Albert Sesé
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Albert Sesé has a total of 143 co-authors. Here are the top co-authors by number of shared publications:
- Juan José Montaño
University of the Balearic Islands
10 shared publications - Rafael Jiménez
University of the Balearic Islands (UIB), Palma, Spain
9 shared publications - José Miguel Morales-Asencio
Department of Nursing, Faculty of Health Sciences, University of Malaga, 29071 Malaga, Spain
7 shared publications Alfonso Palmer
6 shared publications- Miquel Bennasar-Veny
Research Group on Global Health, University of the Balearic Islands, Palma, Spain; Research Group on Nursing, Community and Global Health, Health Research Institute of the Balearic Islands (IdISBa), Palma, Spain; Department of Nursing and Physiotherapy, University of the Balearic Islands, Palma, Spain; Centre for Biomedical Research Network (CIBER) in Epidemiology and Public Health (CIBERESP), Madrid, Spain
5 shared publications - Elena Gervilla
University of the Balearic Islands
4 shared publications
Latest Publications
- Open Access
- 15 October 2026
- Published by Wiley in Journal of Evaluation in Clinical Practice
- Vol. 32 (7) , e70668
Defining Core Evidence‐Based Practice Knowledge for Health Professionals: A Delphi Consensus Study
Rationale, Aims and Objectives: A clearly defined content domain is needed to assess whether health professionals possess the conceptual knowledge required for Evidence‐Based Practice (EBP). Existing competency frameworks and assessment instruments often combine knowledge with skills, attitudes and behaviours, limiting the identification of specific knowledge deficits. This study aimed to define the core EBP knowledge domain and obtain content validity evidence for a taxonomy applicable across health professions. Method: The study comprised three phases. First, two structured literature reviews identified relevant EBP competency frameworks and knowledge assessment instruments. These findings informed the operational definition of the EBP knowledge construct and the development of a preliminary seven‐dimension taxonomy. Content validity was then examined through a two‐round Delphi study. Eighteen experts participated in the first round and 17 in the second. Panellists rated the adequacy and relevance of each dimension and content area using a six‐point Likert scale and provided qualitative feedback. Agreement was defined as the proportion of experts assigning a score of 5 or 6, with a retention threshold of at least 80% for both criteria. Results: After the first Delphi round, several areas were reformulated, redistributed or removed to reduce conceptual overlap, and two dimensions were eliminated. In the second round, all retained dimensions and areas reached the agreement threshold except one newly introduced area, which was removed. The final taxonomy comprised 15 content areas organised into five dimensions: clinical question formulation, scientific literature search, critical appraisal, evidence implementation and knowledge translation, and evaluation of the EBP process. Conclusion: The taxonomy provides a consensus‐informed representation of core EBP knowledge and distinguishes conceptual knowledge from broader professional competence. It offers a basis for future objective assessment development and for identifying knowledge gaps in EBP training and implementation initiatives.
- 15 October 2026
- Published by Wiley in Journal of Evaluation in Clinical Practice
- Vol. 32 (7) , e70668
Open AccessDefining Core Evidence‐Based Practice Knowledge for Health Professionals: A Delphi Consensus Study
Rationale, Aims and Objectives: A clearly defined content domain is needed to assess whether health professionals possess the conceptual knowledge required for Evidence‐Based Practice (EBP). Existing competency frameworks and assessment instruments often combine knowledge with skills, attitudes and behaviours, limiting the identification of specific knowledge deficits. This study aimed to define the core EBP knowledge domain and obtain content validity evidence for a taxonomy applicable across health professions. Method: The study comprised three phases. First, two structured literature reviews identified relevant EBP competency frameworks and knowledge assessment instruments. These findings informed the operational definition of the EBP knowledge construct and the development of a preliminary seven‐dimension taxonomy. Content validity was then examined through a two‐round Delphi study. Eighteen experts participated in the first round and 17 in the second. Panellists rated the adequacy and relevance of each dimension and content area using a six‐point Likert scale and provided qualitative feedback. Agreement was defined as the proportion of experts assigning a score of 5 or 6, with a retention threshold of at least 80% for both criteria. Results: After the first Delphi round, several areas were reformulated, redistributed or removed to reduce conceptual overlap, and two dimensions were eliminated. In the second round, all retained dimensions and areas reached the agreement threshold except one newly introduced area, which was removed. The final taxonomy comprised 15 content areas organised into five dimensions: clinical question formulation, scientific literature search, critical appraisal, evidence implementation and knowledge translation, and evaluation of the EBP process. Conclusion: The taxonomy provides a consensus‐informed representation of core EBP knowledge and distinguishes conceptual knowledge from broader professional competence. It offers a basis for future objective assessment development and for identifying knowledge gaps in EBP training and implementation initiatives.
