Risk prediction in cutaneous melanoma patients from their clinico-pathological features: superiority of clinical data over gene expression data

Abstract

Risk assessment in cutaneous melanoma (CM) patients is one of the major challenges in the effective treatment of CM patients. Traditionally, clinico-pathological features such as Breslow thickness, American Joint Committee on Cancer (AJCC) tumor staging, etc. are utilized for this purpose. However, due to advancements in technology, most of the upcoming risk prediction methods are gene-expression profile (GEP) based. In this study, we have tried to develop new GEP and clinico-pathological features-based biomarkers and assessed their prognostic strength in contrast to existing prognostic methods. We developed risk prediction models using the expression of the genes associated with different cancer-related pathways and got a maximum hazard ratio (HR) of 2.52 with p-value ~10^-8 for the apoptotic pathway. Another model, based on combination of apoptotic and notch pathway genes boosted the HR to 2.57. Next, we developed models based on individual clinical features and got a maximum HR of 2.45 with p-value ~10^-6 for Breslow thickness. We also developed models using the best features of clinical as well as gene-expression data and obtained a maximum HR of 3.19 with p-value ~10^-9. Finally, we developed a new ensemble method using clinical variables only and got a maximum HR of 6.40 with p-value ~10^-15. Based on this method, a web-based service and an android application named 'CMcrpred' is available at (https://webs.iiitd.edu.in/raghava/cmcrpred/) and Google Play Store respectively to facilitate scientific community. This study reveals that our new ensemble method based on only clinico-pathological features overperforms methods based on GEP based profiles as well as currently used AJCC staging. It also highlights the need to explore the full potential of clinical variables for prognostication of cancer patients.

Keywords: Bioinformatics; Cancer; Cancer research; Genetics; Melanoma; Oncology; Prognosis; Risk prediction; Skin; Survival analysis.

Figure 1

Kaplan Meier plot for risk stratification of CM patients. (a) Based on prognostic index of apoptotic genes. Based on GPM gene set, patients with PI ≥ median (PI) are at a greater risk than patients with PI < median (PI) with HR = 2.52 and p-val = 3 × 10⁻⁸. (b) Based on prognostic index of apoptotic GPM and NOTCH combined genes. Patients with PI ≥ median (PI) are at a greater risk than patients with PI < median (PI) with HR = 2.57 and p-val = 1.5 × 10⁻⁸.

Figure 2

CM patients were stratified based on the predicted survival time (pred OS) by the 52 BPM based SVR model. Patients with pred OS ≤ median (pred OS) are at higher risk than the patients with pred OS > median (pred OS).

Figure 3

Kaplan Meier plots for risk stratification of CM patients based on SVR model with combination of 52 BPM and Breslow thickness as features. Patients with Pred OS $\le$ median (Pred OS) are at a greater risk than patients with Pred OS > median (Pred OS) with HR = 3.19 and p-val = 8.9 × 10⁻¹⁰.

Figure 4

Kaplan Meier plot for risk stratification of CM patients based on Risk Grade (RG). Patients with RG > 1 are at a greater risk than patients with RG ≤ 1 with HR = 6.40 and p-val = 2.49 × 10⁻¹⁵.

Figure 5

Boxplot representing the distinct segregation of risk groups by RG on the basis of 5- and 10- year survival outcomes predicted by “AJCC individualised melanoma patients outcome prediction tool”. A total of 162 predictions were made using the tool out of which 116 were low-risk patients (RG<=1) and 46 were high-risk (RG > 1).