Predicting Mutations in Cutaneous Melanoma Patients Using Neural Network Analysis

Overview

Journal J Skin Cancer

Publisher Wiley

Specialty Dermatology

Date 2024 Dec 30

PMID 39735251

Authors

Oleksandr Dudin

Ozar Mintser

Vitalii Gurianov

Nazarii Kobyliak

Dmytro Kaminskyi

Alina Matvieieva

Roman Shabalkov

Artem Mashukov

Oksana Sulaieva

Affiliations

Soon will be listed here.

Abstract

Point mutations at codon 600 of the BRAF oncogene are the most common alterations in cutaneous melanoma (CM). Assessment of BRAF status allows to personalize patient management, though the affordability of molecular testing is limited in some countries. This study aimed to develop a model for predicting alteration in BRAF based on routinely available clinical and histological data. For identifying the key factors associated with point mutations in BRAF, 2041 patients with CM were recruited in the study. The presence of BRAF mutations was an endpoint. The variables included demographic data (gender and age), anatomic location, stage, histological subtype, number of mitosis, and also such features as ulceration, Clark level, Breslow thickness, infiltration by lymphocytes, invasiveness, regression, microsatellites, and association with nevi. A relatively high rate of BRAF mutation was revealed in the Ukrainian cohort of patients with CM. BRAF-mutant melanoma was associated with younger age and location of nonsun-exposed skin. Besides, sex-specific differences were found between CM of various anatomic distributions and the frequency of distinct BRAF mutation subtypes. A minimal set of variables linked to BRAF mutations, defined by the genetic input selection algorithm, included patient age, primary tumor location, histological type, lymphovascular invasion, ulceration, and association with nevi. To encounter nonlinear links, neural network modeling was applied resulting in a multilayer perceptron (MLP) with one hidden layer. Its architecture included four neurons with a logistic activation function. The AUROCMLP6 of the MLP model comprised 0.79 (95% CІ: 0.74-0.84). Under the optimal threshold, the model demonstrated the following parameters: sensitivity: 89.4% (95% CІ: 84.5%-93.1%), specificity: 50.7% (95% CІ: 42.2%-59.1%), positive predictive value: 73.1% (95% CІ: 69.6%-76.3%), and negative predictive value: 76.0% (95% CІ: 67.6%-82.8%). The developed MLP model enables the prediction of the mutation in BRAF oncogene in CM, alleviating decisions on personalized management of patients with CM. In conclusion, the developed MLP model, which relies on the assessment of 6 variables, can predict the mutation status in patients with CM, supporting decisions on patient management.

References

van der Kooij M, Wetzels M, Aarts M, van den Berkmortel F, Blank C, Boers-Sonderen M . Age Does Matter in Adolescents and Young Adults versus Older Adults with Advanced Melanoma; A National Cohort Study Comparing Tumor Characteristics, Treatment Pattern, Toxicity and Response. Cancers (Basel). 2020; 12(8). PMC: 7464956. DOI: 10.3390/cancers12082072. View

Michaloglou C, Vredeveld L, Soengas M, Denoyelle C, Kuilman T, van der Horst C . BRAFE600-associated senescence-like cell cycle arrest of human naevi. Nature. 2005; 436(7051):720-4. DOI: 10.1038/nature03890. View

Yang T, Yu S, Ke C, Cheng S . The Genomic Landscape of Melanoma and Its Therapeutic Implications. Genes (Basel). 2023; 14(5). PMC: 10218388. DOI: 10.3390/genes14051021. View

Lokhandwala P, Tseng L, Rodriguez E, Zheng G, Pallavajjalla A, Gocke C . Clinical mutational profiling and categorization of BRAF mutations in melanomas using next generation sequencing. BMC Cancer. 2019; 19(1):665. PMC: 6612071. DOI: 10.1186/s12885-019-5864-1. View

Bauer J, Buttner P, Murali R, Okamoto I, Kolaitis N, Landi M . BRAF mutations in cutaneous melanoma are independently associated with age, anatomic site of the primary tumor, and the degree of solar elastosis at the primary tumor site. Pigment Cell Melanoma Res. 2011; 24(2):345-51. PMC: 3107974. DOI: 10.1111/j.1755-148X.2011.00837.x. View

Wiggins J, Polsky D . Melanoma origins: data from early-stage tumours supports de novo and naevus-associated melanomas as distinct subtypes. Br J Dermatol. 2021; 185(1):9-10. DOI: 10.1111/bjd.20396. View

