Martínez Velasco, Antonieta Teodora
Main Affiliation
Preferred name
Martínez Velasco, Antonieta Teodora
Official Name
Martínez Velasco, Antonieta Teodora
ORCID
0000-0001-6535-1440 
Researcher ID
DWK-4326-2022
Scopus Author ID
57192978286
36 results
Now showing 1 - 10 of 36
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, The Value of Assertiveness in Patient Care in Health Institutions Under the Expert Systems ApproachAssertive communication between health professionals and patients plays a crucial role in the disease–health relationship, creating trust and loyalty while promoting health. A medical expert computer system that emulates human reasoning by acting as a human expert would do so to provide clinical decision support to physicians, patients, and others involved in health care. This research aims to analyse and develop a model of assertiveness in patient care in health institutions through Bayesian networks with machine learning techniques. For this, a model is created in which the critical factors that impact optimally managing assertive communication are identified and quantified, which allows health institutions to generate value for the patient through a service experience with humane treatment. The results show that the most relevant factors in managing assertive communication in health institutions are disease information, communication, human capital, medical team, health institution, continuity of care, patient safety, and patient rights. Furthermore, the evidence shows that the optimal or non-optimal management of assertive communication and its various processes, through the causality of the variables, allow the interrelation to be more adequately captured to manage it. ©The authors ©Emerald. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Determining the Influence of Socioeconomic and Clinical Factors in Diabetes in the Mexican Population Using Machine Learning TechniquesDiabetes has a significant cost for health systems and the economy in general of countries, in addition to affecting the quality of life of people who suffer from it. Studying and analyzing the economic and clinical factors that trigger it allows us to identify the financial burden it represents and how policies and programs can be generated to support the prevention of this disease. This research aims to analyze the influence of socioeconomic and clinical factors on the Mexican population suffering from Diabetes. The analysis methods that are applied are the machine learning technique. The results in the Mexican population show that deaths from Diabetes occur more frequently in the population between 20 and 59 years of age. The factors related to housing-urbanization, specifically homes without piped water homes and houses with dirt floors, as well as people without the right to social security, are the critical factors that correlate with deaths caused by Diabetes: Hypertension, pneumonia, chronic respiratory diseases, coronary diseases, and influenza. ©The authors © Springer. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Regulations and Laws Affecting Women’s Economic Opportunities: A Worldwide Approach(SAGE Publications, 2025); ; Leyva-Hernández, Sandra NellyThis research aims to analyze the regulations and laws that promote economic opportunities for women at an international level, predict their impact on income levels, and estimate when legal gender equality will be achieved across different regions. The countries are compared over time, based on their income levels and regional locations, considering regulatory indicators on mobility, workplace, pay, marriage, parenthood, entrepreneurship, assets, and pensions. The methodological strategy was based on machine learning methods. The results indicate a positive trend in the average scores of all regulatory indicators, revealing significant differences across groups of countries and suggesting more egalitarian regulatory frameworks for developed countries, as well as more imbalanced and less progressive frameworks for underdeveloped and developing countries. The regulatory axes that better predict a country’s income level were parenthood, analyzing laws affecting women’s work after having children; assets, which consider gender differences in ownership and inheritance; and marriage, related to the legal constraints on women affected by marriage and divorce. However, the paternity axis is the last to be achieved. ©The authors ©SAGE Publications ©SAGE Open. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, The Most Relevant Factors in the Gender Gap in European Countries(Academic Conferences International Ltd, 2025); ; Gender equality is essential for the sustainable development of all countries. It brings economic growth, improved education and health for the entire population, poverty reduction, and social and political stability as democracy is strengthened and more peaceful communities are generated. However, its study is complex and includes various dimensions. This research aims to analyze the most relevant factors of the gender gap in European countries. The methodological strategy is based on machine learning techniques applied to the Gender Equality Index, which includes the EU27 countries and was developed by EIGE. These machine-learning techniques are methods computers use to learn from data and make predictions without being explicitly programmed. This index has 31 relevant indicators that are grouped into 14 subdimensions, which are, in turn, divided into six dimensions. The relevant dimensions in the study of gender equality are I. work (5 indicators), II. Money (4 indicators), III. Knowledge (3 indicators), IV. Time (4 indicators), V. power (8 indicators), and VI. Health (7 indicators). The results show a women's gap. Three of the most relevant dimensions from this research inhibit gender equity: I. Power in its three economic, political, and social dimensions; II. Knowledge in its two dimensions of attainment, participation, and segregation, and III. Time in its dimension of social activities. Women's most significant factors for the gender gap are power, knowledge, and time. ©The authors ©International Conference on Gender Research. