Articles producció científica> Medicina i Cirurgia

A Machine Learning decision-making tool for extubation in Intensive Care Unit patients

  • Identification data

    Identifier: imarina:9138927
    Authors:
    Fabregat AMagret MFerré JAVernet AGuasch NRodríguez AGómez JBodí M
    Abstract:
    © 2020 Elsevier B.V. Background and Objective: To increase the success rate of invasive mechanical ventilation weaning in critically ill patients using Machine Learning models capable of accurately predicting the outcome of programmed extubations. Methods: The study population was adult patients admitted to the Intensive Care Unit. Target events were programmed extubations, both successful and failed. The working dataset is assembled by combining heterogeneous data including time series from Clinical Information Systems, patient demographics, medical records and respiratory event logs. Three classification learners have been compared: Logistic Discriminant Analysis, Gradient Boosting Method and Support Vector Machines. Standard methodologies have been used for preprocessing, hyperparameter tuning and resampling. Results: The Support Vector Machine classifier is found to correctly predict the outcome of an extubation with a 94.6% accuracy. Contrary to current decision-making criteria for extubation based on Spontaneous Breathing Trials, the classifier predictors only require monitor data, medical entry records and patient demographics. Conclusions: Machine Learning-based tools have been found to accurately predict the extubation outcome in critical patients with invasive mechanical ventilation. The use of this important predictive capability to assess the extubation decision could potentially reduce the rate of extubation failure, currently at 9%. With about 40% of critically ill patients eventually receiving invasive mechanical ventilation during their stay and given the serious potential complications associated to reintubation, the excellent predictive ability of the model presented here suggests that Machine Learning techniques could significantly improve the clinica
  • Others:

    Author, as appears in the article.: Fabregat A; Magret M; Ferré JA; Vernet A; Guasch N; Rodríguez A; Gómez J; Bodí M
    Department: Medicina i Cirurgia Bioquímica i Biotecnologia Enginyeria Mecànica
    URV's Author/s: Bodi Saera, Maria Amparo / Fabregat Tomàs, Alexandre / Ferré Vidal, Josep Anton / Gómez Alvarez, Josep / Magret Iglesias, Mònica / Vernet Peña, Antonio
    Keywords: Support vector machine Reintubation Machine learning Invasive mechanical ventilation Gradient boosting Extubation Clinical decision support tool
    Abstract: © 2020 Elsevier B.V. Background and Objective: To increase the success rate of invasive mechanical ventilation weaning in critically ill patients using Machine Learning models capable of accurately predicting the outcome of programmed extubations. Methods: The study population was adult patients admitted to the Intensive Care Unit. Target events were programmed extubations, both successful and failed. The working dataset is assembled by combining heterogeneous data including time series from Clinical Information Systems, patient demographics, medical records and respiratory event logs. Three classification learners have been compared: Logistic Discriminant Analysis, Gradient Boosting Method and Support Vector Machines. Standard methodologies have been used for preprocessing, hyperparameter tuning and resampling. Results: The Support Vector Machine classifier is found to correctly predict the outcome of an extubation with a 94.6% accuracy. Contrary to current decision-making criteria for extubation based on Spontaneous Breathing Trials, the classifier predictors only require monitor data, medical entry records and patient demographics. Conclusions: Machine Learning-based tools have been found to accurately predict the extubation outcome in critical patients with invasive mechanical ventilation. The use of this important predictive capability to assess the extubation decision could potentially reduce the rate of extubation failure, currently at 9%. With about 40% of critically ill patients eventually receiving invasive mechanical ventilation during their stay and given the serious potential complications associated to reintubation, the excellent predictive ability of the model presented here suggests that Machine Learning techniques could significantly improve the clinical outcomes of critical patients.
    Thematic Areas: Software Saúde coletiva Psicología Odontología Medicina iii Medicina ii Medicina i Medical informatics Matemática / probabilidade e estatística Interdisciplinar Health informatics General medicine Engineering, biomedical Engenharias iv Engenharias iii Engenharias ii Educação física Computer science, theory & methods Computer science, interdisciplinary applications Computer science applications Ciências biológicas ii Ciências biológicas i Ciências ambientais Ciências agrárias i Ciência da computação Biotecnología
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: josep.gomez@urv.cat monica.magret@urv.cat alexandre.fabregat@urv.cat anton.vernet@urv.cat josep.a.ferre@urv.cat mariaamparo.bodi@urv.cat mariaamparo.bodi@urv.cat
    Author identifier: 0000-0002-0573-7621 0000-0002-9534-9920 0000-0002-6032-2605 0000-0002-7028-1368 0000-0002-0831-0885 0000-0001-7652-8379 0000-0001-7652-8379
    Record's date: 2024-07-27
    Papper version: info:eu-repo/semantics/acceptedVersion
    Link to the original source: https://www.sciencedirect.com/science/article/abs/pii/S0169260720317028?via%3Dihub#!
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Computer Methods And Programs In Biomedicine. 200 (105869): 105869-
    APA: Fabregat A; Magret M; Ferré JA; Vernet A; Guasch N; Rodríguez A; Gómez J; Bodí M (2021). A Machine Learning decision-making tool for extubation in Intensive Care Unit patients. Computer Methods And Programs In Biomedicine, 200(105869), 105869-. DOI: 10.1016/j.cmpb.2020.105869
    Article's DOI: 10.1016/j.cmpb.2020.105869
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2021
    Publication Type: Journal Publications
  • Keywords:

    Computer Science Applications,Computer Science, Interdisciplinary Applications,Computer Science, Theory & Methods,Engineering, Biomedical,Health Informatics,Medical Informatics,Software
    Support vector machine
    Reintubation
    Machine learning
    Invasive mechanical ventilation
    Gradient boosting
    Extubation
    Clinical decision support tool
    Software
    Saúde coletiva
    Psicología
    Odontología
    Medicina iii
    Medicina ii
    Medicina i
    Medical informatics
    Matemática / probabilidade e estatística
    Interdisciplinar
    Health informatics
    General medicine
    Engineering, biomedical
    Engenharias iv
    Engenharias iii
    Engenharias ii
    Educação física
    Computer science, theory & methods
    Computer science, interdisciplinary applications
    Computer science applications
    Ciências biológicas ii
    Ciências biológicas i
    Ciências ambientais
    Ciências agrárias i
    Ciência da computação
    Biotecnología
  • Documents:

  • Cerca a google

    Search to google scholar