- Open Access
- 21 September 2026
- Published by Wiley in Family Process
- Vol. 65 (3) , e70198
User Profiles in Supervised Family Centers and Their Relationship With Childhood Symptomatology
High‐intensity interparental conflict constitutes a major risk factor for children's emotional and behavioral adjustment, especially in families using Supervised Family Centers (SFCs) after separation or divorce. This study aimed to identify parental profiles among SFC users in Spain and to examine their association with children's internalizing and externalizing symptoms over time. A person‐centered latent profile analysis was conducted on 504 separated parents (54.8% mothers) from 10 autonomous communities, with 84 participants completing the 1‐year follow‐up. Measures included interparental conflict, co‐parenting, family violence, parental physical and psychological symptoms, and resilience. Three profiles emerged: (1) moderate conflict and resilience, (2) adaptive adjustment with low conflict and moderate co‐parenting quality, and (3) high conflict and symptomatology. Children of parents in the third profile presented significantly higher levels of emotional distress, peer difficulties, and child‐to‐parent violence ( p < 0.001). Longitudinal analyses showed no significant changes in symptomatology over 1 year, with minor improvements in emotional sensitivity among children in families with an adaptive profile. The findings highlight the interplay between interparental conflict, parental well‐being, and co‐parenting dynamics in shaping children's outcomes. From a theoretical standpoint, results emphasize the need to understand children's distress within systemic family frameworks. In practice, they underscore the importance of implementing early, comprehensive assessments in the SFCs to identify high‐risk families and design tailored interventions to reduce children's symptoms.
- 21 September 2026
- Published by Wiley in Family Process
- Vol. 65 (3) , e70198
Open AccessUser Profiles in Supervised Family Centers and Their Relationship With Childhood Symptomatology
High‐intensity interparental conflict constitutes a major risk factor for children's emotional and behavioral adjustment, especially in families using Supervised Family Centers (SFCs) after separation or divorce. This study aimed to identify parental profiles among SFC users in Spain and to examine their association with children's internalizing and externalizing symptoms over time. A person‐centered latent profile analysis was conducted on 504 separated parents (54.8% mothers) from 10 autonomous communities, with 84 participants completing the 1‐year follow‐up. Measures included interparental conflict, co‐parenting, family violence, parental physical and psychological symptoms, and resilience. Three profiles emerged: (1) moderate conflict and resilience, (2) adaptive adjustment with low conflict and moderate co‐parenting quality, and (3) high conflict and symptomatology. Children of parents in the third profile presented significantly higher levels of emotional distress, peer difficulties, and child‐to‐parent violence ( p < 0.001). Longitudinal analyses showed no significant changes in symptomatology over 1 year, with minor improvements in emotional sensitivity among children in families with an adaptive profile. The findings highlight the interplay between interparental conflict, parental well‐being, and co‐parenting dynamics in shaping children's outcomes. From a theoretical standpoint, results emphasize the need to understand children's distress within systemic family frameworks. In practice, they underscore the importance of implementing early, comprehensive assessments in the SFCs to identify high‐risk families and design tailored interventions to reduce children's symptoms.
