A Machine-Learning Approach to Identify a Prognostic Cytokine Signature That Is Associated With Nivolumab Clearance in Patients With Advanced Melanoma.

Journal: Clinical pharmacology and therapeutics
PMID:

Abstract

Lower clearance of immune checkpoint inhibitors is a predictor of improved overall survival (OS) in patients with advanced cancer. We investigated a novel approach using machine learning to identify a baseline composite cytokine signature via clearance, which, in turn, could be associated with OS in advanced melanoma. Peripheral nivolumab clearance and cytokine data from patients treated with nivolumab in two phase III studies (n = 468 (pooled)) and another phase III study (n = 158) were used for machine-learning model development and validation, respectively. Random forest (Boruta) algorithm was used for feature selection and classification of nivolumab clearance. The 16 top-ranking baseline inflammatory cytokines reflecting immune-cell modulation were selected as a composite signature to predict nivolumab clearance (area under the curve (AUC) = 0.75; accuracy = 0.7). Predicted clearance (high vs. low) via the cytokine signature was significantly associated with OS across all three studies (P < 0.01), regardless of treatment (nivolumab vs. chemotherapy).

Authors

  • Rui Wang
    Department of Clinical Laboratory Medicine Center, Inner Mongolia Autonomous Region People's Hospital, Hohhot, Inner Mongolia, China.
  • Xiao Shao
    Oncology Translational Medicine, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Junying Zheng
    Oncology Translational Medicine, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Abdel Saci
    Oncology Translational Medicine, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Xiaozhong Qian
    Oncology Translational Medicine, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Irene Pak
    Information and Data Management, Bristol-Myers Squibb, New Brunswick, New Jersey, USA.
  • Amit Roy
    Clinical Pharmacology and Pharmacometrics, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Akintunde Bello
    Clinical Pharmacology and Pharmacometrics, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Jasmine I Rizzo
    Global Clinical Research, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Fareeda Hosein
    Global Clinical Research, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Rebecca A Moss
    Global Clinical Research, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Megan Wind-Rotolo
    Oncology Translational Medicine, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.
  • Yan Feng
    Clinical Pharmacology and Pharmacometrics, Bristol-Myers Squibb, Lawrenceville, New Jersey, USA.