Martínez Velasco, Antonieta Teodora
Thumbnail Image
Preferred name
Martínez Velasco, Antonieta Teodora
Official Name
Martínez Velasco, Antonieta Teodora
Alternative Name
amartinezv
Main Affiliation
ORCID
Scopus Author ID
57192978286
Researcher ID
DWK-4326-2022

Research Output
Now showing 1 - 10 of 24
No Thumbnail Available
Publication

Business Model Innovation and Decision-Making for the Productive Sector in Times of Crisis

2022 , Terán-Bustamante, Antonia , Martínez Velasco, Antonieta Teodora

The pandemic caused by COVID-19 has affected all companies and their business models. For this reason, firms have needed to redesign these models, focusing on customer value proposition. The purpose of this research is to analyze Business Model Innovation (BMI) for decision-making. The methodological strategy is carried out through Bayesian networks. A model is made in which the main elements that make up a BMI are identified and quantified, which impact better decision-making to properly manage the proposal value for customers, technology, and achieve innovation. Evidence shows that the construction of BMI requires a model that mainly considers the relationships between variables such as knowledge architecture, implementation operation, change and evolution, and agile response. BMI will apply to organizations to the extent that it contemplates variables related to customer service and attention, as well as those related to innovation in organizations, attention, and those related to innovation in organizations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View
No Thumbnail Available
Publication

An Explainable Tool to Support Age-related Macular Degeneration Diagnosis

2022 , Martinez-Villaseñor, Lourdes , Miralles-Pechuán, Luis , Ponce, Hiram , Martínez Velasco, Antonieta Teodora

Artificial intelligence and deep learning, in particu-lar, have gained large attention in the ophthalmology community due to the possibility of processing large amounts of data and dig-itized ocular images. Intelligent systems are developed to support the diagnosis and treatment of a number of ophthalmic diseases such as age-related macular degeneration (AMD), glaucoma and retinopathy of prematurity. Hence, explainability is necessary to gain trust and therefore the adoption of these critical decision support systems. Visual explanations have been proposed for AMD diagnosis only when optical coherence tomography (OCT) images are used, but interpretability using other inputs (i.e. data point-based features) for AMD diagnosis is rather limited. In this paper, we propose a practical tool to support AMD diagnosis based on Artificial Hydrocarbon Networks (AHN) with different kinds of input data such as demographic characteristics, features known as risk factors for AMD, and genetic variants obtained from DNA genotyping. The proposed explainer, namely eXplainable Artificial Hydrocarbon Networks (XAHN) is able to get global and local interpretations of the AHN model. An explainability assessment of the XAHN explainer was applied to clinicians for getting feedback from the tool. We consider the XAHN explainer tool will be beneficial to support expert clinicians in AMD diagnosis, especially where input data are not visual. © 2022 IEEE.

View
No Thumbnail Available
Publication

A Survey of Machine Learning Approaches for Age Related Macular Degeneration Diagnosis and Prediction

2018 , Martínez Velasco, Antonieta Teodora , Martinez-Villaseñor, Lourdes

Age Related Macular Degeneration (AMD) is a complex disease caused by the interaction of multiple genes and environmental factors. AMD is the leading cause of visual dysfunction and blindness in developed countries, and a rising cause in underdeveloped countries. Currently, retinal images are studied in order to identify drusen in the retina. The classification of these images allows to support the medical diagnosis. Likewise, genetic variants and risk factors are studied in order to make predictive studies of the disease, which are carried out with the support of statistical tools and, recently, with Machine Learning (ML) methods. In this paper, we present a survey of studies performed in complex diseases under both approaches, especially for the case of AMD. We emphasize the approach based on the genetic variants of individuals, as it is a support tool for the prevention of AMD. According to the vision of personalized medicine, disease prevention is a priority to improve the quality of life of people and their families, as well as to avoid the inherent health burden. © Springer Nature Switzerland AG 2018.