- 30 August 2026
- Published by Grupo Editorial Psicofundación in Psicothema
- Vol. 38 (4) , 213-223
Psychometric Evaluation and Normative Framework for the Movie for the Assessment of Social Cognition in Spanish-Speaking Adults
Background: The Movie for the Assessment of Social Cognition-Spanish (MASC-SP) assesses general mentalization performance and associated error patterns: over-mentalization, under-mentalization, and non-mentalization. This study aims to provide the first large-scale psychometric evaluation and normative framework for MASC-SP scores in Spanish-speaking adults. Method: 2,582 healthy adults completed the MASC-SP via a secure online platform. The psychometric evaluation included factor analysis, measurement invariance, internal consistency, and floor/ceiling effects. Normative data were stratified by demographic variables and are presented as empirical percentiles and z-scores. Results: MASC-SP scores showed a predominantly unifactorial structure, with internal consistency ranging from questionable to good. A floor effect was observed in the non-mentalization error score. Female participants and those with a university education scored higher and made fewer errors than men and those without a university education. Age-related results were heterogeneous. Conclusions: The results support interpreting the MASC-SP total score as a robust quantitative indicator of general mentalization performance and the error scores as secondary qualitative indicators of different error patterns. Normative data stratified by sex and educational level provide a useful reference for research and clinical settings. However, norms stratified by age groups should be applied with caution due to their questionable clinical and developmental relevance.
- 30 August 2026
- Published by Grupo Editorial Psicofundación in Psicothema
- Vol. 38 (4) , 213-223
Psychometric Evaluation and Normative Framework for the Movie for the Assessment of Social Cognition in Spanish-Speaking Adults
Background: The Movie for the Assessment of Social Cognition-Spanish (MASC-SP) assesses general mentalization performance and associated error patterns: over-mentalization, under-mentalization, and non-mentalization. This study aims to provide the first large-scale psychometric evaluation and normative framework for MASC-SP scores in Spanish-speaking adults. Method: 2,582 healthy adults completed the MASC-SP via a secure online platform. The psychometric evaluation included factor analysis, measurement invariance, internal consistency, and floor/ceiling effects. Normative data were stratified by demographic variables and are presented as empirical percentiles and z-scores. Results: MASC-SP scores showed a predominantly unifactorial structure, with internal consistency ranging from questionable to good. A floor effect was observed in the non-mentalization error score. Female participants and those with a university education scored higher and made fewer errors than men and those without a university education. Age-related results were heterogeneous. Conclusions: The results support interpreting the MASC-SP total score as a robust quantitative indicator of general mentalization performance and the error scores as secondary qualitative indicators of different error patterns. Normative data stratified by sex and educational level provide a useful reference for research and clinical settings. However, norms stratified by age groups should be applied with caution due to their questionable clinical and developmental relevance.
- 24 July 2026
- Published by American Educational Research Association (AERA) in Journal of Educational and Behavioral Statistics
MLwrap: Simplifying Machine Learning Workflows in R
MLwrap is an R package that streamlines machine learning (ML) workflows, making them accessible, efficient, and reproducible, especially within the Knowledge Discovery in Databases process. It offers a unified, minimalistic interface covering all predictive modeling stages: data preprocessing, model construction, hyperparameter optimization, evaluation, and sensitivity analysis. MLwrap supports popular algorithms like Neural Networks, Support Vector Machines, Random Forests, and XGBoost Decision Trees. The workflow is organized into four core functions: preprocessing(), build_model(), fine_tuning(), and sensitivity_analysis(). These functions encapsulate the entire ML pipeline into a single, reproducible analysis object. Demonstrated via regression and classification examples, MLwrap simplifies complex tasks, providing interpretable results. It empowers analysts and researchers, particularly in health and social sciences, to efficiently extract actionable insights with transparency.
- 24 July 2026
- Published by American Educational Research Association (AERA) in Journal of Educational and Behavioral Statistics
MLwrap: Simplifying Machine Learning Workflows in R
MLwrap is an R package that streamlines machine learning (ML) workflows, making them accessible, efficient, and reproducible, especially within the Knowledge Discovery in Databases process. It offers a unified, minimalistic interface covering all predictive modeling stages: data preprocessing, model construction, hyperparameter optimization, evaluation, and sensitivity analysis. MLwrap supports popular algorithms like Neural Networks, Support Vector Machines, Random Forests, and XGBoost Decision Trees. The workflow is organized into four core functions: preprocessing(), build_model(), fine_tuning(), and sensitivity_analysis(). These functions encapsulate the entire ML pipeline into a single, reproducible analysis object. Demonstrated via regression and classification examples, MLwrap simplifies complex tasks, providing interpretable results. It empowers analysts and researchers, particularly in health and social sciences, to efficiently extract actionable insights with transparency.
