Conference Agenda

Deep learning (DL) techniques have substantially transformed medical imaging diagnostics by improving diagnostic accuracy, clinical efficiency, and decision support. This article presents a systematic literature review (SLR) that aims to analyze the evolution, contributions, limitations, and clinical benefits of DL architectures applied to medical imaging diagnostics during the period 2020–2025. The review was conducted following the PRISMA framework guidelines. The literature search in the Scopus database yielded 10,623 results on artificial intelligence, deep learning, and medical imaging. After applying automated filters and a thorough manual review, 38 scientific articles were selected that met rigorous criteria for clinical validation, use of real medical images, and diagnostic utility. The results indicate that CNNs and hybrid CNN-SVM models are the most widely used architectures, accounting for more than 57% of the articles reviewed. In addition, there is a growing adoption of modern architectures such as U-Net, ResNet, DenseNet, and emerging models based on Transformers. The greatest contributions are categorized into three areas: computational (42.1%), methodological (34.2%), and clinical (23.7%). In the clinical world, DL systems consistently improved diagnostic accuracy, reduced interobserver variability, improved workflows, and aided decision-making in imaging such as MRI, CT, ultrasound, and mammography. However, challenges remain in terms of data heterogeneity, model generalization, algorithmic interpretability, regulatory frameworks, and institutional readiness. In summary, this review provides a structured, evidence-based synthesis, bringing algorithmic research closer to its practical application in the clinic.

This paper presents a comparative study on fall detection in older adults using four pre-trained convolutional neural network models (VGG16, VGG19, ResNet50V2 and ResNet101V2), and Vision Transformer for Image Classification (ViT) model. Falls among older adults remain one of the leading cause of injury and reduced quality of life, and real-time detection systems can allow timely intervention to minimize harm. The proposed models are evaluated on a publicly available dataset composed of RGB images categorized into falls and non-falls. Each image is pre-processed through cropping, resizing to 128×128 and 224×224 pixels for CNN-based and ViT models, respectively, and Min-Max normalization.Transfer learning is applied to fine-tune the models using ImageNet-initialized weights, modifying the final layers to address the binary classification task. Models are trained and tested under consistent conditions, and performance is evaluated using accuracy, precision, recall, and F1 score metrics, supported by confusion matrices and ROC curves. Among the models, ViT model achievesthe highest classification accuracy (98%) and demonstrates a strong balance across performance metrics, particularly in detecting actual falls cases, which is critical in healthcare applications. This study confirms the effectiveness of ViT models for fall detection from single-camera input without the need for wearable sensors.

The rapid adoption of artificial intelligence (AI) and information and communication technologies (ICTs) is profoundly transforming the management of strategic communication and Public and Institutional Relations (PR). This article presents findings and reflections derived from a research project carried out in Argentina, whose purpose was to analyze the application and impact of AI and ICTs on PR management in organizations in the country, to identify challenges and opportunities, and to propose guidelines for the responsible adoption of these tools.

The study is based on an interdisciplinary approach that integrates contributions from PR theory, research on communication, technology and society, and recent literature on AI applied to work processes and organizational management. Methodologically, a sequential mixed-methods design was followed, combining a literature review, in-depth interviews with professionals, surveys of communication and PR managers, and direct observation of communication strategies and actions in digital environments.

The results show significant progress in the incorporation of AI- and ICT-based tools into certain work processes and, at the same time, broad opportunities for application and major challenges for organizational management.

The article proposes a conceptual framework for understanding AI in PR as a sociotechnical system that requires balancing technological innovation, organizational culture and professional competencies, and concludes with recommendations for the responsible adoption of technology in the management of communication and relationships with stakeholders.

The present research compares Machine Learning models to predict growth (average final weight) and support profitability decisions in a high Andean fish farm. Linear and Random Forest Regression were evaluated using a set of 500 weekly records, integrating historical data provided by the fish farm and synthetic data generated within validated physicochemical ranges. The results concluded with a high performance in the growth prediction (R²>0.98) and adequate performance in profitability (R²≈0.87). In addition, the profitability classifier achieved 0.93 accuracy, suggesting operational utility as an early warning.

This paper presents a comparative analysis of the performance of four supervised machine learning algorithms based on Boosting models: XGBoost, LightGBM, CatBoost, and Gradient Boosting Machine. The objective is to classify students according to their enrollment modality: face-to-face or blended learning at a National University of Education in Peru during the period 2020–2024. A dataset from the Peruvian government's national open data platform was used, which includes academic and demographic information about students. The four machine learning models were then trained using the stratified cross-validation technique to ensure that each class was adequately represented. To analyze the performance of the evaluated machine learning models, the following evaluation metrics were used: Accuracy, Precision, Recall, F1-Score, and Area Under the Curve (AUC). Of all the models evaluated, the CATBOOST algorithm stood out for offering a balance between precision and efficiency. These final findings highlight the importance and usefulness of implementing automated systems that support enrollment planning and management in both face-to-face and blended learning modalities in Peruvian higher education.

Diabetes mellitus is a leading cause of morbidity and mortality worldwide, making its early prediction a public health priority. This study compares the performance of Extreme Gradient Boosting (XGBoost) and a Hybrid Variational Autoencoder (Hybrid VAE) for diabetes classification, evaluating both their predictive accuracy and clinical interpretability. Using the scikit-learn diabetes dataset (442 samples, 10 clinical variables), two models were implemented: XGBoost with hyperparameter optimization and a Hybrid VAE with an 8-dimensional latent space designed to learn interpretable representations of underlying physiological factors. Accuracy, precision, recall, F1-score, and AUC-ROC were assessed, along with latent space analysis using PCA. The Hybrid VAE outperformed XGBoost in all evaluated metrics: accuracy (73.03% vs. 69.66%), recall (79.55% vs. 70.45%), F1-score (0.7447 vs. 0.6966), and AUC-ROC (0.8045 vs. 0.7702). Latent space analysis revealed a natural separation between diabetic and non-diabetic patients in the principal components, with a cumulative explained variance of 64.0%. The importance of features in XGBoost identified body mass index (BMI) and serum S5 measurement as the most relevant predictors. The Hybrid VAE demonstrates superior performance to XGBoost in diabetes prediction, combining high predictive accuracy with the added advantage of an interpretable latent space that captures the underlying structure of the disease. This hybrid approach represents a promising alternative for clinical applications where both accuracy and understanding of the underlying mechanisms are critical.