Literature DB >> 31523422

Multi-objective semi-supervised clustering to identify health service patterns for injured patients.

Hadi Akbarzadeh Khorshidi1, Uwe Aickelin1, Gholamreza Haffari2, Behrooz Hassani-Mahmooei3.   

Abstract

PURPOSE: This study develops a pattern recognition method that identifies patterns based on their similarity and their association with the outcome of interest. The practical purpose of developing this pattern recognition method is to group patients, who are injured in transport accidents, in the early stages post-injury. This grouping is based on distinctive patterns in health service use within the first week post-injury. The groups also provide predictive information towards the total cost of medication process. As a result, the group of patients who have undesirable outcomes are identified as early as possible based health service use patterns.
METHODS: We propose a multi-objective optimization model to group patients. An objective function is the cost function of k-medians clustering to recognize the similar patterns. Another objective function is the cross-validated root-mean-square error to examine the association with the total cost. The best grouping is obtained by minimizing both objective functions. As a result, the multi-objective optimization model is a semi-supervised clustering which learns health service use patterns in both unsupervised and supervised ways. We also introduce an evolutionary computation approach includes stochastic gradient descent and Pareto optimal solutions to find the optimal solution. In addition, we use the decision tree method to reproduce the optimal groups using an interpretable classification model.
RESULTS: The results show that the proposed multi-objective semi-supervised clustering identifies distinct groups of health service uses and contributes to predict the total cost. The performance of the multi-objective model has been examined using two metrics such as the average silhouette width and the cross-validation error. The examination proves that the multi-objective model outperforms the single-objective ones. In addition, the interpretable classification model shows that imaging and therapeutic services are critical services in the first-week post-injury to group injured patients.
CONCLUSION: The proposed multi-objective semi-supervised clustering finds the optimal clusters that not only are well-separated from each other but can provide informative insights regarding the outcome of interest. It also overcomes two drawback of clustering methods such as being sensitive to the initial cluster centers and need for specifying the number of clusters.

Entities:  

Keywords:  Evolutionary computation; Health service patterns; Injured patients; Multi-objective optimization; Semi-supervised clustering

Year:  2019        PMID: 31523422      PMCID: PMC6715760          DOI: 10.1007/s13755-019-0080-6

Source DB:  PubMed          Journal:  Health Inf Sci Syst        ISSN: 2047-2501


  9 in total

1.  Some new indexes of cluster validity.

Authors:  J C Bezdek; N R Pal
Journal:  IEEE Trans Syst Man Cybern B Cybern       Date:  1998

2.  Classifying GABAergic interneurons with semi-supervised projected model-based clustering.

Authors:  Bojan Mihaljević; Ruth Benavides-Piccione; Luis Guerra; Javier DeFelipe; Pedro Larrañaga; Concha Bielza
Journal:  Artif Intell Med       Date:  2015-01-02       Impact factor: 5.326

3.  Patterns of health care use of injured adults: A population-based matched cohort study.

Authors:  Rebecca J Mitchell; Cate M Cameron; Rod McClure
Journal:  Injury       Date:  2017-04-14       Impact factor: 2.586

4.  Finding discriminative and interpretable patterns in sequences of surgical activities.

Authors:  Germain Forestier; François Petitjean; Pavel Senin; Laurent Riffaud; Pierre-Louis Henaux; Pierre Jannin
Journal:  Artif Intell Med       Date:  2017-09-22       Impact factor: 5.326

5.  Early Identification of Undesirable Outcomes for Transport Accident Injured Patients Using Semi-Supervised Clustering.

Authors:  Hadi A Khorshidi; Gholamreza Haffari; Uwe Aickelin; Behrooz Hassani-Mahmooei
Journal:  Stud Health Technol Inform       Date:  2019-08-08

Review 6.  Patient healthcare trajectory. An essential monitoring tool: a systematic review.

Authors:  Jessica Pinaire; Jérôme Azé; Sandra Bringay; Paul Landais
Journal:  Health Inf Sci Syst       Date:  2017-04-12

7.  Classification tree modeling to identify severe and moderate vehicular injuries in young and middle-aged adults.

Authors:  Linda J Scheetz; Juan Zhang; John Kolassa
Journal:  Artif Intell Med       Date:  2008-12-16       Impact factor: 5.326

8.  An Approach Towards Reducing Road Traffic Injuries and Improving Public Health Through Big Data Telematics: A Randomised Controlled Trial Protocol.

Authors:  Mehrdad Azmin; Ayyoob Jafari; Nazila Rezaei; Kavi Bhalla; Dipan Bose; Saeid Shahraz; Mina Dehghani; Parastoo Niloofar; Soraya Fatholahi; Javad Hedayati; Hamidreza Jamshidi; Farshad Farzadfar
Journal:  Arch Iran Med       Date:  2018-11-01       Impact factor: 1.354

9.  Compensation Research Database: population-based injury data for surveillance, linkage and mining.

Authors:  Khic-Houy Prang; Behrooz Hassani-Mahmooei; Alex Collie
Journal:  BMC Res Notes       Date:  2016-10-01
  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.