Title: Methodology of classification, forecast and prediction of healthcare providers accredited in high quality in Colombia

Authors: Tomás Fontalvo-Herrera; Enrique Delahoz-Dominguez; Orianna Fontalvo

Addresses: Faculty of Economics Sciences, University of Cartagena, Cartagena, Colombia ' Industrial Engineering Department, Engineering Faculty, Universidad Tecnológica de Bolívar, Cartagena, Colombia ' Engineering Faculty, Universidad del Norte, Barranquilla, Colombia

Abstract: This research presents a methodology for classification, forecasting and prediction of healthcare providers accredited in Colombia. For this purpose, a quantitative, descriptive and predictive analysis was carried out of 27 institutions accredited in Colombia by 2016. Consequently, the machine learning techniques cluster analysis and artificial neural networks were used to define business profiles of the institutions under study. The method classifying, forecasting and predicting the membership of a healthcare provider to a business profile, previously created based on the high-quality patterns of accreditation. The input variables were assets, account receivable, inventory, property and equipment and the output variables health service sales and net profit. The cluster analysis defined two main groups. 1) accredited institutions in the process of financial consolidation; 2) accredited institutions financially sound. The process of forecasting and prediction through the creation of an artificial neural network yielded a 95% CI (088, 0.9975) precision in the classification, and 100% and 80% for sensitivity and specificity values respectively. The results evidence the capacity of the proposed methodology to recognise the characteristics and association patterns of HCP accredited in high quality.

Keywords: cluster-analysis; neural networks; quality; business profiles; healthcare; Colombia.

DOI: 10.1504/IJPQM.2021.115290

International Journal of Productivity and Quality Management, 2021 Vol.33 No.1, pp.1 - 20

Received: 05 Jul 2019
Accepted: 01 Nov 2019
Published online: 26 May 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article