Artículos y papers

URI permanente para esta colección

Examinar

Envíos recientes

Mostrando 1 - 20 de 4068
  • Publicación
    Ocio, Prevención del Bullying y Ciberbullying en Adolescentes: una Revisión Sistemática
    (Universidad de Almería, 2025-04-01) Díaz Esterri, Jorge; Galán Casado, Diego Antonio; Juanas Oliva, Ángel de; García Castilla, Francisco Javier
    Introducción. El bullying y el ciberbullyng atenta contra la identidad de las personas adolescentes que lo sufren. Este fenómeno multidimensional se produce, entre el grupo de iguales, en diversos entornos de interacción más allá de los contextos de aula. Además, presenta diferentes factores de riesgo relacionados con los espacios y actividades de ocio, los cuales, en muchos casos, poseen un alto potencial preventivo durante la adolescencia. Método. Este artículo presenta una revisión sistemática sobre explora los factores de riesgo y protección vincluados a los espacios y actividades de ocio que ocupan el tiempo libre de las personas adolescentes en relación con el bullying y ciberbullying. Para ello, se adoptó una metodología cualitativa que incluyó la identificación sistemática, el análisis y la síntesis de contenidos relevantes de publicaciones científicas basada en las directrices PRISMA. Resultados. Se llevó a cabo una búsqueda estructurada que abarcó estudios revisados por pares en las siguientes bases de datos: Dialnet, Scopus, Web of Science, y EbscoHOST. A partir de una exploración inicial de 513 resultados, se seleccionaron finalmente 14 manuscritos. Los principales resultados refieren una estrecha relación entre el ocio digital, el ciberacoso y la cibervictimización. También se destaca la relación entre el acoso escolar y otras actividades de ocio consideradas como nocivas como es el caso del consumo de alcohol o el consumo excesivo de televisión u otros medios de comunicación. Asimismo, los niños y adolescentes acosados tenían hasta cuatro veces más probabilidades que sus compañeros no acosados de tener problemas de salud mental con repercusiones negativas en su vida cotidiana, en las relaciones con los amigos, en el aprendizaje en la escuela o en las actividades de ocio. Por su parte, el ocio compartido con los padres reducía la probabilidad de victimización y actividades como la lectura o el desarrollo de actividad física, minimizaban la posibilidad de ser agresor o víctima. Discusión y conclusiones. Los resultados sugieren la proliferación de un amplio número de investigaciones sobre la temática abordada cuya transferencia puede contribuir a la fundamentación de intervenciones socioeducativas mediante actividades de ocio para la prevención del bullying y el ciberbullying en la adolescencia.
  • Publicación
    Influence of Age, Gender and Years of Experience on Teachers in Promoting Strategies for Digital Sustainability and Data Protection
    (Springer Nature, 2023-07-15) Vázquez Cano, Esteban; Sáez López, José Manuel; Grimaldo Santamaría, Rolando Óscar; Quicios García, Mª Del Pilar
    The aim of this research was to know how widespread the activities were, and to what extent they were being implemented, in relation to data protection and digital sustainability in Primary Education schools. This study also analyzed whether teachers’ age, gender and years of experience in the profession influenced the development of this type of practices among students. To this end, the GAUBIPRO (4150516/6) questionnaire, registered at the Spanish Patent and Trademark Office, was sent out to 308 Spanish teachers in Primary Education in Spain. The investigation was conducted by applying three multivariate statistical procedures: chi-squared with Kendall’s Tau-c coefficient, variance analysis using a single-factor ANOVA, and the HJ-Plot method, to find patterns of group behavior among the variables studied. The results showed that age, gender and years of experience were significant variables in the development of strategies for data protection and digital sustainability in Primary Education. For years of experience, the results showed that teachers with the highest mean number of years in the teaching profession were the least likely to apply data protection protocols. Male teachers were found to promote more general data protection strategies, while female teachers were more active in the design and use of activities in the classroom. In terms of age, the results clearly demonstrated that the higher the mean age of the teachers, the lower the rate of application of actions to promote data protection and digital security among young students, in three variables in particular: “foster strategies”, “advise students” and “inform families”.
  • Publicación
    Latent factors on the design and adoption of gamified apps in primary education
    (Springer, 2023-04-25) Vázquez Cano, Esteban; Fombona, Javier; Rodríguez Arce, Jorge; Quicios García, Mª Del Pilar
    The main objective of this research is to determine the perception of teachers about the elements that increases the educational effectiveness of gamified apps in primary education. A methodology based on an importance-performance analysis was daeveloped, using a structural equations model to calcuate the degree of importance of each variable. The sample was formed of 212 Spanish teachers with experience using educational apps in the teaching–learning process. Six categories were identified as precursors of educational effectiveness: (1) curriculum connection, (2) feedback and operational experience, (3) assessment and learning analytics, (4) sustainability (Protection Personal data), (5) equal access and (6) flow. These six categories enhance the three traditional areas of gamification intervention: cognitive, emotional and social. In this sense, the design and adoption of an educational gamified app should: (1) establish a clear link between the game and curricular content and competence development; (2) promote self-regulated learning through individual and collaborative activities; (3) offer adapted learning by integrating differentiated personalized learning pathways; (4) integrate learning analytics that can be consulted by teacher, student and family; (5) comply with data protection regulation and promote a safe, sustainable and ethical use of the information generated; (6) take into account different levels of functional diversity. When the gamified app design incorporates these attributes, primary education teachers perceive that such resources can be integrated effectively into the teaching–learning processes.
  • Publicación
    Pervasiveness of the p-Laplace operator under localization of fractional g-Laplace operators
    (Biemdas Academic Publishers, 2025-06-01) Ortega García, Alejandro
    In this paper, we analyze the behavior of the truncated functionals as (Formula presented) for δ → 0+, where G is an Orlicz function which is assumed to be regularly varying at 0. A prototype of such function is given by G(t) = tp(1+ |log(t)|) with p ≥ 2. These kinds of functionals arise naturally in peridynamics, where long-range interactions are neglected and only those that exerted at distance smaller than δ > 0 are taken into account, i.e., the horizon δ > 0 represents the range of interactions or nonlocality. This paper is inspired by the celebrated result by Bourgain, Brezis and Mironescu, who analyzed the limit s → 1− with G(t) = tp. In particular, we prove that, under appropriate conditions, (Formula presented) for p = index(G) and an explicit constant KN,p > 0. Moreover, the converse is also true if the above localization limit exist as δ → 0+, and the Orlicz function G is a regularly varying function with index(G) = p.
  • Publicación
    On the Robin function for the fractional Laplacian on symmetric domains
    (Springer Nature, 2024-01-04) Ortega García, Alejandro
    In this work we prove, under symmetry and convexity assumptions on the domain Ω, the non-degeneracy at zero of the Hessian matrix of the Robin function for the spectral fractional Laplacian. This work extends to the fractional setting the results of M. Grossi concerning the classical Laplace operator.
  • Publicación
    Nonlinear elliptic systems involving Hardy-Sobolev Criticalities
    (Springer, 2023-08-23) López-Soriano, Rafael; Ortega García, Alejandro
    This paper is focused on the solvability of a family of nonlinear elliptic systems defined in RN . Such equations contain Hardy potentials and Hardy–Sobolev criticalities coupled by a possible critical Hardy–Sobolev term. That problem arises as a generalization of Gross–Pitaevskii and Bose–Einstein type systems. By means of variational techniques, we shall find ground and bound states in terms of the coupling parameter ν and the order of the different parameters and exponents. In particular, for a wide range of parameters we find solutions as minimizers or Mountain–Pass critical points of the energy functional on the underlying Nehari manifold.
  • Publicación
    Subcritical nonlocal problems with mixed boundary conditions
    (World Scientific Publishing, 2014-01) Molica Bisci, Giovanni; Ortega García, Alejandro; Luca Vilasi
    By using linking and ∇-theorems in this paper we prove the existence of multiple solutions for the following nonlocal problem with mixed Dirichlet–Neumann boundary data, (Formular Presented) where (−Δ)s, s ∈ (1/2, 1), is the spectral fractional Laplacian operator, Ω ⊂ RN, N > 2s, is a smooth bounded domain, λ > 0 is a real parameter, ν is the outward normal to ∂Ω, ΣD, ΣN are smooth (N − 1)-dimensional submanifolds of ∂Ω such that ΣD ∪ ΣN = ∂Ω, ΣD ∩ ΣN = ∅ and ΣD ∩ ΣN = Γ is a smooth (N − 2)-dimensional submanifold of ∂Ω.
