Privacy preserving distributed learning classifiers - Sequential learning with small sets of data.

Journal: Computers in biology and medicine
Published Date: Jul 31, 2021

Abstract

BACKGROUND: Artificial intelligence (AI) typically requires a significant amount of high-quality data to build reliable models, where gathering enough data within a single institution can be particularly challenging. In this study we investigated the impact of using sequential learning to exploit very small, siloed sets of clinical and imaging data to train AI models. Furthermore, we evaluated the capacity of such models to achieve equivalent performance when compared to models trained with the same data over a single centralized database.

Authors

  • Fadila Zerka
    The D-Lab & The M-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands.
  • Visara Urovi
    Institute of Data Science (IDS), Maastricht University, the Netherlands.
  • Fabio Bottari
    Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Ralph T H Leijenaar
    The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, The Netherlands.
  • Seán Walsh
    Department of Radiation Oncology (MAASTRO Clinic), Dr. Tanslaan 12, Maastricht, The Netherlands.
  • Hanif Gabrani-Juma
    Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Martin Gueuning
    Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Akshayaa Vaidyanathan
    The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, The Netherlands. akshayaa.vaidyanathan@oncoradiomics.com.
  • Wim Vos
    FLUIDDA nv, Kontich, Belgium.
  • Mariaelena Occhipinti
    Dept of Biomedical, Clinical and Experimental Sciences "Mario Serio", University of Florence, Florence, Italy.
  • Henry C Woodruff
    The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, The Netherlands.
  • Michel Dumontier
    Stanford University, Stanford, CA USA.
  • Philippe Lambin
    Department of Radiation Oncology (MAASTRO Clinic), Dr. Tanslaan 12, Maastricht, The Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals