Persona:
Pérez Martín, Jorge

Foto de perfil
Dirección de correo electrónico
jperezmartin@dia.uned.es
ORCID
0000-0002-3588-7233
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Pérez Martín
Nombre de pila
Jorge
Nombre

Filtros

2021 - 20234
Restablecer filtros

Ajustes

search.filters.applied.f.itemDepartamento: Estadística, Investigación Operativa y Cálculo Numérico ×

Resultados de la búsqueda

Mostrando 1 - 4 de 4
  • Miniatura
    Publicación
    Multi-input convolutional neural network for breast cancer detection using thermal images and clinical data
    (Elsevier, 2021-06) Sánchez Cauce, Raquel; Pérez Martín, Jorge; Luque Gallego, Manuel; Agencia Estatal de Investigación (España)
    Background and objective Breast cancer is the most common cancer in women. While mammography is the most widely used screening technique for the early detection of this disease, it has several disadvantages such as radiation exposure or high economic cost. Recently, multiple authors studied the ability of machine learning algorithms for early diagnosis of breast cancer using thermal images, showing that thermography can be considered as a complementary test to mammography, or even as a primary test under certain circumstances. Moreover, although some personal and clinical data are considered risk factors of breast cancer, none of these works considered that information jointly with thermal images. Methods We propose a novel approach for early detection of breast cancer combining thermal images of different views with personal and clinical data, building a multi-input classification model which exploits the benefits of convolutional neural networks for image analysis. First, we searched for structures using only thermal images. Next, we added the clinical data as a new branch of each of these structures, aiming to improve its performance. Results We applied our method to the most widely used public database of breast thermal images, the Database for Mastology Research with Infrared Image. The best model achieves a 97% accuracy and an area under the ROC curve of 0.99, with a specificity of 100% and a sensitivity of 83%. Conclusions After studying the impact of thermal images and personal and clinical data on multi-input convolutional neural networks for breast cancer diagnosis, we conclude that: (1) adding the lateral views to the front view improves the performance of the classification model, and (2) including personal and clinical data helps the model to recognize sick patients.
  • Miniatura
    Publicación
    Cost-effectiveness analysis with probabilistic graphical models
    (Bayesian Network Modelling Association, 2021-06-30) Díez Vegas, Francisco Javier; Luque Gallego, Manuel; Arias Calleja, Manuel; Pérez Martín, Jorge
    The two formalisms most widely used for the representation and analysis of decision problems in medicine are decision trees and Markov flat models, which seriously limit the complexity of the problems that can be addressed. In contrast, probabilistic graphical models (PGMs) can represent the state and the evolution of the system (the patient) using much richer structures, but they are rarely used for economic evaluations in medicine given that, until recently, they could not perform cost-effectiveness analysis (CEA). In this paper we summarize the research done by our group, developing new types of PGMs and new algorithms for CEA and implementing them in OpenMarkov, an open-source tool especially designed for medicine.
  • Miniatura
    Publicación
    Cost-effectiveness analysis with decision analysis networks
    (Asociación Española para la Inteligencia Artificial, 2021-08-24) Díez Vegas, Francisco Javier; Luque Gallego, Manuel; Arias Calleja, Manuel; Pérez Martín, Jorge; Agencia Estatal de Investigación (España)
    Decision analysis networks (DANs) are a new type of probabilistic graphical model. Like influence diagrams (IDs), they are much more compact and easier to build than decision trees and can represent conditional independencies, but they can also represent problems involving partial orderings of the decisions (order asymmetry) and other types of asymmetry. Given that DANs can solve symmetric problems as easily and as efficiently as IDs, and are more appropriate for asymmetric problems—which include virtually all real-world problems—DANs might replace IDs as the standard type of probabilistic graphical model for decision analysis. In particular, they can be use to perform cost-effectiveness analyses (CEAs), which are used increasingly in medicine to determine whether the health benefit of an intervention is worth the economic cost.
  • Miniatura
    Publicación
    Software para evaluación económica en medicina
    (Fundación PORIB, 2023-12) Díez Vegas, Francisco Javier; Yago Sánchez, Carmen María; Pérez Martín, Jorge; Luque Gallego, Manuel; Arias Calleja, Manuel