Early identification of undesirable outcomes for transport accident injured patients using semi-supervised clustering

Hadi A. Khorshidi, Gholamreza Haffari, Uwe Aickelin, Behrooz Hassani-Mahmooei

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Identifying those patient groups, who have unwanted outcomes, in the early stages is crucial to providing the most appropriate level of care. In this study, we intend to find distinctive patterns in health service use (HSU) of transport accident injured patients within the first week post-injury. Aiming those patterns that are associated with the outcome of interest. To recognize these patterns, we propose a multi-objective optimization model that minimizes the k-medians cost function and regression error simultaneously. Thus, we use a semi-supervised clustering approach to identify patient groups based on HSU patterns and their association with total cost. To solve the optimization problem, we introduce an evolutionary algorithm using stochastic gradient descent and Pareto optimal solutions. As a result, we find the best optimal clusters by minimizing both objective functions. The results show that the proposed semi-supervised approach identifies distinct groups of HSUs and contributes to predict total cost. Also, the experiments prove the performance of the multi-objective approach in comparison with single-objective approaches.

Original languageEnglish
Title of host publicationDigital Health: Changing the Way Healthcare is Conceptualised and Delivered
Subtitle of host publicationSelected Papers from the 27th Australian National Health Informatics Conference (HIC 2019)
EditorsElizabeth Cummings, Mark Merolli, Louise K. Schaper
Place of PublicationAmsterdam Netherlands
PublisherIOS Press
Pages1-6
Number of pages6
ISBN (Electronic)9781643680071
ISBN (Print)9781643680064
DOIs
Publication statusPublished - 8 Aug 2019
EventAustralian National Health Informatics Conference 2019 - Melbourne, Australia
Duration: 12 Aug 201914 Aug 2019
Conference number: 27th
https://www.hisa.org.au/hic2019/

Publication series

NameStudies in Health Technology and Informatics
Volume266
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

ConferenceAustralian National Health Informatics Conference 2019
Abbreviated titleHIC 2019
CountryAustralia
CityMelbourne
Period12/08/1914/08/19
Internet address

Keywords

  • Health service patterns
  • Injured patients
  • Injury outcomes
  • Multi-objective optimization
  • Semi-supervised clustering

Cite this

Khorshidi, H. A., Haffari, G., Aickelin, U., & Hassani-Mahmooei, B. (2019). Early identification of undesirable outcomes for transport accident injured patients using semi-supervised clustering. In E. Cummings, M. Merolli, & L. K. Schaper (Eds.), Digital Health: Changing the Way Healthcare is Conceptualised and Delivered: Selected Papers from the 27th Australian National Health Informatics Conference (HIC 2019) (pp. 1-6). (Studies in Health Technology and Informatics; Vol. 266). IOS Press. https://doi.org/10.3233/SHTI190764