View
No Thumbnail Available
Publication

Confiabilidad y validez de un instrumento de selección de capital humano

2020 , Terán-Bustamante, Antonia , Castillo Ramírez, Claudia Estrella , Martínez Velasco, Antonieta Teodora

El objetivo de esta investigación es analizar la validación y confiabilidad de un instrumento para la selección de capital humano en las organizaciones enfocado a la confianza-integridad. Para evaluar la confiabilidad y validez del instrumento se realizan dos tipos de análisis, el primero con modelos de la teoría clásica mediante el Alpha de Cronbach y el estadístico Kuder-Richardson 20. El segundo análisis se realiza utilizando la Teoría de Respuesta al Item (TRI) a través del modelo de Rasch, utilizando programación en R. El test desarrollado se realiza con enfoque en psicopatía organizacional. La evidencia encontrada muestra confiabilidad y validez en la prueba analizada, tanto para la valoración de las preguntas como para la fiabilidad en la selección de los individuos analizados. Así mismo, el modelo de Rach aporta información valiosa a nivel preguntas y sujetos para tener un mejor instrumento. Esta investigación aporta conocimiento en dos sentidos i) en los test de personalidad aplicados en las organizaciones para la selección de capital humano en forma más confiable y ii) en mostrar una metodología

View
No Thumbnail Available
Publication

Addressing Class Imbalance in Healthcare Data: Machine Learning Solutions for Age-Related Macular Degeneration and Preeclampsia

2024 , Martínez Velasco, Antonieta Teodora , Martinez-Villaseñor, Lourdes , Miralles-Pechuán, Luis

The use of machine learning in healthcare has transformed the way diseases are diagnosed and treatments are optimized. However, medical databases often lack balanced data due to challenges in data collection caused by privacy regulations. Certain health conditions are underrepresented, which hampers machine learning performance. To address this problem, a hybrid approach has been proposed that combines the Synthetic Minority Oversampling Technique (SMOTE) with undersampling and uses two specific techniques tailored for imbalanced datasets. Comparative evaluations were conducted using various thresholds to reduce one class and employing Balanced Accuracy to mitigate bias toward the majority class, with popular machine learning methods. The results showed that Balanced Bagging and Balanced Random Forest consistently outperformed other methods, performing the best with an average ranking of 1.42 and 3.58 out of 32 configurations in the two datasets, respectively. Tree-based approaches such as Random Forest and Gradient Boosting demonstrated similar effectiveness, emphasizing the power of aggregating predictions from multiple trees to reduce bias. Notably, undersampling and SMOTE proved advantageous for non-tree-based models like KNN, SVM, and Logistic Regression showcasing their usefulness across different algorithms. This study provides a robust solution for handling imbalanced datasets in healthcare, which could potentially optimize healthcare interventions and improve patient outcomes and care©IEEE Latin America Transactions, The authors

View
No Thumbnail Available
Publication

Critical Factors in the Participation of Women in Science, Technology, Engineering, and Mathematics -STEM- Disciplines in Mexico

2024-01-01 , Martínez Velasco, Antonieta Teodora , González, Fernando José Menéndez , DelaTorre-Diaz, Lorena , Terán-Bustamante, Antonia

Currently, women participate in STEM areas, still with a very marked gender gap. Taking this as a reference, in this work, an investigation has been carried out based on questionnaires applied to students of STEM careers. The information obtained was analyzed using multi-criteria decision methods. In particular, the Order of Preference by Similarity to the Ideal Solution (TOPSIS) method was applied to determine the most favorable conditions for women to study a STEM career. Through this analysis, this research has found that women's choice of a STEM career is strongly influenced firstly by the father's profession, secondly by the mother's profession, and also has a positive impact on the discrimination to which the person has been subjected, self-motivation. And self-esteem. These results indicate that it is necessary to influence the early educational stages to provide support from the family and school environment to women so that they develop their skills around STEM careers. In future work, the data obtained could be analyzed in greater depth, considering that the richness of the open responses may be lost by coding the respondents’ opinions as categorical variables. ©Springer.

View
No Thumbnail Available
Publication

Transformación digital para la competitividad de las empresas

2024 , Jorge Arturo Salgado García , Terán-Bustamante, Antonia , Martínez Velasco, Antonieta Teodora

La transformación digital es un proceso tanto tecnológico como sociocultural que involucra la adopción de tecnologías digitales y modificaciones en los modelos de negocio y la estrategia de las firmas. La literatura que estudia relaciones entre la transformación digital y la competitividad de las empresas se incrementó en el periodo de postpandemia, sin embargo, las investigaciones antes de la pandemia son escasas, por lo cual el objetivo de esta investigación es analizar el efecto de la transformación digital en la competitividad de las empresas antes de esta crisis. Los datos que se utilizaron para el análisis son de las Encuestas Nacionales sobre Productividad y Competitividad de las Pymes en Sectores Estratégicos en México. El análisis se realizó en dos partes: I. geoestadístico para buscar clústeres geográficos de corte natural y II. estadístico mediante la regresión Ridge. Los resultados evidenciaron que tanto la transformación digital como la competitividad se distribuyen de manera desigual en los territorios; sin embargo, se encontró un efecto positivo de la transformación digital en la competitividad de estas. De acuerdo con lo anterior, se concluyó que las empresas que quieran aumentar su competitividad deben incrementar su transformación digital, por lo que los gobiernos deben continuar estableciendo políticas y programas de transformación digital en todos los sectores y en forma más equitativa.

