Unraveling Uncertainty: The Impact of Biological and Analytical Variation on the Prediction Uncertainty of Categorical Prediction Models.

Journal: The journal of applied laboratory medicine
PMID:

Abstract

BACKGROUND: Interest in prediction models, including machine learning (ML) models, based on laboratory data has increased tremendously. Uncertainty in laboratory measurements and predictions based on such data are inherently intertwined. This study developed a framework for assessing the impact of biological and analytical variation on the prediction uncertainty of categorical prediction models.

Authors

  • Remy J H Martens
    Department of Clinical Chemistry and Hematology, Zuyderland Medical Center, Sittard-Geleen, the Netherlands.
  • William P T M van Doorn
    CARIM School for Cardiovascular Diseases, Maastricht University, Maastricht, The Netherlands.
  • Mathie P G Leers
    Department of Clinical Chemistry and Hematology, Zuyderland Medical Center, Sittard-Geleen, the Netherlands.
  • Steven J R Meex
    CARIM School for Cardiovascular Diseases, Maastricht University, Maastricht, The Netherlands.
  • Floris Helmich
    Department of Clinical Chemistry and Hematology, Zuyderland Medical Center, Sittard-Geleen, the Netherlands.