Predictive Models for Outcomes With Immune Checkpoint Inhibitor Treatment in Metastatic Melanoma

Get Permission

In a study reported in the Journal of Clinical Oncology, Pires da Silva et al developed predictive models for objective response and progression-free and overall survival among patients receiving anti–PD-1 antibodies with or without ipilimumab for metastatic melanoma.

The analyses involved data from 1,644 patients treated with anti–PD-1 antibodies with or without ipilimumab at 16 centers in Australia, the United States, and Europe. The final models were developed in a discovery cohort of 633 patients; each model was validated internally and externally in two independent validation cohorts (validation 1 cohort, n = 419; validation 2 cohort, n = 592).

Key Findings

The final model for predicting objective response rate was based on Eastern Cooperative Oncology Group performance status, presence or absence of liver and lung metastases, serum lactate dehydrogenase, blood neutrophil-lymphocyte ratio, therapy (monotherapy or combination), and line of treatment. The model yielded a receiver operating characteristic area under the curve (AUC) of 0.71. C-statistics were 0.69 for internal validation and 0.67 and 0.67 for external validation in the validation 1 and validation 2 cohorts, respectively.

The final model for progression-free survival included all components of the objective response rate model except the presence or absence of lung metastases and included the additional variables of the  presence or absence of brain metastases and blood hemoglobin. The model yielded an AUC of 0.68. C-statistics were 0.67 for internal validation and 0.67  and 0.66 in the  validation 1 and validation 2 cohorts.

The final model for overall survival included the same components as the progression-free survival model. It yielded an AUC of 0.77. C-statistics were 0.76 for internal validation and 0.72 and 0.74 in the validation 1 and validation 2 cohorts.

Nomogram calculators were developed from the clinical models and are available at to predict outcomes for patients with metastatic melanoma treated with anti–PD-1 antibodies with or without ipilimumab.

The investigators concluded: “Newly developed combinations of routinely collected baseline clinical factors predict the response and survival outcomes of patients with metastatic melanoma treated with immunotherapy and may serve as valuable tools for clinical decision-making.”

Alexander M. Menzies, MD, PhD, of Melanoma Institute Australia, The University of Sydney, is the corresponding author of the Journal of Clinical Oncology article.

Disclosure: The study was supported by Melanoma Institute Australia and others. For full disclosures of the study authors, visit

The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.