Search

In recent years, educational data mining has emerged as a growing discipline focused on developing models for predicting academic performance. The primary objective of this research was to tune classification models to predict academic performance in secondary school. The dataset employed for this study encompassed information from 19,545 high school students. We used descriptive statistics to characterise information contained in personal, school, and socioeconomic variables. We implemented two data mining techniques, namely artificial neural networks (ANN) and support vector machines (SVM). Parameter optimisation was conducted through five–fold cross–validation, and model performance was assessed using accuracy and F 1 –Score. The results indicate a functional dependence between predictor variables and academic performance. The algorithms demonstrated an average performance exceeding 80% accuracy. Notably, ANN outperformed SVM in the dataset analysed. This type of methodology could help educational institutions to predict academic underachievement and thus generate strategies to improve students' academic performance. [ABSTRACT FROM AUTHOR]

Copyright of Revista Tecno Lógicas is the property of Instituto Tecnologico Metropolitano and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Biomédica: Revista del Instituto Nacional de Salud is the property of Instituto Nacional de Salud of Colombia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Introduction. Diabetes is a chronic disease characterized by a high blood glucose level. It can lead to complications that affect the quality of life and increase the costs of healthcare. In recent years, prevalence and mortality rates have increased worldwide. The development of models with high predictive performance can help in the early identification of the disease. Objective. To develope a model based on artificial intelligence to support clinical decisionmaking in the early detection of diabetes. Materials and methods. We conducted a cross-sectional study, using a dataset that contained age, signs, and symptoms of patients with diabetes and of healthy individuals. Pre-processing techniques were applied to the data. Subsequently, we built the model based on fuzzy cognitive maps. Performance was evaluated with three metrics: accuracy, specificity, and sensitivity. Results. The developed model obtained an excellent predictive performance with an accuracy of 95%. In addition, it allowed to identify the behavior of the variables involved using simulated iterations, which provided valuable information about the dynamics of the risk factors associated with diabetes. Conclusions. Fuzzy cognitive maps demonstrated a high value for the early identification of the disease and in clinical decision-making. The results suggest the potential of these approaches in clinical applications related to diabetes and support their usefulness in medical practice to improve patient outcomes.