Nomogram for predicting survival after first-line anti-PD-1-based immunotherapy in unresectable stage IV melanoma: a multicenter international study

Abstract

Background: The introduction of anti-programmed cell death protein 1 (PD-1) immunotherapy has revolutionized the treatment landscape for melanoma, enhancing both response rates and survival outcomes in patients with advanced stages of the disease. Despite these remarkable advances, a noteworthy subset of patients (40%-60%) does not derive advantage from this therapeutic approach. This study aims to identify key predictive factors and create a user-friendly predictive nomogram for stage IV melanoma patients receiving first-line anti-PD-1-based immunotherapy, improving treatment decisions.

Materials and methods: In this retrospective study, we included patients with unresectable stage IV melanoma who received first-line treatment with either anti-PD-1 monotherapy or anti-PD-1 plus anti-cytotoxic T-lymphocyte associated protein 4 between 2014 and 2018. We documented clinicopathological features and blood markers upon therapy initiation. By employing the random survival forest model and backward variable selection of the Cox model, we identified variables associated with progression-free survival (PFS) after the first-line anti-PD-1-based treatment. We developed and validated a predictive nomogram for PFS utilizing the identified variables. We assessed calibration and discrimination performance metrics as part of the evaluation process.

Results: The study involved 719 patients, divided into a training cohort of 405 (56%) patients and a validation cohort of 314 (44%) patients. We combined findings from the random survival forest and the Cox model to create a nomogram that incorporates the following factors: lactate dehydrogenase (LDH), S100, melanoma subtype, neutrophil-to-lymphocyte ratio (NLR), body mass index, type of immune checkpoint inhibitor, and presence of liver or brain metastasis. The resultant model had a C-index of 0.67 in the training cohort and 0.66 in the validation cohort. Performance remained in different patient subgroups. Calibration analysis revealed a favorable correlation between predicted and actual PFS rates.

Conclusions: We developed and validated a predictive nomogram for long-term PFS in patients with unresectable stage IV melanoma undergoing first-line anti-PD-1-based immunotherapy.

Keywords: anti-PD-1-based immunotherapy; biomarkers; immune checkpoint inhibition; nomogram; progression-free survival; stage IV melanoma.

Graphical abstract

Figure 1

Plot showing the results of the random survival forest. The x-axis shows the variable importance of each variable. The variables with positive variable importance are depicted in green, while the ones with negative variable importance (vimp) are depicted in burgundy. BMI, body mass index; ICI, immune checkpoint inhibitors; LDH, lactate dehydrogenase; NLR, neutrophil-to-lymphocyte ratio.

Figure 2

The nomogram and score creation. (A) Plot showing the nomogram that was built using the selected eight variables. The nomogram combines these eight clinicopathologic features to predict the PFS of stage IV melanoma patients after first-line anti-PD-1-based therapy. (B) Plots showing the relationship between the total points of the nomogram (score) and the PFS probability at 1, 2, 3, and 5 years after therapy initiation in the training cohort. BMI, body mass index; ICI, immune checkpoint inhibitors; LDH, lactate dehydrogenase; NLR, neutrophil-to-lymphocyte ratio; PD-1, programmed cell death protein 1; PFS, progression-free survival.

Figure 3

The score derived from the nomogram and the survival outcomes. (A) Plots that show the distribution of the score in the patients in the two cohorts. Green represents the patients who did develop progression after anti-PD-1-based therapy and burgundy dots represent patients who did not progress. (B) Plot showing the distribution, the median, the lower, and the upper quartile of the total points, calculated using the nomogram among patients in the two cohorts. Using the quartiles of the training cohort, three groups were created. (C) Kaplan–Meier curves showing the PFS of the three groups that were created using the quartiles of the total points in the training cohort in the training (left) and validation (right) cohorts. (D) Plot showing the MSS of the three groups defined by the total points of the nomogram in the training cohort for the training (left) and validation (right) cohorts. MSS. melanoma-specific survival; PD-1, programmed cell death protein 1; PFS, progression-free survival.

Figure 4

Performance metrics plots regarding progression-free survival and its clinical application. (A) Calibration curves of the model in the training (left) and validation (right) cohort. (B) Brier score in relation to time in months after therapy start for the training (left) and validation (right) cohort. (C) Decision curve analysis depicting the net clinical benefit of the model in the training (left) and validation (right) cohort. PFS, progression-free survival.

Figure 5

Performance metrics to predict risk of progression. (A) Area of the receiver operating characteristic curve (AU-ROC) in relation to time in months after therapy start for the training (left) and validation (right) cohorts. (B) ROC curves. (C) Precision and recall curves.