NMNaia Mas-Bilbao
Naia Mas-Bilbao
*This is an algorithmically generated author record based on publicly available information.
Naia Mas-Bilbao has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
I. Seijas
Service of Intensive Care Medicine, Hospital Universitario Cruces, Barakaldo, Bizkaia, Spain
2 shared publicationsM. Catalán
Service of Intensive Care Medicine, Hospital Universitario 12 de Octubre, Madrid, Spain
2 shared publicationsM. Palomar
Service of Intensive Care Medicine, Hospital Arnau de Vilanova. Lleida, Institut de Reserca Biomèdica (IRB) y Universitat Autónoma de Barcelona, Barcelona, Spain
2 shared publicationsM.P. Gracia
Service of Intensive Care Medicine, Hospital Universitari del Mar, Universitat Autònoma de Barcelona, Barcelona, Spain
2 shared publicationsR. Gimeno
Intensive Care Unit, Hospital Universitario la Fe, Valencia, Spain
2 shared publicationsR. Rivas
Service of Intensive Care Medicine, Hospital de Galdakao-Usansolo, Galdakao, Bizkaia, Spain
2 shared publications
Latest Publications
- Open Access
- 26 August 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (8) , e0322101
Modelling in-hospital length of stay: A comparison of linear and ensemble models for competing risk analysis
Length of Stay (LoS) for in-hospital patients is a relevant indicator of efficiency in healthcare. Moreover, it is often related to the occurrence of hospital-acquired complications. In this work, we aim to explore time-to-event analysis for modelling LoS. We employed competing risk models (CR), as we considered two mutually exclusive outcomes: favorable discharge and deterioration. The explanatory variables included the patient’s sex, age, and longitudinal vital signs collected from a dataset comprising admissions. To address sparse measurements, we transformed longitudinal vital signs into cross-sectional statistics. Our approach involves data pre-processing, imputation of missing data, and variable selection. We proposed four types of CR models: Cause-specific Cox, Sub-distribution hazard, and two variants of Random Survival Forests, with both generalised Log-Rank test (cause-specific hazard estimates) and Gray’s test (cumulative incidences estimations) as node splitting rules. Performance in LoS CR models was evaluated over a time frame from 2 to 15 days. Additionally, we considered baselines with two well-established clinical early warning scores the National Early Warning Score (NEWS) and the Modified Early Warning Score (MEWS). The best model was Random Survival Forest using Gray’s test split, with Integrated Brier Score[×100] of 0.386, C-Index above 99%, and Brier Score below 0.006, along the entire time frame. Employing cross-sectional statistics derived from vital signs, along with rigorous data pre-processing, outperformed the degree of correctness of modelling LoS, compared to NEWS and MEWS.- 26 August 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (8) , e0322101
Open AccessModelling in-hospital length of stay: A comparison of linear and ensemble models for competing risk analysis
Length of Stay (LoS) for in-hospital patients is a relevant indicator of efficiency in healthcare. Moreover, it is often related to the occurrence of hospital-acquired complications. In this work, we aim to explore time-to-event analysis for modelling LoS. We employed competing risk models (CR), as we considered two mutually exclusive outcomes: favorable discharge and deterioration. The explanatory variables included the patient’s sex, age, and longitudinal vital signs collected from a dataset comprising admissions. To address sparse measurements, we transformed longitudinal vital signs into cross-sectional statistics. Our approach involves data pre-processing, imputation of missing data, and variable selection. We proposed four types of CR models: Cause-specific Cox, Sub-distribution hazard, and two variants of Random Survival Forests, with both generalised Log-Rank test (cause-specific hazard estimates) and Gray’s test (cumulative incidences estimations) as node splitting rules. Performance in LoS CR models was evaluated over a time frame from 2 to 15 days. Additionally, we considered baselines with two well-established clinical early warning scores the National Early Warning Score (NEWS) and the Modified Early Warning Score (MEWS). The best model was Random Survival Forest using Gray’s test split, with Integrated Brier Score[×100] of 0.386, C-Index above 99%, and Brier Score below 0.006, along the entire time frame. Employing cross-sectional statistics derived from vital signs, along with rigorous data pre-processing, outperformed the degree of correctness of modelling LoS, compared to NEWS and MEWS. - 1 May 2016
- Published by Elsevier in Medicina Intensiva (English Edition)
- Vol. 40 (4) , 216-229
Characteristics and outcomes of patients admitted to Spanish ICU: A prospective observational study from the ENVIN-HELICS registry (2006–2011)
- 1 May 2016
- Published by Elsevier in Medicina Intensiva (English Edition)
- Vol. 40 (4) , 216-229
Characteristics and outcomes of patients admitted to Spanish ICU: A prospective observational study from the ENVIN-HELICS registry (2006–2011)
- 1 June 2015
- Published by Elsevier in Medicina Intensiva (English Edition)
- Vol. 39 (5) , 279-289
Análisis comparativo de pacientes ingresados en Unidades de Cuidados Intensivos españolas por causa médica y quirúrgica
- 1 June 2015
- Published by Elsevier in Medicina Intensiva (English Edition)
- Vol. 39 (5) , 279-289
Análisis comparativo de pacientes ingresados en Unidades de Cuidados Intensivos españolas por causa médica y quirúrgica