Datos sintéticos de un modelo de datos común para las aplicaciones de inteligencia artificial en salud materna: reporte de experiencia en el contexto colombiano.

Saved in:

Bibliographic Details
Title:	Datos sintéticos de un modelo de datos común para las aplicaciones de inteligencia artificial en salud materna: reporte de experiencia en el contexto colombiano.
Alternate Title:	Synthetic data within a common data model for artificial intelligence applications in maternal health: experience report in the Colombian context.
Authors:	Augusto Torres-Silva, Ever¹ ever@netuxtecnologia.com, José Gaviria-Jiménez, Juan², María Guevara-Zambrano, Ana³, Herrera-Almanza, Laura⁴, Flórez-Arango, José⁵
Source:	Biomédica: Revista del Instituto Nacional de Salud. 2025 Special Issue, Vol. 45, p71-82. 12p.
Subjects:	MATERNAL health, ARTIFICIAL intelligence, PRENATAL care, MEDICAL records, DATA harmonization, DATA privacy, DATA modeling
Geographic Terms:	COLOMBIA
Abstract (English):	Introduction. Synthetic data in healthcare is an alternative for generating clinical records that resemble those registered in real clinical scenarios. The benefits of synthetic data are: greater volume of data, the possibility of representing specific patient populations, protection of real-data privacy, and improved data-sharing among different actors. Objective. To formulate a synthetic data generation model for the gestational care process in Colombia and adapt it to the Observational Medical Outcomes Partnership (OMOP) common data model to facilitate its integration into artificial intelligence applications in maternal health. Materials and methods. We conducted a case study of fully synthetic data formulation that included some of the most frequent outcomes and conditions during gestation based on a typical care process for pregnant women in Colombia. This approach was complemented by the generation of a common data model to facilitate data integration in future artificial intelligence applications or complementary systems that benefit from a standardized language, regardless of the system or form of classification. Results. We formulated a model for the synthetic generation of clinical data -applicable to real clinical settings- that spans the entire gestational care until the perinatal period. The model included the most frequent clinical conditions and outcomes, which were diagrammed in the Synthea™ tool with their corresponding clinical probabilities of occurrence based on the reported literature or the usual practice of obstetric specialists in Colombia. Conclusions. This study demonstrates that the generation of synthetic data applied to the gestational care process in Colombia was feasible and represents a pioneering contribution in the region. [ABSTRACT FROM AUTHOR]
Abstract (Spanish):	Introducción. Los datos sintéticos en salud son una alternativa para generar registros clínicos que permitan obtener historias clínicas similares a las reales y que puedan ser usadas en diferentes situaciones clínicas. Objetivo. Formular un modelo basado en la generación de datos sintéticos para el proceso de atención de la gestación en Colombia y adaptarlo al modelo de datos común de la Observational Medical Outcomes Partnership (OMOP) para facilitar su integración en aplicaciones de inteligencia artificial en salud materna. Materiales y métodos. Se realizó un estudio de caso de formulación de datos completamente sintéticos, en el cual se incluyeron algunos de los desenlaces y condiciones más frecuentes de la gestación durante un proceso típico de atención de mujeres gestantes en Colombia. La propuesta se complementó con la generación de un modelo común de datos para facilitar la integración de los datos en futuras aplicaciones de inteligencia artificial o de sistemas complementarios que se beneficien de un lenguaje común, independiente del sistema o de la forma de clasificación. Resultados. Se logró la formulación de un modelo para la generación sintética de datos clínicos en el entorno clínico de atención de la gestación hasta el periodo perinatal. El modelo incluyó las condiciones clínicas y los desenlaces más frecuentes, los cuales se diagramaron en la herramienta Synthea™ con sus respectivas probabilidades clínicas de ocurrencia, según la literatura reportada o la práctica habitual de los especialistas en obstetricia en Colombia. Conclusiones. Este estudio demuestra que la generación de datos sintéticos aplicados al proceso de atención de la gestación en Colombia es factible y constituye un aporte pionero en la región. [ABSTRACT FROM AUTHOR]
	Copyright of Biomédica: Revista del Instituto Nacional de Salud is the property of Instituto Nacional de Salud of Colombia and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	MedicLatina

Description
Abstract:	Introduction. Synthetic data in healthcare is an alternative for generating clinical records that resemble those registered in real clinical scenarios. The benefits of synthetic data are: greater volume of data, the possibility of representing specific patient populations, protection of real-data privacy, and improved data-sharing among different actors. Objective. To formulate a synthetic data generation model for the gestational care process in Colombia and adapt it to the Observational Medical Outcomes Partnership (OMOP) common data model to facilitate its integration into artificial intelligence applications in maternal health. Materials and methods. We conducted a case study of fully synthetic data formulation that included some of the most frequent outcomes and conditions during gestation based on a typical care process for pregnant women in Colombia. This approach was complemented by the generation of a common data model to facilitate data integration in future artificial intelligence applications or complementary systems that benefit from a standardized language, regardless of the system or form of classification. Results. We formulated a model for the synthetic generation of clinical data -applicable to real clinical settings- that spans the entire gestational care until the perinatal period. The model included the most frequent clinical conditions and outcomes, which were diagrammed in the Synthea™ tool with their corresponding clinical probabilities of occurrence based on the reported literature or the usual practice of obstetric specialists in Colombia. Conclusions. This study demonstrates that the generation of synthetic data applied to the gestational care process in Colombia was feasible and represents a pioneering contribution in the region. [ABSTRACT FROM AUTHOR]
ISSN:	01204157
DOI:	10.7705/biomedica.7937