AutoScore-Imbalance: An interpretable machine learning tool for development of clinical scores with rare events data.

Journal: Journal of biomedical informatics
Published Date:

Abstract

BACKGROUND: Medical decision-making impacts both individual and public health. Clinical scores are commonly used among various decision-making models to determine the degree of disease deterioration at the bedside. AutoScore was proposed as a useful clinical score generator based on machine learning and a generalized linear model. However, its current framework still leaves room for improvement when addressing unbalanced data of rare events.

Authors

  • Han Yuan
    Computational and Systems Biology Program, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
  • Feng Xie
    School of Computer Science, Guangdong University of Technology, Guangzhou, China. Electronic address: 1111705006@mail2.gdut.edu.cn.
  • Marcus Eng Hock Ong
    Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore. marcus.ong.e.h@sgh.com.sg.
  • Yilin Ning
    Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore.
  • Marcel Lucas Chee
    Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia.
  • Seyed Ehsan Saffari
    Duke-NUS Medical School, National University of Singapore, Singapore.
  • Hairil Rizal Abdullah
    Department of Anesthesiology, Singapore General Hospital, Singapore, Singapore.
  • Benjamin Alan Goldstein
    Programme in Health Services and Systems Research, Duke-National University of Singapore Medical School, Singapore.
  • Bibhas Chakraborty
    Programme in Health Services and Systems Research, Duke-National University of Singapore Medical School, Singapore.
  • Nan Liu
    Duke-NUS Medical School Centre for Quantitative Medicine Singapore Singapore.