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Making Better Medical Decisions Using Machine Learning: A Bayesian ModelCurrently, most countries seek universal health coverage for all people; however, in the face of the crisis in health systems caused by the COVID-19 pandemic and the high demand for these services, it is more relevant to have tools that allow faster data taking. However, making medical decisions is one of the most complex processes. Artificial intelligence (AI) is a rapidly evolving field that can transform various aspects of healthcare, such as diagnosis, treatment, prevention, and management. However, to have confidence in the systems, the actors must ensure they are adequately trained to make correct decisions. This research analyzes medical decision-making through Bayesian networks with machine learning techniques. This research creates a methodology and model for making medical decisions based on artificial intelligence. The model shows critical factors that optimally influence decision-making to generate value that translates into patient health. The results show that optimal or non-optimal medical decision-making and its various aspects through the causality of the variables allow the interrelation to be more adequately captured to manage it. The most relevant factors for adequate decision-making are Ethical Issues, Risk/Benefit, Scientific Integrity, Transparent Decisions, Data Preprocessing and Curation, Performance Evaluation, and ML Model. ©The authors © Springer. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Whiteness, Technological Capital and Platformed Interculturality: COIL Experiences in Latin America(Informa UK Limited, 2026); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Management of scientific and ancestral knowledge: a decision-making model in mezcal industry in Mexico(Frontiers Media SA, 2025); ; Leyva-Hernández, Sandra NellyIntroduction: Knowledge management is essential to ensure the sustainability of rural communities and small producers since it generates value for innovation, productivity, and competitiveness. The aim of this study is to identify relevant factors for adequate decision-making in managing knowledge in the Mexican mezcal industry and its impact on developing rural communities and small producers - mezcaleros. For this purpose, a decision-making model for managing scientific and ancestral knowledge is created to support links with universities, research centers, and rural communities to accelerate innovation and competitiveness in this sector. Methods: The analysis methods were carried out through decision-making, machine-learning techniques, and fuzzy logic. Results: The Bayesian Network model suggests that the preceding variables to optimize the Mezcaleros Knowledge Management are the Mezcaleros Indigenous community, the Denomination of Origin, Scientific and Ancestral Knowledge, Waste Management and Use, and Jima. Discussion: This knowledge management model aims to guide small producers to be more productive and competitive through the support of a facilitator. ©The authors ©Frontiers in Artificial Intelligence ©Frontiers Media SA. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Conceptual Framework for Digital Transformation of Business Models: Advancing Towards Industry 5.0(Springer Nature Switzerland, 2026); ; Hernández-Lara, Ana BeatrizDigital transformation is progressing unevenly across industries, with varying levels of success influenced by organizational and sector-specific factors. Understanding where to focus investments and what type of transformation to adopt has become a crucial challenge for companies seeking competitiveness and market relevance in the digital era. This paper aims to analyze companies’ strategic decision making to foster digital transformation, conducting a literature review, and proposing a conceptual framework for digital transformation of business models. The study identifies key drivers of successful digital transformation, including digital strategy, human capital, scalability, customer focus, security and risk management. Integrating these factors, the proposed model emphasizes the strategic alignment of digital initiatives with organizational goals, fostering a culture of continuous innovation and adaptability. The findings contribute to a deeper understanding of the mechanisms and prerequisites for effective digital transformation, offering insights for organizations navigating the shift toward Industry 5.0. ©The authors ©Springer. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Knowledge and innovation management model in the mezcal industry in Mexico(Elsevier, 2025); 11 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Addressing Class Imbalance in Healthcare Data: Machine Learning Solutions for Age-Related Macular Degeneration and Preeclampsia(IEEE, 2024); ; Miralles-Pechuán, LuisThe 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 authorsScopus© Citations 1 11