Exploring computational methods in the statistical analysis of imprecise medical data: between epistemology and ontology

The accuracy of the results is essential to evaluate the effectiveness of statistical methods in the analysis of medical data with uncertainty. Indicators such as margin of error, percent agreement and coefficient of determination quantified accuracy under epistemic and ontological uncertainty. The stability of the methods was assessed by variation in trend analysis, sensitivity to small variations and model robustness. Data reliability focused on the selection of methods that effectively handle epistemic uncertainty, recording assumptions, sensitivity analysis and internal consistency. Ontological imprecision was quantified using the fuzzy membership degree and the overlap coefficient. The exploration of computational methods underlined the importance of accuracy and the handling of epistemic and ontological uncertainty, ensuring reliable results. The geometric mean filter, with a score of 0,7790, stood out as the best for its accuracy and ability to effectively handle uncertainty.

• Autores: Nieto Sanchez, Zulmary Carolina; Bravo Valero, Antonio José
• Fecha de publicación: 2024
• Institución: Universidad Simón Bolívar
• Repositorio: Repositorio Digital USB
• Idioma: eng
• OAI Identifier: oai:bonga.unisimon.edu.co:20.500.12442/16224
• Acceso en línea: https://hdl.handle.net/20.500.12442/16224; https://doi.org/10.56294/saludcyt20241341
• Palabra clave: Estadística; Métodos computacionales; Datos imprecisos; Incertidumbre; Epistemología; Ontología; Statistics; Computational Methods; Imprecise Data; Uncertainty; Epistemology; Ontology
• Rights: openAccess
• License: Attribution-NonCommercial-NoDerivs 3.0 United States