System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Epublish

PubMed: 40890392 DOI: 10.1038/s41746-025-01962-y

Deep hierarchical subtyping of multi-organ systemic sclerosis trajectories - a EUSTAR study.

NPJ Digit Med 8(1):563

Authors: Cécile Trottet, Manuel Schürch, Ahmed Allam, Liubov Petelytska, Ivan Castellví, Radim Bečvář, Jeska de Vries-Bouwstra, Florenzo Iannone, Patricia Carreira, Marie-Elise Truchetet, Giovanna Cuomo, Elena Rezus, Francesco Paolo Cantatore, Carmen Pilar Simeón-Aznar, Magda Parvu, Marta Dzhus, Oliver Distler, Anna-Maria Hoffmann-Vold, Michael Krauthammer

Affiliations

  • Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland.
  • ETH AI Center, Zurich, Switzerland.
  • Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
  • Department of Data Science, Dana-Farber Cancer Institute, Boston, MA, USA.
  • Department of Rheumatology, University Hospital Zurich, University of Zurich, Zurich, Switzerland.
  • Department of Internal Medicine #3, Bogomolets National Medical University, Kyiv, Ukraine.
  • Department of Rheumatology, Hospital de la Santa Creu i Sant Pau, Barcelona, Spain.
  • Institute of Rheumatology, Department of Rheumatology, 1st Medical School, Charles University, Prague, Czech Republic.
  • Leiden University Medical Center, Department of Rheumatology, Leiden, The Netherlands.
  • Rheumatology DiMePReJ, University of Bari, School of Medicine, Bari, Italy.
  • Hospital Universitario 12 de Octubre, Rheumatology Department, Madrid, Spain.
  • CHU de Bordeaux, Rheumatology Department, Bordeaux, France.
  • Università della Campania, UOC Medicina Interna, Napoli, Italy.
  • "Grigore T Popa" University of Medicine and Pharmacy, Rehabilitation Hospital, Department of Rheumatology, Iasi, Romania.
  • University of Foggia, Department of Medical and Surgical Sciences, Rheumatology Unit, Foggia, Italy.
  • Hospital Universitario Vall d'Hebron, Department of Internal Medicine, Systemic Autoimmune Diseases Unit, Barcelona, Spain.
  • Colentina Clinical Hospital, Rheumatology Department, Bucharest, Romania.
  • Bogomolets National Medical University, Kyiv, Ukraine.
  • Department of Rheumatology, Oslo University Hospital, Oslo, Norway.
  • Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland.
  • ETH AI Center, Zurich, Switzerland.

Abstract

Systemic sclerosis (SSc) is a chronic autoimmune disease with multi-organ involvement. Historically, SSc classification has focused on the type of skin involvement (limited versus diffuse); however, a growing evidence of organ-specific variability suggests the presence of more than two distinct subtypes. We propose a semi-supervised generative deep learning framework leveraging expert-driven definitions of organ-specific involvement and severity. We model SSc disease trajectories in the European Scleroderma Trials and Research (EUSTAR) database, containing 14,000 patients across 67,000 medical visits, and identify clinically meaningful subtypes to enhance patient stratification and prognosis. We systematically evaluate the model's predictive accuracy, robustness to missing data, and clinical interpretability. We identified five patient clusters, separating patients based on the degree of organ involvement. Notably, a subset with limited skin involvement still showed high risks of lung and heart complications, underscoring the importance of data-driven methods and multi-organ models to complement established insights from clinical practice.

MeSH

Skin, Sclerosis, Multiple Chronic Conditions, Scleroderma, Systemic