Développement d’un modèle d’apprentissage automatique pour l’identification de patients susceptibles de répondre aux manœuvres de recrutement alvéolaire
Thèse ou mémoire / Thesis or Dissertation
Date de publication
Autrices et auteurs
Identifiant ORCID de l’auteur
Contributrices et contributeurs
Direction de recherche
Publié dans
Date de la Conférence
Lieu de la Conférence
Éditeur
Cycle d'études
Maîtrise / Master's
Programme
Affiliation
Mots-clés
- hypoxémie
- insuffissance respiratoire
- soins intensifs pédiatriques
- manoeuvres de recrutement
- médecine computationnelle
- hypoxemia
- respiratory failure
- pediatric intensive care
- recruitment maneuvers
- computational medicine
Organisme subventionnaire
Résumé
Résumé
Acute hypoxemic respiratory failure (AHRF) is a common cause of admission to pediatric intensive care units. AHRF is part of several clinical syndromes, the most severe with the highest mortality rate, is the pediatric acute respiratory distress syndrome (ARDS). The most recent guidelines from the Pediatric Acute Lung Injury Consensus Conference (PALICC) in 2023 provide clinicians with recommendations on ventilation techniques, but these are not personalized. Pulmonary recruitment maneuvers are ventilation techniques used to optimize the number of alveoli participating in gas exchange and could be a promising approach for personalizing treatment in hypoxemic patients or those suffering from ARDS. The objective of this thesis was to develop a machine learning model trained on continuous temporal data to predict which patients are likely to improve their oxygenation following recruitment maneuvers. To achieve this goal, we validated a continuous oxygenation monitoring tool and performed data extraction and processing from the high-resolution pediatric intensive care unit database at Sainte-Justine Hospital. We then developed and optimized machine learning algorithms, including logistic regression, support vector machines, neural networks, and decision trees. The best-performing model was a random forest, demonstrating an area under the ROC curve (AUROC) of 0.78 (95% CI: 0.74 – 0.83), an accuracy of 85%, a sensitivity of 73%, and a specificity of 80%. This model highlights the significant potential of computational medicine techniques in helping to personalize respiratory treatments in intensive care. Further improvements, including the integration of bedside imaging data and external validation, are needed to enhance model performance before its clinical implementation.
Acute hypoxemic respiratory failure (AHRF) is a common cause of admission to pediatric intensive care units. AHRF is part of several clinical syndromes, the most severe with the highest mortality rate, is the pediatric acute respiratory distress syndrome (ARDS). The most recent guidelines from the Pediatric Acute Lung Injury Consensus Conference (PALICC) in 2023 provide clinicians with recommendations on ventilation techniques, but these are not personalized. Pulmonary recruitment maneuvers are ventilation techniques used to optimize the number of alveoli participating in gas exchange and could be a promising approach for personalizing treatment in hypoxemic patients or those suffering from ARDS. The objective of this thesis was to develop a machine learning model trained on continuous temporal data to predict which patients are likely to improve their oxygenation following recruitment maneuvers. To achieve this goal, we validated a continuous oxygenation monitoring tool and performed data extraction and processing from the high-resolution pediatric intensive care unit database at Sainte-Justine Hospital. We then developed and optimized machine learning algorithms, including logistic regression, support vector machines, neural networks, and decision trees. The best-performing model was a random forest, demonstrating an area under the ROC curve (AUROC) of 0.78 (95% CI: 0.74 – 0.83), an accuracy of 85%, a sensitivity of 73%, and a specificity of 80%. This model highlights the significant potential of computational medicine techniques in helping to personalize respiratory treatments in intensive care. Further improvements, including the integration of bedside imaging data and external validation, are needed to enhance model performance before its clinical implementation.
Acute hypoxemic respiratory failure (AHRF) is a common cause of admission to pediatric intensive care units. AHRF is part of several clinical syndromes, the most severe with the highest mortality rate, is the pediatric acute respiratory distress syndrome (ARDS). The most recent guidelines from the Pediatric Acute Lung Injury Consensus Conference (PALICC) in 2023 provide clinicians with recommendations on ventilation techniques, but these are not personalized. Pulmonary recruitment maneuvers are ventilation techniques used to optimize the number of alveoli participating in gas exchange and could be a promising approach for personalizing treatment in hypoxemic patients or those suffering from ARDS. The objective of this thesis was to develop a machine learning model trained on continuous temporal data to predict which patients are likely to improve their oxygenation following recruitment maneuvers. To achieve this goal, we validated a continuous oxygenation monitoring tool and performed data extraction and processing from the high-resolution pediatric intensive care unit database at Sainte-Justine Hospital. We then developed and optimized machine learning algorithms, including logistic regression, support vector machines, neural networks, and decision trees. The best-performing model was a random forest, demonstrating an area under the ROC curve (AUROC) of 0.78 (95% CI: 0.74 – 0.83), an accuracy of 85%, a sensitivity of 73%, and a specificity of 80%. This model highlights the significant potential of computational medicine techniques in helping to personalize respiratory treatments in intensive care. Further improvements, including the integration of bedside imaging data and external validation, are needed to enhance model performance before its clinical implementation.
Table des matières
Notes
Notes
Autre version linguistique
Ensemble de données lié
Licence
Collections
Approbation
Évaluation
Complété par
Référencé par
Ce document diffusé sur Papyrus est la propriété exclusive des titulaires des droits d'auteur et est protégé par la Loi sur le droit d'auteur (L.R.C. (1985), ch. C-42). Sauf si le document est diffusé sous une licence Creative Commons, il ne peut être utilisé que dans le cadre d'une utilisation équitable et non commerciale comme le prévoit la Loi (i.e. à des fins d'étude privée ou de recherche, de critique ou de compte-rendu). Pour toute autre utilisation, une autorisation écrite des titulaires des droits d'auteur sera nécessaire.