  • Publicación
    El estado de la cuestión en torno a la represión y depuración franquistas del Magisterio canario (1936-1943)
    (José Miguel Rodríguez Yanes, 2024) Negrín Fajardo, Olegario
    Este artículo tiene el objetivo central de dar a conocer las principales publicaciones que se han hecho acerca de la represión franquista en general, y de la depuración del profesorado canario de primera enseñanza en particular. Nos referimos a libros, capítulos de libros, artículos de revistas especializadas y comunicaciones y ponencias en congresos, que se han ocupado de desentrañar la aplicación de la maquinaria represiva franquista, que en el ámbito de la enseñanza del Magisterio se caracterizó por aplicar unos protocolos de persecución y aniquilación de todo lo que recordara a la enseñanza de la II República, a la Escuela Nueva, la masonería o a la Institución Libre de Enseñanza. La finalidad manifiesta era apartar de la carrera docente a todos los educadores que por sus antecedentes no fueran proclives a la política educativa del nacional catolicismo franquista, impuesta por los vencedores de la guerra civil, al tiempo que se planificaba el nuevo sistema educativo con los enseñantes apropiados para poner en valor una educación conservadora simbolizada por la alianza de la espada y la cruz.
  • Publicación
    ¿Qué papel juegan los partidos políticos en las protestas sociales? Tendencias recientes en Argentina y Chile
    (Universidad del Rosario (Colombia), 2024) Donoso, Sofia; Somma, Nicolás M.; Rossi, Federico M.; https://orcid.org/0000-0001-5053-0198; https://orcid.org/0000-0001-8717-3868
    Existe un consenso cada vez mayor sobre la naturaleza complementaria de la política institucional y no institucional como medio para impulsar las agendas políticas. Sin embargo, la mayor parte de la investigación tiende a concentrarse en un aspecto de esta relación, a saber, cómo los movimientos sociales influyen en la arena política, por ejemplo, impactando diferentes etapas del proceso de formulación de políticas y creando nuevos partidos políticos. Hay comparativamente menos comprensión de la dinámica inversa: el grado en que los partidos políticos también influyen en el ámbito de la protesta al adoptar y utilizar estrategias y tácticas —comúnmente asociadas con los movimientos sociales— y al conectarse con los manifestantes. Centrándose en Argentina y Chile, dos países que han experimentado oleadas masivas de protestas en los últimos años, este artículo examina la presencia de los partidos políticos en la organización, realización y canalización de manifestaciones. La recepción de los partidos políticos en las manifestaciones está estrechamente ligada a si son bienvenidos o no en el ámbito de la protesta. También analizamos cómo los manifestantes argentinos y chilenos perciben a los partidos políticos y el nivel de identificación que sienten con ellos. Nuestra principal fuente de datos proviene de 1 935 encuestas realizadas como parte de la red Caught in the Act of Protest: Contextualizing Contestation (CCC) entre 2015 y 2017. Encontramos que los partidos políticos en Argentina exhiben vínculos más fuertes con los movimientos sociales en comparación con los de Chile. Buscamos vincular este resultado con patrones divergentes e históricamente arraigados de dinámicas de protesta en ambos países y discutimos las implicaciones de nuestros hallazgos en la conclusión.
  • Publicación
    Grievance Politics and Technocracy in a Developmental State: Healthcare Policy Reforms in Singapore
    (Wiley, 2024) Naqvi, Ijlal; Rossi, Federico M.; Kay Jin Tan, Rayner; https://orcid.org/0000-0001-7351-8482; https://orcid.org/0000-0002-9188-3368
    This article uses a process-tracing approach to understand changes in Singapore's health sector from the start of self-rule in 1959 to the end of the COVID-19 pandemic in 2022. Singapore is a developmental state recognized for its effective management of healthcare costs and its lack of political freedom. In both respects, the ‘Singapore model’ is of interest to other cities and nations. The standard narrative is one of technocratic proficiency in a context in which civic freedoms are heavily constrained, but this article identifies the surprisingly important role of social voices at key moments. It finds episodes in which effective changes to social policies are not the product of a state embedded in an organized society, but rather are influenced by the independent organizational capacity of certain social groups providing inputs to state elites on social grievances and policy needs. Effective policy changes require a responsive state elite that — even if it is technocratically dominated, as is the case in Singapore — can listen to social claims and provide answers that are not repressive. The article conceptualizes these dynamics as ‘grievance politics’ and shows their role in explaining health reforms. It contributes to understanding global health systems and policy making in developmental states by a fruitful cross-fertilization with social movement studies.
