GIS-Based Multi-Criteria Decision-Support System and Machine Learning for Hospital Site Selection: Case Study Oran, Algeria

GIS-Based Multi-Criteria Decision-Support System and Machine Learning for Hospital Site Selection: Case Study Oran, Algeria

Khadidja Benmoussa, Djamila Hamdadou, Zine El Abidine Roukh
DOI: 10.4018/IJSSCI.285592
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The selection of hospital sites is one of the most important choice a decision maker has to take so as to resist the pandemic. The decision may considerably affect the outbreak transmission in terms of efficiency , budget, etc. The main targeted objective of this study is to find the ideal location where to set up a hospital in the willaya of Oran Alg. For this reason, we have used a geographic information system coupled to the multi-criteria analysis method AHP in order to evaluate diverse criteria of physiological positioning , environmental and economical. Another objective of this study is to evaluate the advanced techniques of the automatic learning . the method of the random forest (RF) for the patterning of the hospital site selection in the willaya of Oran. The result of our study may be useful to decision makers to know the suitability of the sites as it provides a high level of confidence and consequently accelerate the power to control the COVID19 pandemic.
Article Preview
Top

Introduction

Algeria, like other countries is a developing country. Hospitals consume a considerable part of the health budget and certain public hospitals and health-care sectors fail to optimize the public welfare. Among the criteria that raise hospitals performances are the site positioning. This is a subject of great concern in the world in view of environment, morphology and socio-economy.

Presently, the country is in a state of panic. The main topic of discussion on TVs and social networks is about COVID19. The number of people tested positive is increasing. The authorities have shut down party rooms, cafeterias and restaurants and for everybody, this is a dive in the unknown. Efficient systems to run hospitals and provide trustworthy services are necessary to face the transmission of the disease.

The rule in the health-care sector arouses an increasing interest to researchers and practitioners; rules of conception & construction calculations follow & adapt theses progresses to the national context. The issue is not to apply a certain number of regulatory requirements but to have a global approach that takes into account all the factors that are likely to have an impact on the construction behavior. The present study will be interested particularly by the hospital environment. The choices made in each of these fields will have repercussions on the behavior of all concerned. This approach will help the people involved to establish different requirements. The norms and rules that the most applied to build a hospital are:(Eastman, Lee et al. 2009):

  • Geotechnical and hydrological conditions

  • Topographic conditions

The main objectives from this study are to map the fields selections by the combination of the statistic model AHP. The geographic information system and the automatic learning for the willaya of Oran North West Algeria. In order to reach this aim, the analytic initiative of the geospatial distribution is proposed. We have sampled 11 parameters of environmental predisposition i.e. inland waters, floodplain, slope, elevation, terrain use, COVID-19 transmission, health-care sectors, traffic, transport, roads, railways, population and residential areas. A weighting of each parameter has been carried out by the AHP based on the GIS environment.

As a result, a thematic cartography of the hospital site selection has been set by the classification of the global index of classification.

This synthetic simulated map of potential hospital sites makes it possible to identify the more appropriate sites for hospital building and will help as an adapted tool to land and country planning.

In that respect, the AHP method is proposed to help the health administration & policy makers select the more advantageous place for the new hospital investments in the public & private sector.

The main objectives from this article is to propose a cartography for the hospital site selection in the willaya of Oran by the analytical hierarchy process method under the aegis of the geographical information system GIS. This approach is based on data collection, the evaluation of the susceptibility degree and finally on the algebraic cartography of the site selection.

The automatic learning techniques supply suitable tools to produce a map of hospital sites appropriateness. We have operated the random forest method. This method is an advanced version of the decision- tree that uses a structure of a model in a tree shape for the prediction of classification via a multiple splitting process. This latter gives a precision to 98.47370%. The covid19 transmission and population have been the most hospital influential factors.

Top

Background

The AHP is a pair wise comparative measurement theory in which priority scales are derived from the judgment of experts Bhushan and Rai (2007). Furthermore, the final priorities of alternatives in a decision are obtained through an iterative process of comparison (i.e., a top-down process). The inclusion of explicit geographical component is the main difference between multi-criteria spatial analysis and traditional multi-criteria techniques.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing