Amaia Pikatza

Download

[u' @article{pikatza-huerga_machine_2025, title = {Machine learning approaches for predicting heart failure readmissions}, copyright = {https://creativecommons.org/licenses/by/4.0/}, issn = {0032-5473, 1469-0756}, url = {https://academic.oup.com/pmj/advance-article/doi/10.1093/postmj/qgaf102/8187509}, doi = {10.1093/postmj/qgaf102}, abstract = {Abstract Purpose 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 Na\xefve 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.}, language = {en}, urldate = {2025-10-03}, journal = {Postgraduate Medical Journal}, author = {Pikatza-Huerga, Amaia and Almeida, Aitor and Quiros, Raul and Larrea, Nere and Jose Legarreta, Mari and Zulaika, Unai and Garcia, Rodrigo and Garcia, Susana}, month = jul, year = {2025}, keywords = {AI for health, feature importance, jcr, jcr4.5, machine learning, q1}, pages = {qgaf102}, } ']

[u' @inproceedings{pikatza-huerga_analysing_2025, address = {Porto}, title = {Analysing the {Impact} of {Images} and {Text} for {Predicting} {Human} {Creativity} {Through} {Encoders}}, isbn = {978-989-758-743-6}, url = {https://ict4awe.scitevents.org/}, language = {English}, booktitle = {Proceedings of the 11th {International} {Conference} on {Information} and {Communication} {Technologies} for {Ageing} {Well} and e-{Health}}, publisher = {SCITEPRESS}, author = {Pikatza-Huerga, Amaia and Matanzas de Luis, Pablo and Fernandez-De-Retana Uribe, Miguel and Pe\xf1a Lasa, Javier and Zulaika, Unai and Almeida, Aitor}, year = {2025}, keywords = {AI for health, Artistic Expression, Creativity assessment, EEG, Image analysis, Machine learning, Originality evaluation, Text analysis, core, mental health}, pages = {15--24}, } ']

[u' @article{pikatza-huerga_predictive_2025, title = {Predictive assessment of eating disorder risk and recovery: {Uncovering} the effectiveness of questionnaires and influencing characteristics}, volume = {28}, issn = {20010370}, shorttitle = {Predictive assessment of eating disorder risk and recovery}, url = {https://linkinghub.elsevier.com/retrieve/pii/S2001037025001187}, doi = {10.1016/j.csbj.2025.03.048}, language = {en}, urldate = {2025-04-10}, journal = {Computational and Structural Biotechnology Journal}, author = {Pikatza-Huerga, A. and Las Hayas, C. and Zulaika, U. and Almeida, A.}, year = {2025}, keywords = {AI for health, eating disorders, feature importance, jcr, jcr4.5, machine learning, mental health, q1}, pages = {118--127}, } ']

[u' @incollection{machado_development_2023, address = {Cham}, title = {Development of an {Open} {Source} {IoT}-{Blockchain} {Platform} for {Traceability} of {Fresh} {Products} from {Farm} to {Fork}}, volume = {778}, isbn = {9783031451546 9783031451553}, url = {https://link.springer.com/10.1007/978-3-031-45155-3_46}, language = {en}, urldate = {2025-10-03}, booktitle = {Blockchain and {Applications}, 5th {International} {Congress}}, publisher = {Springer Nature Switzerland}, author = {Pikatza, Amaia and Sainz, Nekane and Gonz\xe1lez, Iv\xe1n and Emaldi, Mikel}, editor = {Machado, Jos\xe9 Manuel and Prieto, Javier and Vieira, Paulo and Peixoto, Hugo and Abelha, Ant\xf3nio and Arroyo, David and Vigneri, Luigi}, year = {2023}, doi = {10.1007/978-3-031-45155-3_46}, pages = {487--497}, } ']