  • Publicación
    Juan Millares Carló, profesor grancanario de Segunda Enseñanza, una carrera truncada por la depuración franquista
    (Departamento de Ediciones del Cabildo de Gran Canaria, 2018-02-02) Negrín Fajardo, Olegario
    Este artículo tiene por objeto el análisis y valoración del proceso de depuración abierto al profesor grancanario Juan Millares Carló (1895-1965) en julio de 1937, como docente del Instituto de Arrecife de Lanzarote en el momento del levantamiento militar de 1936, y que culminó con su expulsión de la enseñanza por una Orden Ministerial de mayo de 1939. Aunque mucho más tarde se le permitió reingresar en la enseñanza oficial, se puede decir que el franquismo acabó con su carrera, le perjudicó gravemente a él y a su familia desde el punto de vista social y económico, y todo ello basándose en unas acusaciones sectarias fabricadas por miembros de las fuerzas vivas más reaccionarias del momento. En todo ese periodo de sufrimiento, Juan Millares Carló consiguió sacar adelante a su amplia familia sin dejar de escribir y de enseñar manteniendo intacta la esencia de sus ideales.
  • Publicación
    Democracy as a trust-building learning process: Organizational dilemmas in social movements
    (Sage Journals, 2024) Rossi, Federico M.
    Combining agonistic pluralism and social movements literature with trust studies, I propose a conceptualization for how the organizational dilemma is tackled in social movements. Defined as a trust-building organizational learning process, I show the role-played by social trust—meaning, the construction of the relational boundaries of a shared goal without diluting the heterogeneity of self-identities and interests—as an organizational prerequisite for democratic organization of a political group. Empirically, I identify four alternative pathways to the (democratic) organizational dilemma: innovation through new organizational models; repetition of past experiences; reformulation of practices; and emulation of previous organizational models.
  • Publicación
    A review on segmentation of knee articular cartilage: from conventional methods towards deep learning
    (Elsevier, 2020-06) Ebrahimkhani, Somayeh; Jaward, Mohamed Hisham; Cicuttini, Flavia M.; Dharmaratne, Anuja; Wang, Yuanyuan; García Seco de Herrera, Alba
    In this paper, we review the state-of-the-art approaches for knee articular cartilage segmentation from conventional techniques to deep learning (DL) based techniques. Knee articular cartilage segmentation on magnetic resonance (MR) images is of great importance in early diagnosis of osteoarthritis (OA). Besides, segmentation allows estimating the articular cartilage loss rate which is utilised in clinical practice for assessing the disease progression and morphological changes. It has been traditionally applied in quantifying longitudinal knee OA progression pattern to detect and assess the articular cartilage thickness and volume. Topics covered include various image processing algorithms and major features of different segmentation techniques, feature computations and the performance evaluation metrics. This paper is intended to provide researchers with a broad overview of the currently existing methods in the field, as well as to highlight the shortcomings and potential considerations in the application at clinical practice. The survey showed that state-of-the-art techniques based on DL outperform the other segmentation methods. The analysis of the existing methods reveals that integration of DL-based algorithms with other traditional model-based approaches has achieved the best results (mean Dice similarity coefficient (DSC) between 85.8% and 90%).
  • Publicación
    Trust and social movements: A new research agenda
    (Sage Journals, 2024) Weipert-Fenner, Irene; Rossi, Federico M.; Sika, Nadine; Wolff, Jonas; https://orcid.org/0000-0003-1225-5230; https://orcid.org/0000-0002-7348-7206
    Social movement studies clearly suggest that trust matters for processes of social mobilization: When engaging in costly, and potentially risky, contentious collective action on a common goal, activists and groups rely on the expectation that fellow protestors and allies will not fail them. To date, however, we lack research that explains which types of trust shape the emergence and evolution of social movements. Trust, we argue, is not simply an independent variable influencing mobilization, but is itself shaped—built, stabilized, weakened, or even destroyed—over the course of collective contentious action. To set the stage for a corresponding research agenda, this introduction to the special issue “Trust and Social Movements” bridges the gap between research on trust and social movement studies and clarifies the complex conceptual relationship between various types of trust and the dynamics of social mobilization. Furthermore, we identify overarching research questions, summarize the contributions to the special issue, and discuss key findings.