View
No Thumbnail Available
Publication

Explainable artificial hydrocarbon networks classifier applied to preeclampsia

2024 , Ponce, Hiram , Martinez-Villaseñor, Lourdes , Martínez Velasco, Antonieta Teodora

Explainability is crucial in domains where system decisions have significant implications for human trust in black-box models. Lack of understanding regarding how these decisions are made hinders the adoption of so-called clinical decision support systems. While neural networks and deep learning methods exhibit impressive performance, they remain less explainable than white-box approaches. Artificial Hydrocarbon Networks (AHN) is an effective black-box model that can be used to support critical clinical decisions if accompanied by explainability mechanisms to instill confidence among clinicians. In this paper, we present a use case involving global and local explanations for AHN models, provided with an automatic procedure so-called eXplainable Artificial Hydrocarbon Networks (XAHN). We apply XAHN to preeclampsia prognosis, enabling interpretability within an accurate black-box model. Our approach involves training a suitable AHN model using the cross-validation with ten repetitions, followed by a comparative analysis against four well-known machine learning techniques. Notably, the AHN model outperformed the others, achieving an F1-score of 74.91%. Additionally, we assess the efficacy of our XAHN explainer through a survey applied to clinicians, evaluating the goodness and satisfaction of the provided explanations. To the best of our knowledge, this work represents one of the earliest attempts to address the explainability challenge in preeclampsia prediction.© 2024 The Author(s). Published by Elsevier Inc.

View
Thumbnail Image
Publication

Metodología para determinar los factores de riesgo asociados con enfermedades complejas: Degeneración Macular Relacionada con la Edad y Preeclampsia

2021 , Martínez Velasco, Antonieta Teodora , Martinez-Villaseñor, Lourdes , Estrada Mena, Francisco Javier , Campus Ciudad de México

El incremento en la aplicación de la inteligencia artificial en la creación de sistemas de soporte de decisiones a escala está transformando también el futuro del cuidado de la salud. La inteligencia artificial se ha utilizado para implementar sistemas de diagnóstico y pronóstico de enfermedades, optimización del tratamiento y predicción del resultado, desarrollo de fármacos y para lidiar con problemas de salud pública. Los datos provenientes de los pacientes se pueden obtener de los registros médicos; estos generalmente son colecciones complejas de datos. Así, la determinación de los factores de riesgo es un reto importante debido a la gran cantidad de datos que actualmente se generan a partir de los estudios genéticos y datos clínicos obtenidos en la consulta médica de algunos hospitales. Con el fin de atender estos retos, en este trabajo se presenta una metodología para determinar los factores de riesgo asociados a enfermedades complejas mediante el enfoque de aprendizaje automático. La metodología se probó en dos escenarios de aplicación: Degeneración Macular Relacionada con la Edad (DMRE) y Preeclampsia (PE), con la entrega un sistema de toma de decisiones interpretable.

View
No Thumbnail Available
Publication

Decision-making model in ancestral knowledge management: The case of the Raicilla in Mexico

2024 , Martínez Velasco, Antonieta Teodora , Antonia Terán-Bustamante , Suhey Ayala-Ramírez , Víctor Manuel Castillo-Girón

Ancestral knowledge is essential in the construction of learning to preserve the sense of relevance, transmit and share knowledge according to its cultural context, and maintain a harmonious relationship with nature and sustainability. The objective of this research is to study and analyze the management of ancestral knowledge in the production of the Raicilla to provide elements to rural communities, producers, and facilitators in decision-making to be able to innovate and be more productive, competitive, sustainable, and improve people’s quality of life. The methodological strategy was carried out through Bayesian networks and Fuzzy Logic. To this end, a model was developed to identify and quantify the critical factors that impact optimally managed technology to generate value that translates into innovation and competitive advantages. The evidence shows that the optimal and non-optimal management of knowledge, technology, and innovation management and its factors, through the causality of the variables, permits us to capture the interrelationship more adequately and manage them. The results show that the most relevant factors for adequate management of ancestral knowledge in the Raicilla sector are facilitators, denomination of origin, extraction and fermentation, and government. The proposed model will support these small producers and help them preserve their identity, culture, and customs, contributing greatly to environmental sustainability.

View