- Open Access
- 16 July 2026
- Published by Frontiers Media SA in Frontiers in Nutrition
- Vol. 13, 1764935
Validity, consistency and network structure of the World Cancer Research Fund/American Institute for Cancer Research Screener in young adults
Introduction: The WCRF/AICR Screener is a validated tool for assessing adherence to the World Cancer Research Fund/American Institute for Cancer Research cancer prevention guidelines. This study aimed to evaluate its validity among young adults and examine connections between dietary variables using network analysis. Methods: Young adults ( n = 112) were recruited (mean age 24.9 years; 70.5% women) and completed the screener alongside validated assessments: bioelectrical impedance analysis, anthropometry, accelerometry, a 4-week Ecological Momentary Dietary Assessment via smartphone app, and a food frequency questionnaire. For validation, agreement [cross-classification (%), the Kappa coefficient (κ), Spearman correlation ( r ), and linear regression] was determined. Dietary network structure was evaluated using the EBICglasso analysis. Results: The WCRF/AICR Screener showed moderate-to-strong validity ( r = 0.57) and good test-retest consistency ( r = 0.73). Exploratory network analysis revealed proximity between healthier foods and separately less healthy ones. It also suggested that sugar-sweetened drinks was strongly connected to multiple dietary variables, with potential influence on the overall network. In contrast, alcohol intake was relatively isolated from the rest of the variables. Discussion: These observations support the use of the Screener for assessing cancer prevention recommendations in healthy young adults and generate exploratory hypotheses on dietary interrelationships that require confirmation in larger and more heterogeneous samples.
- 16 July 2026
- Published by Frontiers Media SA in Frontiers in Nutrition
- Vol. 13, 1764935
Open AccessValidity, consistency and network structure of the World Cancer Research Fund/American Institute for Cancer Research Screener in young adults
Introduction: The WCRF/AICR Screener is a validated tool for assessing adherence to the World Cancer Research Fund/American Institute for Cancer Research cancer prevention guidelines. This study aimed to evaluate its validity among young adults and examine connections between dietary variables using network analysis. Methods: Young adults ( n = 112) were recruited (mean age 24.9 years; 70.5% women) and completed the screener alongside validated assessments: bioelectrical impedance analysis, anthropometry, accelerometry, a 4-week Ecological Momentary Dietary Assessment via smartphone app, and a food frequency questionnaire. For validation, agreement [cross-classification (%), the Kappa coefficient (κ), Spearman correlation ( r ), and linear regression] was determined. Dietary network structure was evaluated using the EBICglasso analysis. Results: The WCRF/AICR Screener showed moderate-to-strong validity ( r = 0.57) and good test-retest consistency ( r = 0.73). Exploratory network analysis revealed proximity between healthier foods and separately less healthy ones. It also suggested that sugar-sweetened drinks was strongly connected to multiple dietary variables, with potential influence on the overall network. In contrast, alcohol intake was relatively isolated from the rest of the variables. Discussion: These observations support the use of the Screener for assessing cancer prevention recommendations in healthy young adults and generate exploratory hypotheses on dietary interrelationships that require confirmation in larger and more heterogeneous samples.
- 30 May 2026
- Published by Grupo Editorial Psicofundación in Psicothema
- Vol. 38 (3) , 149-160
The Illness Management and Recovery (IMR) Scale: A Network Analysis of User and Professional Perspectives
Background: Recovery IS a multidimensional, subjective PROCESS that emphasizes personal strategies AND empowerment beyond symptom remission. The Illness Management AND Recovery (IMR) scale incorporates the perspectives OF BOTH users AND professionals, although its internal structure has had ONLY limited examination through advanced psychometric methods. Network analysis was applied TO the IMR scale WITH the aims OF (1) exploring interrelationships among items, (2) assessing network stability, AND (3) analyzing measurement invariance BETWEEN users AND professionals. Method: DATA were collected FROM 172 users AND 49 mental health professionals USING the IMR scale. Network analysis used the Triangulated Maximally Filtered Graph (TMFG) method AND the walktrap ALGORITHM, WITH stability assessed through bootstrapping. Results: The analysis indicated 39 significant connections among 15 items, highlighting coping strategies AS the central node, along WITH symptom distress, functional difficulties, AND symptom recovery. Exploratory Graph Analysis IDENTIFIED three factors: (1) Personal Growth AND Planning, (2) Social AND Health Behavior Management, AND (3) Symptom Management AND Resilience. Conclusions: Network analysis underscores the importance OF coping strategies, suggesting that interventions should focus ON strengthening these skills TO support recovery.
- 30 May 2026
- Published by Grupo Editorial Psicofundación in Psicothema
- Vol. 38 (3) , 149-160
The Illness Management and Recovery (IMR) Scale: A Network Analysis of User and Professional Perspectives
Background: Recovery IS a multidimensional, subjective PROCESS that emphasizes personal strategies AND empowerment beyond symptom remission. The Illness Management AND Recovery (IMR) scale incorporates the perspectives OF BOTH users AND professionals, although its internal structure has had ONLY limited examination through advanced psychometric methods. Network analysis was applied TO the IMR scale WITH the aims OF (1) exploring interrelationships among items, (2) assessing network stability, AND (3) analyzing measurement invariance BETWEEN users AND professionals. Method: DATA were collected FROM 172 users AND 49 mental health professionals USING the IMR scale. Network analysis used the Triangulated Maximally Filtered Graph (TMFG) method AND the walktrap ALGORITHM, WITH stability assessed through bootstrapping. Results: The analysis indicated 39 significant connections among 15 items, highlighting coping strategies AS the central node, along WITH symptom distress, functional difficulties, AND symptom recovery. Exploratory Graph Analysis IDENTIFIED three factors: (1) Personal Growth AND Planning, (2) Social AND Health Behavior Management, AND (3) Symptom Management AND Resilience. Conclusions: Network analysis underscores the importance OF coping strategies, suggesting that interventions should focus ON strengthening these skills TO support recovery.
- Open Access
- 22 May 2026
- Published by Frontiers Media SA in Frontiers in Psychiatry
- Vol. 17, 1819456
Technology-related behavioral addiction profiles and mental health in teachers
Introduction: Teachers' mental health is increasingly challenged by ubiquitous digital demands, yet little is known about how specific constellations of online behaviors and compulsive buying cluster in this key professional group or how they map onto psychiatric symptomatology. Methods: This cross-sectional study examined problematic use of the internet, mobile phones, instant messaging, social networking sites and videogames, together with compulsive buying, in 1,043 in-service teachers from all educational stages in Spain. Participants completed validated self-report measures of problematic ICT use, compulsive buying, anxiety, depression and online vulnerability. Latent profile analysis combined with k-means clustering identified homogeneous behavioral profiles, and differences in affective symptoms and sociodemographic characteristics were tested using analysis of variance and chi-square tests. Results: Four distinct profiles emerged. A low-risk group showed minimal problematic ICT use or compulsive buying and very low levels of anxiety, depression and online vulnerability. Two intermediate groups were characterized by predominantly ICT-related risk or predominantly compulsive buying, each showing specific and clinically relevant patterns of emotional symptoms. A high-risk group, overrepresented by younger and predominantly female teachers, displayed concurrent problematic ICT use and compulsive buying together with markedly elevated anxiety, depression and online vulnerability, accounting for a large share of the variance in mental health outcomes. Younger teachers were consistently more likely to belong to the high-risk profiles that carried the greatest psychological burden. Discussion: These findings reveal substantial and clinically meaningful heterogeneity in digital and consumer risk behaviors among teachers and point to a subgroup with a profile compatible with behavioral addictions and significant psychiatric distress. The study underscores the importance of integrating digital-behavior screening into occupational mental health assessment in education and supports the development of targeted, profile-based interventions in digital literacy, emotion regulation and identity reinforcement to protect teachers' mental health in technology-rich environments.
