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

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.

• Autores: Fontalvo Herrera, Tomás José; De la Hoz Domínguez, Enrique José; Fontalvo, Orianna
• Fecha de publicación: 2021
• Institución: Universidad Tecnológica de Bolívar
• Repositorio: Repositorio Institucional UTB
• Idioma: eng
• OAI Identifier: oai:repositorio.utb.edu.co:20.500.12585/10351
• Acceso en línea: https://hdl.handle.net/20.500.12585/10351; https://doi.org/10.1504/IJPQM.2021.115290
• Palabra clave: Cluster-analysis; Neural networks; Quality; Business profiles; Healthcare; LEMB
• Rights: openAccess
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/