Examinando por Autor "Pikatza Huerga, Amaia"
Mostrando 1 - 6 de 6
Resultados por página
Opciones de ordenación
Ítem Analysing the impact of images and text for predicting human creativity through encoders(Science and Technology Publications, Lda, 2025) Pikatza Huerga, Amaia; Matanzas de Luis, Pablo; Fernandez De Retana Uribe, Miguel; Peña Lasa, Javier; Zulaika Zurimendi, Unai; Almeida, AitorThis study explores the application of multimodal machine learning techniques to evaluate the originality and complexity of drawings. Traditional approaches in creativity assessment have primarily focused on visual analysis, often neglecting the potential insights derived from accompanying textual descriptions. The research assesses four target features: drawings’ originality, flexibility and elaboration level, and titles’ creativity, all labelled by expert psychologists. The research compares different image encoding and text embeddings to examine the effectiveness and impact of individual and combined modalities. The results indicate that incorporating textual information enhances the predictive accuracy for all features, suggesting that text provides valuable contextual insights that images alone may overlook. This work demonstrates the importance of a multimodal approach in creativity assessment, paving the way for more comprehensive and nuanced evaluations of artistic expression.Ítem Development and validation of the Resilience in Eating Disorders scale (RED-5)(Actas Españolas de Psiquiatría, 2026-02-15) Las Hayas Rodríguez, Carlota; Hjemdal, Odin; Muñoz, Pedro José ; Padierna Acero, Jesús Ángel ; Beato Fernández, Luis ; Gómez del Barrio, José Andrés; Pérez Valencia, Diana Marcela; Pikatza Huerga, Amaia ; Almeida, AitorBACKGROUND: A resilience scale tailored for individuals with eating disorders (EDs) could significantly enhance our understanding and treatment of EDs. Therefore, we developed and psychometrically evaluated a new Resilience in Eating Disorders scale (RED) following COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN) guidelines. METHOD: Informed by prior qualitative interviews, the new RED scale underwent an initial pilot test among patients with EDs (n = 52) and field tests among patients with EDs (n = 169), ED-recovered individuals (n = 61), and a normative sample of the general population (n = 349), all aged between 27.9 and 29.8 years and residing in Spain. In this study, the participants completed the RED scale, Resilience Scale-25 (RS-25), Eating Attitudes Test-26 (EAT-26), World Health Organisation Quality of Life Scale - Brief Version (WHOQOL-BREF), and Hospital Anxiety and Depression Scale (HADS). Data were collected at baseline and after 1 year. Alongside machine learning techniques, exploratory and confirmatory analyses were employed to evaluate the reliability, construct validity, convergent validity, known-groups validity, predictive validity and responsiveness of the RED scale. RESULTS: The original 52-item version of the RED scale was refined to 44 items following the pilot phase, and ultimately reduced to a 5-item version (RED-5) after field testing and psychometric evaluation. The RED-5 demonstrated strong psychometric properties, with excellent model fit indices (Root Mean Square Error of Approximation (RMSEA) = 0.03, and Comparative Fit Index (CFI) = 0.99) and acceptable internal consistency (Cronbach's alpha = 0.71). Additionally, the RED-5 scale effectively predicted quality of life, anxiety, depression, and ED symptomatology over a 1-year period. CONCLUSIONS: The RED-5 is a concise, psychometrically robust scale specifically developed to assess resilience in patients with EDs. It significantly predicts ED symptoms and quality-of-life outcomes, making it a valuable tool for both clinical practice and research. The RED-5 allows for quick administration and easy scoring. It provides mental health professionals with a tool to guide resilience-informed assessment and more personalized treatment planning.Ítem Human-centred machine learning for health and cognitive modelling(Universidad de Deusto, 2026-06-19) Pikatza Huerga, Amaia; Almeida, Aitor; Zulaika Zurimendi, UnaiMachine learning is increasingly transforming research in healthcare, mental health, and cognitive science by enabling predictive and adaptive systems that support human decision-making. Yet the most accurate models often remain opaque, limiting their interpretability and trustworthiness in domains where transparency is essential. This doctoral research proposes a unified methodological framework for explainable and multimodal machine learning, validated across four representative contexts: prediction of hospital readmission in patients with heart failure (ReIC), prediction of readmission in patients with multiple chronic conditions (RePluris), prediction of eating disorder risk and recovery, and multimodal assessment of creativity from drawings and textual titles. The framework combines data preprocessing, imbalance management, multimodal feature integration, and embedded explainability through SHapley Additive exPlanations (SHAP) and attention-based analyses. Each case study adapts this structure to its domain while maintaining methodological coherence. In cardiovascular and multimorbidity settings, ensemble models integrating clinical, functional, and psychosocial indicators achieved up to 30\% improvement in discrimination compared with traditional Cox and logistic regression baselines. In addition, they highlighted the prognostic value of frailty, anxiety, and depression. In the eating-disorder study, resilience and quality-of-life measures emerged as strong determinants of one-year outcomes, confirming that self-perception and adaptability are central to recovery prediction. The creativity assessment demonstrated that combining image and text embeddings provides complementary information: textual inputs enhanced sensitivity to originality, whereas visual features better captured elaboration and complexity. Across all four domains, the integration of explainability within the modelling process produced systems that balance predictive precision with interpretability, enabling domain experts to trace and validate decision mechanisms. This thesis advances the methodological foundation of human-centred artificial intelligence by demonstrating that explicit incorporation of explainability enhances not only trust but also model performance. The resulting approach contributes to the development of transparent, adaptive, and ethically grounded predictive systems applicable to complex clinical, psychological, and cognitive contexts.