Healthcare pathway discovery and probabilistic machine learning.

Journal: International journal of medical informatics
Published Date:

Abstract

BACKGROUND AND PURPOSE: Healthcare pathways define the execution sequence of clinical activities as patients move through a treatment process, and they are critical for maintaining quality of care. The aim of this study is to combine healthcare pathway discovery with predictive models of individualized recovery times. The pathway discovery has a particular emphasis on producing pathway models that are easy to interpret for clinicians without a sufficient background in process mining. The predictive model takes the stochastic volatility of pathway performance indicators into account.

Authors

  • Andreas W Kempa-Liehr
    Department of Engineering Science, The University of Auckland, 70 Symonds St, Auckland, New Zealand. Electronic address: a.kempa-liehr@auckland.ac.nz.
  • Christina Yin-Chieh Lin
    Department of Engineering Science, The University of Auckland, 70 Symonds St, Auckland, New Zealand.
  • Randall Britten
    Auckland District Health Board, 2 Park Road, Auckland, New Zealand; was at Orion Health, 181 Grafton Rd, Auckland, New Zealand.
  • Delwyn Armstrong
  • Jonathan Wallace
    Waitemata District Health Board, 124 Shakespeare Rd, Auckland, New Zealand.
  • Dylan Mordaunt
    University of Adelaide and Flinders University, Adelaide, Australia; was at Waitemata District Health Board, 124 Shakespeare Rd, Auckland, New Zealand.
  • Michael O'Sullivan
    Department of Engineering Science, The University of Auckland, 70 Symonds St, Auckland, New Zealand.