Serum markers improve current prediction of metastasis development in early‐stage melanoma patients: a machine learning‐based study

Abstract

Metastasis development represents an important threat for melanoma patients, even when diagnosed at early stages and upon removal of the primary tumor. In this scenario, determination of prognostic biomarkers would be of great interest. Serum contains information about the general status of the organism and therefore represents a valuable source for biomarkers. Thus, we aimed to define serological biomarkers that could be used along with clinical and histopathological features of the disease to predict metastatic events on the early‐stage population of patients. We previously demonstrated that in stage II melanoma patients, serum levels of dermcidin (DCD) were associated with metastatic progression. Based on the relevance of the immune response on the cancer progression and the recent association of DCD with local and systemic immune response against cancer cells, serum DCD was analyzed in a new cohort of patients along with interleukin 4 (IL‐4), IL‐6, IL‐10, IL‐17A, interferon γ (IFN‐γ), transforming growth factor‐β (TGF‐ β), and granulocyte–macrophage colony‐stimulating factor (GM‐CSF). We initially recruited 448 melanoma patients, 323 of whom were diagnosed as stages I‐II according to AJCC. Levels of selected cytokines were determined by ELISA and Luminex, and obtained data were analyzed employing machine learning and Kaplan–Meier techniques to define an algorithm capable of accurately classifying early‐stage melanoma patients with a high and low risk of developing metastasis. The results show that in early‐stage melanoma patients, serum levels of the cytokines IL‐4, GM‐CSF, and DCD together with the Breslow thickness are those that best predict melanoma metastasis. Moreover, resulting algorithm represents a new tool to discriminate subjects with good prognosis from those with high risk for a future metastasis.

Investigating Serum and Tissue Expression Identified a Cytokine/Chemokine Signature as a Highly Effective Melanoma Marker

“…In other studies, SVM effectively discriminated melanoma on the basis of dermoscopic images [44], ultrasonic and spectrophotometric images [45], BRAF status [46], or dermo-fluorescence spectra [47], with a reported accuracy up to 90%. SVM was previously used for prognostic purposes in melanoma patients [48] but, to our knowledge, the present study is the first applying the SVM analysis to cytokine/chemokine-expression values to discriminate melanoma from controls, both in serum and in tissue, in a large group of controls and patients. The SVM procedure was indeed able to improve the ability to classify the serum samples, from AUC = 0.70 for IL-6 expression (see Table 2) up to AUC = 0.761 for the combined indicators (see Table 7).…”

Preclinical Development of Seriniquinones as Selective Dermcidin Modulators for the Treatment of Melanoma

“…Initial evidence reported by Porter et al revealed that the protein was overexpressed in 10% of invasive breast carcinomas and conferred cell growth and survival, launching dermcidin as a candidate oncogene [ 51 ]. Thereafter, several research groups reported additional evidence concerning this protein in various types of cancers, as illustrated in Figure 7 : Intracellular or extracellular overexpression of dermcidin in breast cancer [ 52 ], gastric cancer [ 53 , 54 ], hepatocellular carcinoma [ 55 , 56 ], lung cancer [ 57 , 58 ], melanoma [ 59 , 60 ], and pancreatic cancer [ 61 ]; promotion of cell survival [ 48 , 51 , 62 , 63 , 64 ]; and promotion of cell migration [ 55 , 65 ]. Although there are solid data that link dermcidin and cancer, the proper role of the protein at molecular levels and its contribution to tumorigenesis is still unclear.…”

A Positive Dermcidin Expression Is an Unfavorable Prognostic Marker for Extramammary Paget’s Disease

“…Dermcidin expression is higher in lung cancer patients compared with that in healthy subjects [26]. Among cutaneous malignancies, having high serum levels of dermcidin at the moment of melanoma diagnosis has been associated with the metastatic progression of melanoma among melanoma patients [27,28].…”