Citas bibligráficas
Beteta, M., Paniura, R., Valdivia, D. (2023). Propuesta de un modelo predictivo basado en Machine Learning para el diagnóstico temprano de cáncer de mama en una empresa prestadora de servicio de salud privada [Trabajo de investigación, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/671055
Beteta, M., Paniura, R., Valdivia, D. Propuesta de un modelo predictivo basado en Machine Learning para el diagnóstico temprano de cáncer de mama en una empresa prestadora de servicio de salud privada [Trabajo de investigación]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2023. http://hdl.handle.net/10757/671055
@mastersthesis{renati/411623,
title = "Propuesta de un modelo predictivo basado en Machine Learning para el diagnóstico temprano de cáncer de mama en una empresa prestadora de servicio de salud privada",
author = "Valdivia Calderon, David Abdias",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2023"
}
The present research work was developed with the purpose of reducing the operational expenses of breast cancer treatment in different stages (I, II, III and IV), due to the activation of insurance policies. For this proposal, a Private Health Service Provider Company (PHSPC) was taken as a reference. It should be noted that the research work is based on the proposal of implementing a predictive model for early breast cancer diagnosis, for which the literature of different Machine Learning models was reviewed and evaluated by different groups of researchers. Likewise, they compared which one was the most effective in terms of accuracy and effectiveness percentage, and as a result, the best predictive model (Support Vector Machine - SVM) was selected. Then, the real value variables or characteristics (10) for each cellular nucleus of the mammography that will be part of the DataSet trained by the selected model were identified. Finally, for the implementation proposal, the CRISP-DM methodology (standard process for data mining in different industries) will be applied, as it is flexible, easy, structured, and reliable, and also used in similar projects. Additionally, Microsoft Azure's Machine Learning services will be used for this proposal. The implementation of the Model will allow a 2% reduction in the operational costs of breast cancer treatment in the PHSPC, increasing the value of the company in the oncological segment.
Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons