Affordable Access

Access to the full text

Machine learning predicts mortality based on analysis of ventilation parameters of critically ill patients: multi-centre validation

  • Mamandipoor, Behrooz1
  • Frutos-Vivar, Fernando2
  • Peñuelas, Oscar2
  • Rezar, Richard3
  • Raymondos, Konstantinos4
  • Muriel, Alfonso3, 5
  • Du, Bin6
  • Thille, Arnaud W.7
  • Ríos, Fernando8
  • González, Marco9
  • del-Sorbo, Lorenzo10
  • del Carmen Marín, Maria11
  • Pinheiro, Bruno Valle12
  • Soares, Marco Antonio13
  • Nin, Nicolas14
  • Maggiore, Salvatore M.15
  • Bersten, Andrew16
  • Kelm, Malte17
  • Bruno, Raphael Romano17
  • Amin, Pravin18
  • And 12 more
  • 1 Fondazione Bruno Kessler Research Institute, Trento, Italy , Trento (Italy)
  • 2 Hospital Universitario de Getafe & Centro de Investigación en Red de Enfermedades Respiratorias (CIBERES), Madrid, Spain , Madrid (Spain)
  • 3 Paracelsus Medical University of Salzburg, Salzburg, 5020, Austria , Salzburg (Austria)
  • 4 Medizinische Hochschule Hannover, Hannover, Germany , Hannover (Germany)
  • 5 Unidad de Bioestadística Clinica Hospital Ramón y Cajal, Instituto Ramón y Cajal de Investigaciones Sanitarias (IRYCIS) & Centro de Investigación en Red de Epidemiología y Salud Pública (CIBERESP), Madrid, Spain , Madrid (Spain)
  • 6 Peking Union Medical College Hospital, Beijing, People’s Republic of China , Beijing (China)
  • 7 University Hospital of Poitiers, Poitiers, France , Poitiers (France)
  • 8 Hospital Nacional Alejandro Posadas, Buenos Aires, Argentina , Buenos Aires (Argentina)
  • 9 Clínica Medellín & Universidad Pontificia Bolivariana, Medellín, Colombia , Medellín (Colombia)
  • 10 Interdepartmental Division of Critical Care Medicine, Toronto, ON, Canada , Toronto (Canada)
  • 11 Hospital Regional 1° de Octubre, Instituto de Seguridad Y Servicios Sociales de Los Trabajadores del Estado (ISSSTE), México, DF, México , México (Mexico)
  • 12 Federal University of Juiz de Fora, Juiz de Fora, Brazil , Juiz de Fora (Brazil)
  • 13 Hospital Universitario Sao Jose, Belo Horizonte, Brazil , Belo Horizonte (Brazil)
  • 14 Hospital Español, Montevideo, Uruguay , Montevideo (Uruguay)
  • 15 Università Degli Studi G. d’Annunzio Chieti e Pescara, Chieti, Italy , Chieti (Italy)
  • 16 Flinders University, Adelaide, South Australia, Australia , Adelaide (Australia)
  • 17 University of Düsseldorf, Moorenstraße 5, Düsseldorf, 40225, Germany , Düsseldorf (Germany)
  • 18 Bombay Hospital Institute of Medical Sciences, Mumbai, India , Mumbai (India)
  • 19 Istanbul Faculty of Medicine, Istanbul, Turkey , Istanbul (Turkey)
  • 20 Sungkyunkwan University School of Medicine, Seoul, South Korea , Seoul (South Korea)
  • 21 Hospital Fattouma Bourguina, Monastir, Tunisia , Monastir (Tunisia)
  • 22 Hospital de Especialidades Eugenio Espejo, Quito, Ecuador , Quito (Ecuador)
  • 23 Papageorgiou Hospital, Thessaloniki, Greece , Thessaloniki (Greece)
  • 24 Centre Hospitalier Universitarie Ibn Sina - Mohammed V University, Rabat, Morocco , Rabat (Morocco)
  • 25 Mahidol University, Bangkok, Thailand , Bangkok (Thailand)
  • 26 South Texas Veterans Health Care System and University of Texas Health Science Center, San Antonio, TX, USA , San Antonio (United States)
Published Article
BMC Medical Informatics and Decision Making
Springer (Biomed Central Ltd.)
Publication Date
May 07, 2021
DOI: 10.1186/s12911-021-01506-w
Springer Nature


BackgroundMechanical Ventilation (MV) is a complex and central treatment process in the care of critically ill patients. It influences acid–base balance and can also cause prognostically relevant biotrauma by generating forces and liberating reactive oxygen species, negatively affecting outcomes. In this work we evaluate the use of a Recurrent Neural Network (RNN) modelling to predict outcomes of mechanically ventilated patients, using standard mechanical ventilation parameters.MethodsWe performed our analysis on VENTILA dataset, an observational, prospective, international, multi-centre study, performed to investigate the effect of baseline characteristics and management changes over time on the all-cause mortality rate in mechanically ventilated patients in ICU. Our cohort includes 12,596 adult patients older than 18, associated with 12,755 distinct admissions in ICUs across 37 countries and receiving invasive and non-invasive mechanical ventilation. We carry out four different analysis. Initially we select typical mechanical ventilation parameters and evaluate the machine learning model on both, the overall cohort and a subgroup of patients admitted with respiratory disorders. Furthermore, we carry out sensitivity analysis to evaluate whether inclusion of variables related to the function of other organs, improve the predictive performance of the model for both the overall cohort as well as the subgroup of patients with respiratory disorders.ResultsPredictive performance of RNN-based model was higher with Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.72 (± 0.01) and Average Precision (AP) of 0.57 (± 0.01) in comparison to RF and LR for the overall patient dataset. Higher predictive performance was recorded in the subgroup of patients admitted with respiratory disorders with AUC of 0.75 (± 0.02) and AP of 0.65 (± 0.03). Inclusion of function of other organs further improved the performance to AUC of 0.79 (± 0.01) and AP 0.68 (± 0.02) for the overall patient dataset and AUC of 0.79 (± 0.01) and AP 0.72 (± 0.02) for the subgroup with respiratory disorders.ConclusionThe RNN-based model demonstrated better performance than RF and LR in patients in mechanical ventilation and its subgroup admitted with respiratory disorders. Clinical studies are needed to evaluate whether it impacts decision-making and patient outcomes.Trial registration: NCT02731898 (, prospectively registered on April 8, 2016.

Report this publication


Seen <100 times