Examinando por Autor "Estrada, Victor"

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    Decoding sepsis: a 16-year retrospective analysis of activation patterns, mortality predictors, and outcomes from a hospital-wide sepsis protocol
    (MDPI, 2025-08-14) Borges-Sa, Marcio; Giglio, Andrés; Aranda, Maria; Socias, Antonia; Castillo, Alberto del; Mena, Joana; Franco, Sara; Ortega, María; Nieto, Yasmina; Estrada, Victor; Rica, Roberto de la
    Background: Sepsis remains a leading cause of mortality in hospitalized patients. We evaluated characteristics and outcomes of patients identified through a comprehensive hospital-wide sepsis protocol over a 16-year period. Methods: This retrospective cohort study analyzed hospital-wide sepsis protocol activations at a tertiary care hospital in Spain from 2006 to 2022. The protocol required at least two SIRS criteria plus evidence of organ dysfunction in patients over 14 years old. We analyzed demographics, activation criteria, hospital location, mortality predictors using univariate and multivariate analyses, including propensity score modeling, and resource utilization trends. Results: A total of 10,919 patients with 14,546 protocol activations were identified. The median age was 69 years (IQR: 56–78), with 60.9% male patients. Protocol activations occurred in the emergency department (54%), ICU (34.2%), and inpatient wards (11.8%). The most common SIRS criteria were tachycardia (75.6%), tachypnea (50.4%), and fever (48.5%). Prevalent organ dysfunctions included hypotension (53%), hypoxemia (50.1%), oliguria (28.9%), and altered mental status (22%). Overall in-hospital mortality showed a significant linear downward trend from 26.5% in the first year to 13.6% in later years (p < 0.01). Propensity score analysis confirmed independent mortality predictors included hyperlactatemia (aOR 2.21), altered consciousness (aOR 2.09), hypotension (aOR 1.87), and leukopenia (aOR 1.79). ICU admission rate decreased from 58% to 24% over the study period. Conclusions: This 16-year analysis shows that comprehensive hospital-wide sepsis protocols achieve sustained mortality reduction with improved resource utilization efficiency. These findings support implementing comprehensive sepsis protocols as an effective strategy for improving sepsis outcomes.
  • Miniatura
    Ítem
    Hospital-wide sepsis detection: A machine learning model based on prospectively expert-validated cohort
    (MDPI, 2026-01-21) Borges-Sa, Marcio; Giglio, Andrés; Aranda, Maria; Socias, Antonia; del Castillo, Alberto; Pruenza, Cristina; Hernández, Gonzalo; Cerdá, Sofía; Socias, Lorenzo; Estrada, Victor; de la Rica, Roberto; Martin, Elisa; Martin-Loeches, Ignacio
    Background/Objectives: Sepsis detection remains challenging due to clinical heterogeneity and limitations of traditional scoring systems. This study developed and validated a hospital-wide machine learning model for sepsis detection using retrospectively developed data from prospectively expert-validated cases, aiming to improve diagnostic accuracy beyond conventional approaches. Methods: This retrospective cohort study analysed 218,715 hospital episodes (2014–2018) at a tertiary care centre. Sepsis cases (n = 11,864, 5.42%) were prospectively validated in real-time by a Multidisciplinary Sepsis Unit using modified Sepsis-2 criteria with organ dysfunction. The model integrated structured data (26.95%) and unstructured clinical notes (73.04%) extracted via natural language processing from 2829 variables, selecting 230 relevant predictors. Thirty models including random forests, support vector machines, neural networks, and gradient boosting were developed and evaluated. The dataset was randomly split (5/7 training, 2/7 testing) with preserved patient-level independence. Results: The BiAlert Sepsis model (random forest + Sepsis-2 ensemble) achieved an AUC-ROC of 0.95, sensitivity of 0.93, and specificity of 0.84, significantly outperforming traditional approaches. Compared to the best rule-based method (Sepsis-2 + qSOFA, AUC-ROC 0.90), BiAlert reduced false positives by 39.6% (13.10% vs. 21.70%, p < 0.01). Novel predictors included eosinopenia and hypoalbuminemia, while traditional variables (MAP, GCS, platelets) showed minimal univariate association. The model received European Medicines Agency approval as a medical device in June 2024. Conclusions: This hospital-wide machine learning model, trained on prospectively expert-validated cases and integrating extensive NLP-derived features, demonstrates superior sepsis detection performance compared to conventional scoring systems. External validation and prospective clinical impact studies are needed before widespread implementation.