Cover Image

Spatial analysis and prediction of the flow of patients to public health centres in a middle-sized Spanish city

Isabel Ramos, Juan J. Cubillas, Francisco R. Feito, Tomas Ureña
  • Isabel Ramos
    Department of Cartographic, Geodetic Engineering and Photogrammetry, University of Jaen, Jaen, Spain | miramos@ujaen.es
  • Juan J. Cubillas
    TIC-144 Andalusian Research Plan, Department of Computer Science, University of Jaen, Jaen, Spain
  • Francisco R. Feito
    TIC-144 Andalusian Research Plan, Department of Computer Science, University of Jaen, Jaen; Department of Computer Science, University of Jaen, Jaen, Spain
  • Tomas Ureña
    Sanitary District, Andalusian Health Service, Jaen, Spain

Abstract

Human and medical resources in the Spanish primary health care centres are usually planned and managed on the basis of the average number of patients in previous years. However, sudden increases in patient demand leading to delays and slip-ups can occur at any time without warning. This paper describes a predictive model capable of calculating patient demand in advance using geospatial data, whose values depend directly on weather variables and location of the health centre people are assigned to. The results obtained here show that outcomes differ from one centre to another depending on variations in the variables measured. For example, patients aged 25-34 and 55-65 years visited health centres less often than all other groups. It was also observed that the higher the economic level, the fewer visits to health centres. From the temporal point of view, Monday was the day of greatest demand, while Friday the least. On a monthly basis, February had the highest influx of patients. Also, air quality and humidity influenced the number of visits; more visits during poor air quality and high relative humidity. The addition of spatial variables minimised the average error the predictive model from 7.4 to 2.4% and the error without considering spatial variables varied from the high of 11.8% in to the low of 2.5%. The new model reduces the values in the predictive model, which are more homogeneous than previously.

Keywords

Spatial analysis; Health care; Resource optimisation; Data mining; Spain

Full Text:

PDF
HTML
Submitted: 2016-01-19 11:07:39
Published: 2016-11-21 11:53:04
Search for citations in Google Scholar
Related articles: Google Scholar
Abstract views:
327

Views:
PDF
261
HTML
235

Article Metrics

Metrics Loading ...

Metrics powered by PLOS ALM


Copyright (c) 2016 Juan Jose Cubillas, Maria Isabel Ramos, Francisco Ramon Feito, Tomas Ureña

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
 
© PAGEPress 2008-2017     -     PAGEPress is a registered trademark property of PAGEPress srl, Italy.     -     VAT: IT02125780185