Luis Amigó Catholic University

Background: Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental condition with heterogeneity and clinical variability. It has three diagnostic presentations (inattentive, hyperactive/impulsive, combined). It is common for it to occur concomitantly with other psychopathologies (neurodevelopmental disorder or behavioral disorder), which increases the complexity of its detection. Methods: This work developed and evaluated a multiclass machine learning (ML) model to identify ADHD and comorbidities in a pediatric population. The research approach was quantitative and cross-sectional, with a non-experimental design and non-probability sampling. The sample has 892 children aged [6-12] years from Medellín, Colombia (ADHD=780, typically developing controls=112). Cognitive and behavioral assessments were used as predictor variables. Python 3.12.13 was used in the programming algorithms; a computational pipeline was implemented with preprocessing techniques, class balancing using Synthetic Minority Over-sampling Technique (SMOTE) and stratified cross-validation. Results: Multiple classification algorithms were evaluated, Random Forest (RF) was identified as the optimal model (accuracy=.9778, precision=.9798, recall=.9778, F1-score=.9777; weighted averages for multiclass metrics). The results indicate an adequate capacity of the model to differentiate complex clinical profiles with a performance superior to that of traditional binary classification methods. Conclusions: Use of accessible and clinically interpretable psychometric variables enhances the applicability of the tool in real-world healthcare settings with limited access to resources and specialized professionals. ML is a promising complementary tool for ADHD detection. External validation is needed to confirm its generalizability across different populations and clinical contexts.

This study investigates the impact of English conversational clubs on speech anxiety in eleventhgrade EFL students at a public school in Medellín. Using a qualitative case study approach, data was collected through conversation clubs, interviews, and focus groups with six students. The findings reveal that while speech anxiety negatively affects language acquisition, its impact can be mitigated by engaging students in topics of personal interest and implementing varied communicative activities. Students exposed to these methods demonstrated increased confidence, improved participation, and enhanced linguistic skills. The study concludes that conversational clubs serve as effective tools for reducing speech anxiety by fostering a relaxed and interactive learning environment. It recommends that EFL teachers integrate dynamic and interest-driven speaking activities to enhance student motivation and language proficiency.

Machine Learning (ML) has emerged as a powerful tool for enhancing cybersecurity, particularly in detecting phishing emails and malicious messages. Traditional methods, such as rule-based systems and blacklisting, struggle against evolving threats, whereas ML models can analyze large datasets, identify patterns, and adapt to new attack tactics. This paper explores the application of ML in phishing detection, focusing on supervised and unsupervised learning techniques, feature extraction (e.g., email content, headers, and URLs), and natural language processing (NLP) to classify malicious messages. A case study demonstrates the implementation of a Logistic Regression model trained on a labeled dataset, achieving 75.6

El neuromarketing ha transformado la forma en la que las empresas entienden y analizan el comportamiento y la toma de decisiones de los consumidores. Esta investigación realiza una revisión sistemática de literatura de 650 artículos del 2006 al 2025, indexados en las bases de datos de Web of Science y Scopus, con el propósito de explorar la evolución e identificar las perspectivas de investigación sobre el neuromarketing y la toma de decisiones. El estudio, que implementa elementos de la declaración PRISMA 2020 como guía de rigurosidad científica, hizo uso de herramientas cienciométricas como RStudio Cloud, Bibliometrix, el algoritmo del Árbol de la Ciencia y Gephi para construir el mapeo científico y el Árbol de la Ciencia, al igual que para identificar los principales clústeres de investigativos. Los resultados reflejan una tasa de crecimiento anual del 13,23% y un liderazgo geográfico de Estados Unidos, España y China, al igual que el posicionamiento de tres grandes perspectivas. La primera, centrada en la utilización de herramientas neurocientíficas para predecir comportamientos del consumidor. Las investigaciones de la segunda perspectiva se centraron en el papel de los estímulos cerebrales en las decisiones de compra, mientras que la tercera presenta una reflexión ética y crítica sobre el neuromarketing. Asimismo, se identifican líneas de investigación futura relacionadas con la integración de la inteligencia artificial y el neuromarketing, la regulación de esta disciplina y la personalización basada en datos neurocientíficos.

Alzheimer's Disease (AD) is the leading cause of dementia worldwide, yet early detection remains challenging due to limited access to biomarker-based diagnostic tools, especially in low- and middle-income countries. This study aims to evaluate the diagnostic accuracy of NavegApp, a serious game developed to assess Spatial Cognition (SC), in distinguishing individuals at various stages of AD, including asymptomatic and symptomatic PSEN1-E280A mutation carriers. A cross-sectional sample of 226 participants underwent neurological and neuropsychological evaluations alongside NavegApp targeting allocentric navigation, mental rotation, and visuospatial memory. Results showed excellent diagnostic accuracy for distinguishing symptomatic PSEN1-E280A carriers from asymptomatic carriers and healthy controls, particularly in allocentric navigation metrics (AUC-ROC = 0.94-0.97). However, in asymptomatic participants, diagnostic performance was modest (AUC ≈ 0.57-0.60), indicating limited discriminative capacity at the preclinical stage. Cross-sectional comparisons detected prodromal-stage deficits in visuospatial and mental rotation tasks, whereas diagnostic accuracy for distinguishing sporadic MCI from health controls was moderate to low. These findings demonstrate the feasibility of NavegApp as a digital tool for cognitive assessment, with potential applicability in cognitive screening for underserved communities. Further research must validate its use across diverse settings and establish its integration into clinical practice for early AD detection.