- 22 May 2026
- Published by Frontiers Media SA in Frontiers in Psychiatry
- Vol. 17, 1819456
Open AccessTechnology-related behavioral addiction profiles and mental health in teachers
Introduction: Teachers' mental health is increasingly challenged by ubiquitous digital demands, yet little is known about how specific constellations of online behaviors and compulsive buying cluster in this key professional group or how they map onto psychiatric symptomatology. Methods: This cross-sectional study examined problematic use of the internet, mobile phones, instant messaging, social networking sites and videogames, together with compulsive buying, in 1,043 in-service teachers from all educational stages in Spain. Participants completed validated self-report measures of problematic ICT use, compulsive buying, anxiety, depression and online vulnerability. Latent profile analysis combined with k-means clustering identified homogeneous behavioral profiles, and differences in affective symptoms and sociodemographic characteristics were tested using analysis of variance and chi-square tests. Results: Four distinct profiles emerged. A low-risk group showed minimal problematic ICT use or compulsive buying and very low levels of anxiety, depression and online vulnerability. Two intermediate groups were characterized by predominantly ICT-related risk or predominantly compulsive buying, each showing specific and clinically relevant patterns of emotional symptoms. A high-risk group, overrepresented by younger and predominantly female teachers, displayed concurrent problematic ICT use and compulsive buying together with markedly elevated anxiety, depression and online vulnerability, accounting for a large share of the variance in mental health outcomes. Younger teachers were consistently more likely to belong to the high-risk profiles that carried the greatest psychological burden. Discussion: These findings reveal substantial and clinically meaningful heterogeneity in digital and consumer risk behaviors among teachers and point to a subgroup with a profile compatible with behavioral addictions and significant psychiatric distress. The study underscores the importance of integrating digital-behavior screening into occupational mental health assessment in education and supports the development of targeted, profile-based interventions in digital literacy, emotion regulation and identity reinforcement to protect teachers' mental health in technology-rich environments.
- Open Access
Identifying the key components of a diet and lifestyle screener for people living with and beyond cancer: an e-Delphi study
Objectives: There are currently no validated screeners that evaluate diet and lifestyle of people living with and beyond cancer (PLWBC). The purpose of this study was to reach a consensus among an international expert panel on the essential items to include in this type of instrument. Design: A scientific committee developed the initial list of items, which were presented to an expert panel in a two-round-modified electronic Delphi. Panellists were asked to rate the adequacy, relevance and feasibility of self-reporting each item. Qualitative assessments were encouraged. Setting: Four countries (Spain, UK, USA and Portugal). Participants: Experts working in a cancer-related health profession or cancer-related research were recruited. Main outcome measures: Items were initially categorised into seven domains (body composition, physical activity, diet, alcohol, smoking, sleep and psychosocial distress). A content validity index per item (CVI-i) and a scale-level CVI (S-CVI) were calculated (acceptable≥0.78). All items with a CVI-i≥0.78 were submitted to a final consensus meeting. Results: A total of 108 items were proposed to the panel. In Round 1, 77 items were accepted, 10 items were excluded and 6 new items were proposed. During Round 2, 4 items were accepted and 19 were excluded. Diet and alcohol were merged into one domain. The final consensus meeting decided on 61 items categorised into six domains (S-CVI:0.94): body composition, physical activity, diet and alcohol, smoking, sleep and psychosocial distress. Conclusions: We identified the main items to be considered when developing a screener to evaluate diet and lifestyle in PLWBC in a clinical setting, and the results obtained will guide the content of the screener in the following validation study.
Open AccessIdentifying the key components of a diet and lifestyle screener for people living with and beyond cancer: an e-Delphi study
Objectives: There are currently no validated screeners that evaluate diet and lifestyle of people living with and beyond cancer (PLWBC). The purpose of this study was to reach a consensus among an international expert panel on the essential items to include in this type of instrument. Design: A scientific committee developed the initial list of items, which were presented to an expert panel in a two-round-modified electronic Delphi. Panellists were asked to rate the adequacy, relevance and feasibility of self-reporting each item. Qualitative assessments were encouraged. Setting: Four countries (Spain, UK, USA and Portugal). Participants: Experts working in a cancer-related health profession or cancer-related research were recruited. Main outcome measures: Items were initially categorised into seven domains (body composition, physical activity, diet, alcohol, smoking, sleep and psychosocial distress). A content validity index per item (CVI-i) and a scale-level CVI (S-CVI) were calculated (acceptable≥0.78). All items with a CVI-i≥0.78 were submitted to a final consensus meeting. Results: A total of 108 items were proposed to the panel. In Round 1, 77 items were accepted, 10 items were excluded and 6 new items were proposed. During Round 2, 4 items were accepted and 19 were excluded. Diet and alcohol were merged into one domain. The final consensus meeting decided on 61 items categorised into six domains (S-CVI:0.94): body composition, physical activity, diet and alcohol, smoking, sleep and psychosocial distress. Conclusions: We identified the main items to be considered when developing a screener to evaluate diet and lifestyle in PLWBC in a clinical setting, and the results obtained will guide the content of the screener in the following validation study.
- Open Access
- 2 July 2025
- Published by Colegio Oficial de la Psicologia de Madrid in Clinical and Health
- Vol. 36 (2) , 77-95
Decoding Artificial Intelligence: A Tutorial on Neural Networks in Behavioral Research
Background: Artificial Neural Networks (ANNs), particularly multilayer perceptrons (MLPs) with backpropagation, are increasingly used in Behavioral and Health Sciences for data analysis. This paper provides a comprehensive tutorial on implementing backpropagation in MLP models for regression and classification tasks using Python. Method: The tutorial guides readers step-by-step through building a backpropagation MLP using a simulated data matrix (N = 1,000) with psychological variables, demonstrating ANNs’ versatility in predicting continuous variables and classifying (binary and polytomous) patterns. Python scripts and detailed output interpretations are included. Results: MLP models trained with backpropagation show effectiveness in regression (R² = .71) and classification (binary AUC = .93, polytomous AUC range: .81-.93) on test sets. Conclusions: This tutorial aims to demystify ANNs and promote their use in Behavioral and Health Sciences and other fields, bridging the gap between theory and practical implementation. Introducción:, Las Redes Neuronales Artificiales (RNA), especialmente los perceptrones multicapa (MLPs) con retropropagación, son cada vez más utilizadas en Ciencias del Comportamiento y de la Salud para analizar datos. Este artículo presenta un tutorial completo sobre la implementación de modelos MLP con retropropagación para tareas de regresión y clasificación usando Python. ,Método:, El tutorial guía paso a paso la construcción de un MLP con retropropagación utilizando una matriz de datos simulados (,N, = 1,000) con variables psicológicas, demostrando la versatilidad de las RNA en la predicción de variables continuas y clasificación de (binarios y politómicos). Se incluyen scripts de Python y su interpretación detallada. ,Resultados:, Los modelos MLP muestran eficacia en regresión (,R,² = 0.71) y clasificación (AUC binaria = .93, rango AUC politómica: .81-.93) en los tests. ,Conclusiones:, Este tutorial persigue desmitificar las RNA y promover su uso en Ciencias del Comportamiento y la Salud, facilitando la transición de la teoría a la práctica.
- 2 July 2025
- Published by Colegio Oficial de la Psicologia de Madrid in Clinical and Health
- Vol. 36 (2) , 77-95
Open AccessDecoding Artificial Intelligence: A Tutorial on Neural Networks in Behavioral Research
Background: Artificial Neural Networks (ANNs), particularly multilayer perceptrons (MLPs) with backpropagation, are increasingly used in Behavioral and Health Sciences for data analysis. This paper provides a comprehensive tutorial on implementing backpropagation in MLP models for regression and classification tasks using Python. Method: The tutorial guides readers step-by-step through building a backpropagation MLP using a simulated data matrix (N = 1,000) with psychological variables, demonstrating ANNs’ versatility in predicting continuous variables and classifying (binary and polytomous) patterns. Python scripts and detailed output interpretations are included. Results: MLP models trained with backpropagation show effectiveness in regression (R² = .71) and classification (binary AUC = .93, polytomous AUC range: .81-.93) on test sets. Conclusions: This tutorial aims to demystify ANNs and promote their use in Behavioral and Health Sciences and other fields, bridging the gap between theory and practical implementation. Introducción:, Las Redes Neuronales Artificiales (RNA), especialmente los perceptrones multicapa (MLPs) con retropropagación, son cada vez más utilizadas en Ciencias del Comportamiento y de la Salud para analizar datos. Este artículo presenta un tutorial completo sobre la implementación de modelos MLP con retropropagación para tareas de regresión y clasificación usando Python. ,Método:, El tutorial guía paso a paso la construcción de un MLP con retropropagación utilizando una matriz de datos simulados (,N, = 1,000) con variables psicológicas, demostrando la versatilidad de las RNA en la predicción de variables continuas y clasificación de (binarios y politómicos). Se incluyen scripts de Python y su interpretación detallada. ,Resultados:, Los modelos MLP muestran eficacia en regresión (,R,² = 0.71) y clasificación (AUC binaria = .93, rango AUC politómica: .81-.93) en los tests. ,Conclusiones:, Este tutorial persigue desmitificar las RNA y promover su uso en Ciencias del Comportamiento y la Salud, facilitando la transición de la teoría a la práctica.
- 27 March 2025
- Published by Taylor & Francis in Psychology, Health & Medicine
- Vol. 31 (8) , 1-14
From acute to chronic low back pain: the role of negative emotions
Low back pain (LBP) constitutes a persistent and burdensome condition, frequently intricately intertwined with negative emotional states. The focus of this study is to discern distinct patterns of negative emotions among individuals experiencing Acute Low Back Pain (ALBP) and Chronic Low Back Pain (CLBP), in comparison to a pain-free control group. The study endeavors to harness the potential of artificial intelligence (AI) models in evaluating the discriminatory capacity of these emotions within the groups, thus addressing the issue of pain chronicity. The participant cohort consisted of 54 chronic patients, 44 acute, and 51 pain-free individuals for comparison purposes. Using Artificial Neural Networks (ANN), the study unveiled discernible patterns of emotional association. Significant disparities in emotional experiences emerged between acute and chronic patients. Anxiety assumed an essential role following the onset of LBP, whereas in the chronic group, depression took precedence, accompanied by an escalation in both anger and anxiety-related comorbidity. It's crucial to emphasize the absence of discernible variations in pain intensity between chronic and acute patients. These findings hold considerable implications, as they contribute to the refinement of LBP diagnosis and proactively hinder its progression. By unraveling the intricate interplay between negative emotions and the temporal course of LBP, this study deepens our comprehension and lays the groundwork for interventions addressing both the physical and emotional dimensions. These insights provide valuable input for effective diagnostic and therapeutic strategies, thereby alleviating the burden of chronic LBP on individuals and healthcare systems.
- 27 March 2025
- Published by Taylor & Francis in Psychology, Health & Medicine
- Vol. 31 (8) , 1-14
From acute to chronic low back pain: the role of negative emotions
Low back pain (LBP) constitutes a persistent and burdensome condition, frequently intricately intertwined with negative emotional states. The focus of this study is to discern distinct patterns of negative emotions among individuals experiencing Acute Low Back Pain (ALBP) and Chronic Low Back Pain (CLBP), in comparison to a pain-free control group. The study endeavors to harness the potential of artificial intelligence (AI) models in evaluating the discriminatory capacity of these emotions within the groups, thus addressing the issue of pain chronicity. The participant cohort consisted of 54 chronic patients, 44 acute, and 51 pain-free individuals for comparison purposes. Using Artificial Neural Networks (ANN), the study unveiled discernible patterns of emotional association. Significant disparities in emotional experiences emerged between acute and chronic patients. Anxiety assumed an essential role following the onset of LBP, whereas in the chronic group, depression took precedence, accompanied by an escalation in both anger and anxiety-related comorbidity. It's crucial to emphasize the absence of discernible variations in pain intensity between chronic and acute patients. These findings hold considerable implications, as they contribute to the refinement of LBP diagnosis and proactively hinder its progression. By unraveling the intricate interplay between negative emotions and the temporal course of LBP, this study deepens our comprehension and lays the groundwork for interventions addressing both the physical and emotional dimensions. These insights provide valuable input for effective diagnostic and therapeutic strategies, thereby alleviating the burden of chronic LBP on individuals and healthcare systems.