Ítem Machine learning approaches for predicting heart failure readmissions(Oxford University Press, 2025-07-06) Pikatza Huerga, Amaia; Almeida, Aitor; Quirós López, Raúl; Larrea, Nere; Legarreta Olabarrieta, María José; Zulaika Zurimendi, Unai; García, Rodrigo Damián; García Gutiérrez, SusanaPurpose: This study aims to develop and evaluate machine learning (ML) models to predict the likelihood of hospital readmission within 30 days after discharge for patients with heart failure (HF). The goal is to compare the predictive accuracy of ML models with traditional methods such as those based on Cox proportional hazards and logistic regression, to improve clinical outcomes and reduce hospital costs. Methods: We conducted a prospective cohort study of patients discharged from five hospitals following admission for HF. Data were collected on variables including sociodemographic characteristics, medical history, admission details, patient-reported outcomes, and clinical parameters. ML techniques were employed to analyse the data and predict readmission risk, incorporating strategies to handle class imbalance and missing data. Model performance was assessed based on accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and F1 score. Results: Ensemble methods with Synthetic Minority Over-sampling Technique balancing and bagging improved the predictive performance of ML models compared with traditional models. The best-performing ensemble model, using decision trees, Gaussian Naïve Bayes, and neural networks, achieved an AUC of 0.81. In contrast, Cox and logistic regression models showed significantly poorer performance (AUC of 0.58 and 0.50, respectively). SHapley Additive exPlanations analysis revealed that frailty, anxiety, and depression were critical in predicting readmission. Conclusion: ML models, particularly those using ensemble methods, significantly outperform traditional models in predicting short-term readmission for patients with HF. These findings highlight the potential of ML to improve clinical decision-making and resource allocation in HF management.Ítem Machine learning using PROFUND components for 30-day readmission prediction in multimorbid patients: a prospective multicentre study(Nature Research, 2026) Pikatza Huerga, Amaia; Almeida, Aitor ; Quirós, Raúl ; Legarreta Olabarrieta, María José; Zulaika Zurimendi, Unai ; Mestre, Daniela; García Gutiérrez, SusanaEarly hospital readmission in multimorbid patients remains a major clinical challenge. Although risk stratification tools are widely used, predictive performance is often limited. The PROFUND index captures frailty, functional dependence, and social vulnerability, but its role in predicting 30-day readmission is unclear. In this prospective multicentre cohort study, multimorbid patients admitted to Internal Medicine and Geriatrics departments were followed after discharge. The primary outcome was unplanned 30-day readmission among patients surviving to 30 days. Models based on PROFUND components were developed using logistic regression and gradient boosting, including a calibrated ensemble model, and compared with LACE and HOSPITAL scores. Performance was assessed in an external validation cohort. Among 435 patients included in the readmission analysis, 14% were readmitted within 30 days. In external validation, discrimination remained modest (AUC 0.52–0.59). The ensemble XGBoost model achieved the highest AUC (0.59), followed by XGBoost (0.58), HOSPITAL (0.54), and LACE (0.52). Differences were incremental. SHAP analysis identified cognitive impairment, anaemia, advanced age, heart failure severity, functional dependence, and limited caregiver support as key contributors. Incorporating frailty, functional, and social vulnerability domains through PROFUND components resulted in only modest improvements in 30-day readmission prediction. Even with machine learning, discrimination remained limited. The observed performance likely reflects both the intrinsic complexity of short-term readmission and the constraints imposed by sample size and available predictors.Ítem Predictive assessment of eating disorder risk and recovery: uncovering the effectiveness of questionnaires and influencing characteristics(Elsevier B.V., 2025) Pikatza Huerga, Amaia; Las Hayas Rodríguez, Carlota; Zulaika Zurimendi, Unai; Almeida, AitorThis study aims to assess the predictive capabilities of various questionnaires in determining the risk of Eating Disorders (ED) and predicting the level of recovery among individuals. Employing machine learning models and diverse datasets, the research focuses on understanding the effectiveness of different questionnaires in providing insights into ED symptoms and recovery outcomes. Additionally, the study seeks to identify the characteristics that significantly influence the recovery process. The investigation aims to contribute valuable information to enhance the diagnostic and monitoring tools used in the field of mental health, particularly concerning ED