  • Publicación
    Leveraging AI and patient metadata to develop a novel risk score for skin cancer detection
    (Nature Research, 2024-09-06) Islam, Shafiqul; Wishart, Gordon C.; Walls, Joseph; Hall, Per; García Seco de Herrera, Alba; Gan, John Q.; Raza, Haider
    Melanoma of the skin is the 17th most common cancer worldwide. Early detection of suspicious skin lesions (melanoma) can increase 5-year survival rates by 20%. The 7-point checklist (7PCL) has been extensively used to suggest urgent referrals for patients with a possible melanoma. However, the 7PCL method only considers seven meta-features to calculate a risk score and is only relevant for patients with suspected melanoma. There are limited studies on the extensive use of patient metadata for the detection of all skin cancer subtypes. This study investigates artificial intelligence (AI) models that utilise patient metadata consisting of 23 attributes for suspicious skin lesion detection. We have identified a new set of most important risk factors, namely “C4C risk factors”, which is not just for melanoma, but for all types of skin cancer. The performance of the C4C risk factors for suspicious skin lesion detection is compared to that of the 7PCL and the Williams risk factors that predict the lifetime risk of melanoma. Our proposed AI framework ensembles five machine learning models and identifies seven new skin cancer risk factors: lesion pink, lesion size, lesion colour, lesion inflamed, lesion shape, lesion age, and natural hair colour, which achieved a sensitivity of 80.46 ± 2.50% and a specificity of 62.09 ± 1.90% in detecting suspicious skin lesions when evaluated using the metadata of 53,601 skin lesions collected from different skin cancer diagnostic clinics across the UK, significantly outperforming the 7PCL-based method (sensitivity 68.09 ± 2.10%, specificity 61.07 ± 0.90%) and the Williams risk factors (sensitivity 66.32 ± 1.90%, specificity 61.71 ± 0.6%). Furthermore, through weighting the seven new risk factors we came up with a new risk score, namely “C4C risk score”, which alone achieved a sensitivity of 76.09 ± 1.20% and a specificity of 61.71 ± 0.50%, significantly outperforming the 7PCL-based risk score (sensitivity 73.91 ± 1.10%, specificity 49.49 ± 0.50%) and the Williams risk score (sensitivity 60.68 ± 1.30%, specificity 60.87 ± 0.80%). Finally, fusing the C4C risk factors with the 7PCL and Williams risk factors achieved the best performance, with a sensitivity of 85.24 ± 2.20% and a specificity of 61.12 ± 0.90%. We believe that fusing these newly found risk factors and new risk score with image data will further boost the AI model performance for suspicious skin lesion detection. Hence, the new set of skin cancer risk factors has the potential to be used to modify current skin cancer referral guidelines for all skin cancer subtypes, including melanoma.
  • Publicación
    ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset
    (Nature Research, 2024-06-24) Rückert, Johannes; Bloch, Louise; Brünge, Raphael; Idrissi-Yaghir, Ahmad; Schäfer, Henning; Schmidt, Cynthia S.; Koitka, Sven; Pelka, Obioma; Ben Abacha, Asma; García Seco de Herrera, Alba; Müller, Henning; Horn, Peter A.; Nensa, Felix; Friedrich, Christoph M.; https://orcid.org/0000-0002-5038-5899; https://orcid.org/0000-0001-7540-4980; https://orcid.org/0000-0002-6046-4048; https://orcid.org/0000-0003-1507-9690; https://orcid.org/0000-0002-4123-0406; https://orcid.org/0000-0003-1994-0687; https://orcid.org/0000-0001-9704-1180; https://orcid.org/0000-0001-5156-4429
    Automated medical image analysis systems often require large amounts of training data with high quality labels, which are difficult and time consuming to generate. This paper introduces Radiology Object in COntext version 2 (ROCOv2), a multimodal dataset consisting of radiological images and associated medical concepts and captions extracted from the PMC Open Access subset. It is an updated version of the ROCO dataset published in 2018, and adds 35,705 new images added to PMC since 2018. It further provides manually curated concepts for imaging modalities with additional anatomical and directional concepts for X-rays. The dataset consists of 79,789 images and has been used, with minor modifications, in the concept detection and caption prediction tasks of ImageCLEFmedical Caption 2023. The dataset is suitable for training image annotation models based on image-caption pairs, or for multi-label image classification using Unified Medical Language System (UMLS) concepts provided with each image. In addition, it can serve for pre-training of medical domain models, and evaluation of deep learning models for multi-task learning.
  • Publicación
    Boletín de la Sociedad de Lógica, Metodología y Filosofía de la Ciencia en España, num. 4, mayo 1994
    (Sociedad de Lógica, Metodología y Filosofía de la ciencia en España, 1994-05) Sociedad de Lógica, Metodología y Filosofía de la Ciencia en España, SLMFCE
  • Publicación
    An OCR Post-Correction Approach Using Deep Learning for Processing Medical Reports
    (Institute of Electrical and Electronics Engineers, 2021-06-08) Karthikeyan, Srinidhi; García Seco de Herrera, Alba; Doctor, Faiyaz; Mirza, Asim; https://orcid.org/0000-0001-6863-0760; https://orcid.org/0000-0002-6509-5325; https://orcid.org/0000-0002-8412-5489
    According to a recent Deloitte study, the COVID-19 pandemic continues to place a huge strain on the global health care sector. Covid-19 has also catalysed digital transformation across the sector for improving operational efficiencies. As a result, the amount of digitally stored patient data such as discharge letters, scan images, test results or free text entries by doctors has grown significantly. In 2020, 2314 exabytes of medical data was generated globally. This medical data does not conform to a generic structure and is mostly in the form of unstructured digitally generated or scanned paper documents stored as part of a patient’s medical reports. This unstructured data is digitised using Optical Character Recognition (OCR) process. A key challenge here is that the accuracy of the OCR process varies due to the inability of current OCR engines to correctly transcribe scanned or handwritten documents in which text may be skewed, obscured or illegible. This is compounded by the fact that processed text is comprised of specific medical terminologies that do not necessarily form part of general language lexicons. The proposed work uses a deep neural network based self-supervised pre-training technique: Robustly Optimized Bidirectional Encoder Representations from Transformers (RoBERTa) that can learn to predict hidden (masked) sections of text to fill in the gaps of non-transcribable parts of the documents being processed. Evaluating the proposed method on domain-specific datasets which include real medical documents, shows a significantly reduced word error rate demonstrating the effectiveness of the approach.
  • Publicación
    Anthropometric Ratios for Lower-Body Detection Based on Deep Learning and Traditional Methods
    (MDPI, 2022-03-04) Jaruenpunyasak, Jermphiphut; García Seco de Herrera, Alba; Duangsoithong, Rakkrit
    Lower-body detection can be useful in many applications, such as the detection of falling and injuries during exercises. However, it can be challenging to detect the lower-body, especially under various lighting and occlusion conditions. This paper presents a novel lower-body detection framework using proposed anthropometric ratios and compares the performance of deep learning (convolutional neural networks and OpenPose) and traditional detection methods. According to the results, the proposed framework helps to successfully detect the accurate boundaries of the lower-body under various illumination and occlusion conditions for lower-limb monitoring. The proposed framework of anthropometric ratios combined with convolutional neural networks (A-CNNs) also achieves high accuracy (90.14%), while the combination of anthropometric ratios and traditional techniques (A-Traditional) for lower-body detection shows satisfactory performance with an averaged accuracy (74.81%). Although the accuracy of OpenPose (95.82%) is higher than the A-CNNs for lower-body detection, the A-CNNs provides lower complexity than the OpenPose, which is advantageous for lower-body detection and implementation on monitoring systems.
  • Publicación
    Effect of data leakage in brain MRI classification using 2D convolutional neural networks
    (Nature Research, 2021-11-19) Yagis, Ekin; Workalemahu Atnafu, Selamawet; García Seco de Herrera, Alba; Marzi, Chiara; Scheda, Riccardo; Giannelli, Marco; Tessa, Carlo; Citi, Luca; Diciotti, Stefano
    In recent years, 2D convolutional neural networks (CNNs) have been extensively used to diagnose neurological diseases from magnetic resonance imaging (MRI) data due to their potential to discern subtle and intricate patterns. Despite the high performances reported in numerous studies, developing CNN models with good generalization abilities is still a challenging task due to possible data leakage introduced during cross-validation (CV). In this study, we quantitatively assessed the effect of a data leakage caused by 3D MRI data splitting based on a 2D slice-level using three 2D CNN models to classify patients with Alzheimer’s disease (AD) and Parkinson’s disease (PD). Our experiments showed that slice-level CV erroneously boosted the average slice level accuracy on the test set by 30% on Open Access Series of Imaging Studies (OASIS), 29% on Alzheimer’s Disease Neuroimaging Initiative (ADNI), 48% on Parkinson’s Progression Markers Initiative (PPMI) and 55% on a local de-novo PD Versilia dataset. Further tests on a randomly labeled OASIS-derived dataset produced about 96% of (erroneous) accuracy (slice-level split) and 50% accuracy (subject-level split), as expected from a randomized experiment. Overall, the extent of the effect of an erroneous slice-based CV is severe, especially for small datasets.