Machine learning methods to improve bedside fluid responsiveness prediction in severe sepsis or septic shock: an observational study.


Journal

British journal of anaesthesia
ISSN: 1471-6771
Titre abrégé: Br J Anaesth
Pays: England
ID NLM: 0372541

Informations de publication

Date de publication:
04 2021
Historique:
received: 13 10 2020
revised: 10 11 2020
accepted: 24 11 2020
pubmed: 20 1 2021
medline: 1 4 2021
entrez: 19 1 2021
Statut: ppublish

Résumé

Passive leg raising (PLR) predicts fluid responsiveness in critical illness, although restrictions in mobilising patients often preclude this haemodynamic challenge being used. We investigated whether machine learning applied on transthoracic echocardiography (TTE) data might be used as a tool for predicting fluid responsiveness in critically ill patients. We studied, 100 critically ill patients (mean age: 62 yr [standard deviation: 14]) with severe sepsis or septic shock prospectively over 24 months. Transthoracic echocardiography measurements were performed at baseline, after PLR, and before and after a standardised fluid challenge in learning and test populations (n=50 patients each). A 15% increase in stroke volume defined fluid responsiveness. The machine learning methods used were classification and regression tree (CART), partial least-squares regression (PLS), neural network (NNET), and linear discriminant analysis (LDA). Each method was applied offline to determine whether fluid responsiveness may be predicted from left and right cardiac ventricular physiological changes detected by cardiac ultrasound. Predictive values for fluid responsiveness were compared by receiver operating characteristics (area under the curve [AUC]; mean [95% confidence intervals]). In the learning sample, the AUC values were PLR 0.76 (0.62-0.89), CART 0.83 (0.73-0.94), PLS 0.97 (0.93-1), NNET 0.93 (0.85-1), and LDA 0.90 (0.81-0.98). In the test sample, the AUC values were PLR 0.77 (0.64-0.91), CART 0.68 (0.54-0.81), PLS 0.83 (0.71-0.96), NNET 0.83 (0.71-0.94), and LDA 0.85 (0.74-0.96) respectively. The PLS model identified inferior vena cava collapsibility, velocity-time integral, S-wave, E/Ea ratio, and E-wave as key echocardiographic parameters. Machine learning generated several models for predicting fluid responsiveness that were comparable with the haemodynamic response to PLR.

Sections du résumé

BACKGROUND
Passive leg raising (PLR) predicts fluid responsiveness in critical illness, although restrictions in mobilising patients often preclude this haemodynamic challenge being used. We investigated whether machine learning applied on transthoracic echocardiography (TTE) data might be used as a tool for predicting fluid responsiveness in critically ill patients.
METHODS
We studied, 100 critically ill patients (mean age: 62 yr [standard deviation: 14]) with severe sepsis or septic shock prospectively over 24 months. Transthoracic echocardiography measurements were performed at baseline, after PLR, and before and after a standardised fluid challenge in learning and test populations (n=50 patients each). A 15% increase in stroke volume defined fluid responsiveness. The machine learning methods used were classification and regression tree (CART), partial least-squares regression (PLS), neural network (NNET), and linear discriminant analysis (LDA). Each method was applied offline to determine whether fluid responsiveness may be predicted from left and right cardiac ventricular physiological changes detected by cardiac ultrasound. Predictive values for fluid responsiveness were compared by receiver operating characteristics (area under the curve [AUC]; mean [95% confidence intervals]).
RESULTS
In the learning sample, the AUC values were PLR 0.76 (0.62-0.89), CART 0.83 (0.73-0.94), PLS 0.97 (0.93-1), NNET 0.93 (0.85-1), and LDA 0.90 (0.81-0.98). In the test sample, the AUC values were PLR 0.77 (0.64-0.91), CART 0.68 (0.54-0.81), PLS 0.83 (0.71-0.96), NNET 0.83 (0.71-0.94), and LDA 0.85 (0.74-0.96) respectively. The PLS model identified inferior vena cava collapsibility, velocity-time integral, S-wave, E/Ea ratio, and E-wave as key echocardiographic parameters.
CONCLUSIONS
Machine learning generated several models for predicting fluid responsiveness that were comparable with the haemodynamic response to PLR.

Identifiants

pubmed: 33461735
pii: S0007-0912(20)31017-5
doi: 10.1016/j.bja.2020.11.039
pii:
doi:

Types de publication

Journal Article Observational Study

Langues

eng

Sous-ensembles de citation

IM

Pagination

826-834

Informations de copyright

Copyright © 2020 British Journal of Anaesthesia. Published by Elsevier Ltd. All rights reserved.

Auteurs

Benoît Bataille (B)

Service de Réanimation Polyvalente, Centre Hospitalier de Narbonne, Narbonne, France. Electronic address: b_bataille2@yahoo.fr.

Jade de Selle (J)

Service de Réanimation Polyvalente, Centre Hospitalier de Narbonne, Narbonne, France.

Pierre-Etienne Moussot (PE)

Service de Réanimation Polyvalente, Centre Hospitalier de Narbonne, Narbonne, France.

Philippe Marty (P)

Service d'Anesthésie, Clinique Medipôle Garonne, Toulouse, France.

Stein Silva (S)

Réanimation UMR, Centre Hospitalier Universitaire, CHU Purpan, Toulouse, France; Toulouse NeuroImaging Center, UMR UPS/INSERM 1214, CHU Purpan, Toulouse, France.

Pierre Cocquet (P)

Service de Réanimation Polyvalente, Centre Hospitalier de Narbonne, Narbonne, France.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH