Matching patients and healthcare service providers : a novel two-stage method based on knowledge rules and OWA-NSGA-II algorithm

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

15 Scopus Citations
View graph of relations

Author(s)

  • Xi Chen
  • Liu Zhao
  • Haiming Liang
  • Kin Keung Lai

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)221–247
Journal / PublicationJournal of Combinatorial Optimization
Volume37
Issue number1
Online published12 Dec 2017
Publication statusPublished - Jan 2019

Abstract

The matching between patients and healthcare service providers is an important issue in healthcare. Searching an appropriate matching for both patients and healthcare service providers can not only facilitate efficiency of diagnosis and treatment, but also make both of them more satisfied with the matching results. This paper proposes a two-stage method for searching the optimal matching between the patients and healthcare service providers. In the first stage, where a large number of patients are involved in the matching problem, the knowledge rules are proposed to classify the patients with similar categories of disease into the same group. In the second stage, patients in each group are compared in terms of aspiration levels and the evaluation levels of the healthcare service providers, and satisfaction degrees of patients are calculated. Then, a multi-objective optimization model is built by maximizing the satisfaction degrees of patients, maximizing the number of treated patients and balancing the workload of healthcare service providers. To solve this model, the ordinal weighting average non-dominated sorting genetic algorithm II (OWA-NSGA-II) is developed. Furthermore, a practical example of service in rehabilitation therapy is used to illustrate the feasibility of the proposed method. Additionally, several simulation experiments in different large scale problems are conducted to test the performance of OWA-NSGA-II. Simulation results show that the proposed NSGA-II algorithm has better convergence in the large scale problem, yields a more stable distribution of non-dominated solutions, as well as non-dominated solutions much faster.

Research Area(s)

  • Knowledge rules, Matching patients and healthcare service providers, Multi-objective optimization model, Ordinal weighting average non-dominated sorting genetic algorithm II (OWA-NSGA-II)

Citation Format(s)