Clinically Guided Adaptive Machine Learning Update Strategies for Predicting Severe COVID-19 Outcomes.

Journal: The American journal of medicine
Published Date: Oct 17, 2024

Abstract

BACKGROUND: Machine learning algorithms are essential for predicting severe outcomes during public health crises like COVID-19. However, the dynamic nature of diseases requires continual evaluation and updating of these algorithms. This study aims to compare three update strategies for predicting severe COVID-19 outcomes postdiagnosis: "naive" (a single initial model), "frequent" (periodic retraining), and "context-driven" (retraining informed by clinical insights). The goal is to determine the most effective timing and approach for adapting algorithms to evolving disease dynamics and emerging data.

Authors

  • Mehmet Ulvi Saygi Ayvaci
    Information Systems, Naveen Jindal School of Management, The University of Texas at Dallas, Dallas.
  • Varghese S Jacobi
    Information Systems, Naveen Jindal School of Management, The University of Texas at Dallas, Dallas.
  • Young Ryu
    Information Systems, Naveen Jindal School of Management, The University of Texas at Dallas, Dallas.
  • Saikrishna Pannaga Srikar Gundreddy
    Computer Science, Eric Johnson School of Engineering, The University of Texas at Dallas, Richardson.
  • Bekir Tanriover
    Division of Nephrology, College of Medicine, The University of Arizona, Tucson. Electronic address: btanriover@arizona.edu.

Keywords

External Resources

Popular Topics
Recent Journals