that an objective assessment of automated electronic tumor infiltrating lymphocytes percentage (eTILs%) scores is a strong prognostic marker in patients with early-stage melanoma. The study also identified distinct TIL subpopulations that carry the prognostic values.

Thazin Nwe Aung, PhD, postdoctoral associate in the Rimm Lab and lead author of this study, also found that, pending prospective validation, the use of the NN192 machine learning algorithm might evolve into a useful and easy-to-implement tool that will aid in risk stratification for patients with early-stage melanoma. The NN192 calculates the percentage of machine-defined TIL.

The study was published in eBioMedicine. Several Rimm Lab members are among the authors, including corresponding author David Rimm, MD, PhD, Anthony N. Brady Professor of Pathology and professor of medicine (medical oncology), Aileen Fernandez, PhD, Vesal Yaghoobi, MD, MSc, and Yalai Bai, MD, PhD.

The study evaluated the prognostic value of eTILs% quantification to define a subset of melanoma patients with a low risk of relapse after surgery. The study analyzed data from 785 patients from five independent cohorts from multiple institutions to validate their previous finding that an automated TIL score is prognostic for clinically localized primary melanoma patients. Using serial tissue sections of the Yale melanoma cohort, both immunofluorescence and Hematoxylin-and-Eosin (H&E) staining were performed to understand the molecular characteristics of each TIL phenotype and their associations with survival outcomes.

The authors noted that eTILs % scores and electronic total TILs percentage scores (etTILs%) are robust prognostic markers in patients with primary melanoma and may identify a subgroup of Stage II patients at high-risk of recurrence who may benefit from adjuvant therapy. Previously, the prognostic value of TILs assessed by machine learning algorithms in patients with melanoma has been demonstrated but has not been widely adopted.

“In the future, the use of eTILs% might be complemented with molecular subtyping of cells for more discriminating analyses. The use of a combined marker signature may be proven to be the best approach to define a subset of patients that will not benefit from immunotherapy or might develop significant toxicities,” the study concluded.

Data from the study also supports the need for testing of the algorithm in a clinical trial.

Submitted by Terence P. Corcoran on July 22, 2022