Validation of a teaching model instrument for university education in Ecuador through an artificial intelligence algorithm

Introduction: In the context of university education in Ecuador, the application of Artificial Intelligence (AI) for the assessment and adaptation of teaching models marks significant progress toward enhancing educational quality. The integration of AI into pedagogical processes is increasingly recognized as a strategic component for fostering innovation and improving instructional outcomes in higher education. Methods: This study focused on the validation of an AI-based instrument, specifically designed for the evaluation and adaptation of pedagogical strategies in the Ecuadorian university environment. A quantitative methodology was adopted, employing multivariate statistical analyses and structural equation modeling (SEM) to examine the internal consistency, construct validity, and interrelations among various didactic dimensions. The instrument was applied to a statistically representative sample of university professors across both undergraduate and graduate levels. Results: The statistical analysis demonstrated high levels of internal consistency and discriminative validity among the constructs representing different teaching models. The confirmatory factor analysis and SEM procedures verified the adequacy of the theoretical structure and the robustness of the proposed measurement model. Coefficients obtained for reliability and model fit met or exceeded established thresholds in educational research. Discussion: The findings confirm the empirical soundness of the AI-based instrument and support the feasibility of using such tools to assess and enhance teaching models in higher education. These results underscore the importance of adopting innovative, data-driven methodologies that respond to the demands of contemporary educational environments. Furthermore, the use of AI in the validation process enables a more precise interpretation of educational information, reinforcing the relevance of AI-supported models in optimizing teaching and learning processes.