Neural network analysis as a novel skin outcome in a trial of belumosudil in patients with systemic sclerosis.

Journal: Arthritis research & therapy
PMID:

Abstract

BACKGROUND: The modified Rodnan skin score (mRSS), a measure of systemic sclerosis (SSc) skin thickness, is agnostic to inflammation and vasculopathy. Previously, we demonstrated the potential of neural network-based digital pathology applied to SSc skin biopsies as a quantitative outcome. Here, we leverage deep learning and histologic analyses of clinical trial biopsies to decipher SSc skin features 'seen' by artificial intelligence (AI).

Authors

  • Ilayda Gunes
    Department of Internal Medicine, Section of Rheumatology, Allergy & Immunology, Yale School of Medicine, New Haven, USA.
  • Elana J Bernstein
    Division of Rheumatology, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA. Electronic address: ejb2153@cumc.columbia.edu.
  • Shawn E Cowper
    Department of Dermatology, Yale University School of Medicine, New Haven, CT, USA.
  • Gauri Panse
    Departments of Dermatology and Pathology, Yale School of Medicine, New Haven, USA.
  • Niki Pradhan
    Department of Medicine, Division of Rheumatology, Columbia University Irving Medical Center, New York, USA.
  • Lucy Duran Camacho
    Department of Internal Medicine, Section of Rheumatology, Allergy & Immunology, Yale School of Medicine, New Haven, USA.
  • Nicolas Page
    Department of Internal Medicine, Section of Rheumatology, Allergy & Immunology, Yale School of Medicine, New Haven, USA.
  • Elizabeth Bundschuh
    Department of Internal Medicine, Section of Rheumatology, Allergy & Immunology, Yale School of Medicine, New Haven, USA.
  • Alyssa Williams
    Department of Internal Medicine, Section of Rheumatology, Allergy & Immunology, Yale School of Medicine, New Haven, USA.
  • Mary Carns
    Department of Medicine, Division of Rheumatology, Northwestern University Feinberg School of Medicine, Chicago, USA.
  • Kathleen Aren
    Department of Internal Medicine, Division of Rheumatology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA.
  • Sarah Fantus
    Department of Medicine, Division of Rheumatology, Northwestern University Feinberg School of Medicine, Chicago, USA.
  • Elizabeth R Volkmann
    David Geffen School of Medicine, Division of Rheumatology, University of California, los Angeles, Los Angeles, USA.
  • Heather Bukiri
    David Geffen School of Medicine, Division of Rheumatology, University of California, los Angeles, Los Angeles, USA.
  • Chase Correia
    Department of Internal Medicine, Division of Rheumatology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA.
  • Vijaya B Kolachalama
    1Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA 02118 USA.
  • F Perry Wilson
  • Seamus Mawe
    Vermont Complex Systems Center, The University of Vermont, Burlington, Vermont.
  • J Matthew Mahoney
    Department of Neurological Sciences, University of Vermont College of Medicine, Burlington, VT, United States of America.
  • Monique Hinchcliff
    Department of Internal Medicine, Division of Rheumatology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA. Monique.hinchcliff@yale.edu.