Yeh I, von Deimling A, Bastian B . Clonal BRAF mutations in melanocytic nevi and initiating role of BRAF in melanocytic neoplasia. J Natl Cancer Inst. 2013; 105(12):917-9. PMC: 3687371. DOI: 10.1093/jnci/djt119. View

van der Kooij M, Dekkers O, Aarts M, van den Berkmortel F, Boers-Sonderen M, de Groot J . Sex-Based Differences in Treatment with Immune Checkpoint Inhibition and Targeted Therapy for Advanced Melanoma: A Nationwide Cohort Study. Cancers (Basel). 2021; 13(18). PMC: 8465427. DOI: 10.3390/cancers13184639. View

Sung W, Chang C . Nevi, dysplastic nevi, and melanoma: Molecular and immune mechanisms involving the progression. Tzu Chi Med J. 2022; 34(1):1-7. PMC: 8830542. DOI: 10.4103/tcmj.tcmj_158_20. View

10.

Colombino M, Rozzo C, Paliogiannis P, Casula M, Manca A, Doneddu V . Comparison of Mutation Screening Strategies in a Large Real-Life Series of Advanced Melanoma Patients. J Clin Med. 2020; 9(8). PMC: 7464760. DOI: 10.3390/jcm9082430. View

11.

Figueroa-Silva O, Pastur Romay L, Viruez Roca R, Rojas M, Suarez-Penaranda J . Machine Learning Techniques in Predicting BRAF Mutation Status in Cutaneous Melanoma From Clinical and Histopathologic Features. Appl Immunohistochem Mol Morphol. 2022; 30(10):674-680. DOI: 10.1097/PAI.0000000000001075. View

12.

Shreberk-Hassidim R, Ostrowski S, Fisher D . The Complex Interplay between Nevi and Melanoma: Risk Factors and Precursors. Int J Mol Sci. 2023; 24(4). PMC: 9964821. DOI: 10.3390/ijms24043541. View

13.

Poynter J, Elder J, Fullen D, Nair R, Soengas M, Johnson T . BRAF and NRAS mutations in melanoma and melanocytic nevi. Melanoma Res. 2006; 16(4):267-73. DOI: 10.1097/01.cmr.0000222600.73179.f3. View

14.

Menzies A, Haydu L, Visintin L, Carlino M, Howle J, Thompson J . Distinguishing clinicopathologic features of patients with V600E and V600K BRAF-mutant metastatic melanoma. Clin Cancer Res. 2012; 18(12):3242-9. DOI: 10.1158/1078-0432.CCR-12-0052. View

15.

Jackett L, Scolyer R . A Review of Key Biological and Molecular Events Underpinning Transformation of Melanocytes to Primary and Metastatic Melanoma. Cancers (Basel). 2019; 11(12). PMC: 6966527. DOI: 10.3390/cancers11122041. View

16.

Hajdarevic S, Schmitt-Egenolf M, Brulin C, Sundbom E, Hornsten A . Malignant melanoma: gender patterns in care seeking for suspect marks. J Clin Nurs. 2011; 20(17-18):2676-84. DOI: 10.1111/j.1365-2702.2011.03788.x. View

17.

Gonzalez D, Fearfield L, Nathan P, Taniere P, Wallace A, Brown E . BRAF mutation testing algorithm for vemurafenib treatment in melanoma: recommendations from an expert panel. Br J Dermatol. 2013; 168(4):700-7. DOI: 10.1111/bjd.12248. View

18.

Nurdjaja V, Yozu M, Mathy J . Essential Components of Melanoma Histopathological Reporting: The Surgical Oncologist's Perspective. J Skin Cancer. 2018; 2018:9838410. PMC: 5954935. DOI: 10.1155/2018/9838410. View

19.

Kim S, Kim S, Hahn H, Lee Y, Choe Y, Ahn K . Metaanalysis of BRAF mutations and clinicopathologic characteristics in primary melanoma. J Am Acad Dermatol. 2015; 72(6):1036-46.e2. DOI: 10.1016/j.jaad.2015.02.1113. View

20.

Eigentler T, Assi Z, Hassel J, Heinzerling L, Starz H, Berneburg M . Which melanoma patient carries a BRAF-mutation? A comparison of predictive models. Oncotarget. 2016; 7(24):36130-36137. PMC: 5094988. DOI: 10.18632/oncotarget.9143. View