Examinando por Autor "Larrea, Nere"

Mostrando 1 - 2 de 2
  • Miniatura
    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, Susana
    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 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.
  • Miniatura
    Ítem
    Older adult patients in the emergency department: which patients should be selected for a different approach?
    (Korean Geriatrics Society, 2024-03) Larrea, Nere; García Gutiérrez, Susana; Miró Andreu, Óscar; Aguiló, Sira; Jacob Rodríguez, Javier; Alquézar, Aitor; Burillo Putze, Guillermo; Fernández Alonso, Cesáreo; Llorens Soriano, Pere; Roza Alonso, César; Tavasci López, Ivana Verónica; Cañete, Mónica; Ruiz Asensio, Pedro; Paderne Díaz, Beatriz; Pablos Pizarro, Teresa; Rio Navarro, Rigoberto Jesús del; Perelló Viola, Nuria; Hernández Castells, Lourdes; Cortés Soler, Alejandro; Sánchez Fernández-Linares, Elena; Sánchez Serrano, Jesús Ángel; Ezponda, Patxi; Martínez Lorenzo, Andrea; Ortega Liarte, Juan Vicente; Sánchez Ramón, Susana; Ruiz Aranda, Asumpta; Martín Sánchez, Francisco Javier; González del Castillo, Juan
    Background: While multidimensional and interdisciplinary assessment of older adult patients improves their short-term outcomes after evaluation in the emergency department (ED), this assessment is time-consuming and ill-suited for the busy environment. Thus, identifying patients who will benefit from this strategy is challenging. Therefore, this study aimed to identify older adult patients suitable for a different ED approach as well as independent variables associated with poor short-term clinical outcomes. Methods: We included all patients ≥65 years attending 52 EDs in Spain over 7 days. Sociodemographic, comorbidity, and baseline functional status data were collected. The outcomes were 30-day mortality, re-presentation, hospital readmission, and the composite of all outcomes. Results: During the study among 96,014 patients evaluated in the ED, we included 23,338 patients ≥65 years—mean age, 78.4±8.1 years; 12,626 (54.1%) women. During follow-up, 5,776 patients (24.75%) had poor outcomes after evaluation in the ED: 1,140 (4.88%) died, 4,640 (20.51) returned to the ED, and 1,739 (7.69%) were readmitted 30 days after discharge following the index visit. A model including male sex, age ≥75 years, arrival by ambulance, Charlson Comorbidity Index ≥3, and functional impairment had a C-index of 0.81 (95% confidence interval, 0.80–0.82) for 30-day mortality. Conclusion: Male sex, age ≥75 years, arrival by ambulance, functional impairment, or severe comorbidity are features of patients who could benefit from approaches in the ED different from the common triage to improve the poor short-term outcomes of this population.