Early prediction of hemodynamic interventions in the intensive care unit using machine learning.
Clinical decision support
Hemodynamics
Machine learning
Vasoactive therapy
Journal
Critical care (London, England)
ISSN: 1466-609X
Titre abrégé: Crit Care
Pays: England
ID NLM: 9801902
Informations de publication
Date de publication:
14 Nov 2021
14 Nov 2021
Historique:
received:
11
03
2021
accepted:
02
11
2021
entrez:
15
11
2021
pubmed:
16
11
2021
medline:
31
12
2021
Statut:
epublish
Résumé
Timely recognition of hemodynamic instability in critically ill patients enables increased vigilance and early treatment opportunities. We develop the Hemodynamic Stability Index (HSI), which highlights situational awareness of possible hemodynamic instability occurring at the bedside and to prompt assessment for potential hemodynamic interventions. We used an ensemble of decision trees to obtain a real-time risk score that predicts the initiation of hemodynamic interventions an hour into the future. We developed the model using the eICU Research Institute (eRI) database, based on adult ICU admissions from 2012 to 2016. A total of 208,375 ICU stays met the inclusion criteria, with 32,896 patients (prevalence = 18%) experiencing at least one instability event where they received one of the interventions during their stay. Predictors included vital signs, laboratory measurements, and ventilation settings. HSI showed significantly better performance compared to single parameters like systolic blood pressure and shock index (heart rate/systolic blood pressure) and showed good generalization across patient subgroups. HSI AUC was 0.82 and predicted 52% of all hemodynamic interventions with a lead time of 1-h with a specificity of 92%. In addition to predicting future hemodynamic interventions, our model provides confidence intervals and a ranked list of clinical features that contribute to each prediction. Importantly, HSI can use a sparse set of physiologic variables and abstains from making a prediction when the confidence is below an acceptable threshold. The HSI algorithm provides a single score that summarizes hemodynamic status in real time using multiple physiologic parameters in patient monitors and electronic medical records (EMR). Importantly, HSI is designed for real-world deployment, demonstrating generalizability, strong performance under different data availability conditions, and providing model explanation in the form of feature importance and prediction confidence.
Sections du résumé
BACKGROUND
BACKGROUND
Timely recognition of hemodynamic instability in critically ill patients enables increased vigilance and early treatment opportunities. We develop the Hemodynamic Stability Index (HSI), which highlights situational awareness of possible hemodynamic instability occurring at the bedside and to prompt assessment for potential hemodynamic interventions.
METHODS
METHODS
We used an ensemble of decision trees to obtain a real-time risk score that predicts the initiation of hemodynamic interventions an hour into the future. We developed the model using the eICU Research Institute (eRI) database, based on adult ICU admissions from 2012 to 2016. A total of 208,375 ICU stays met the inclusion criteria, with 32,896 patients (prevalence = 18%) experiencing at least one instability event where they received one of the interventions during their stay. Predictors included vital signs, laboratory measurements, and ventilation settings.
RESULTS
RESULTS
HSI showed significantly better performance compared to single parameters like systolic blood pressure and shock index (heart rate/systolic blood pressure) and showed good generalization across patient subgroups. HSI AUC was 0.82 and predicted 52% of all hemodynamic interventions with a lead time of 1-h with a specificity of 92%. In addition to predicting future hemodynamic interventions, our model provides confidence intervals and a ranked list of clinical features that contribute to each prediction. Importantly, HSI can use a sparse set of physiologic variables and abstains from making a prediction when the confidence is below an acceptable threshold.
CONCLUSIONS
CONCLUSIONS
The HSI algorithm provides a single score that summarizes hemodynamic status in real time using multiple physiologic parameters in patient monitors and electronic medical records (EMR). Importantly, HSI is designed for real-world deployment, demonstrating generalizability, strong performance under different data availability conditions, and providing model explanation in the form of feature importance and prediction confidence.
Identifiants
pubmed: 34775971
doi: 10.1186/s13054-021-03808-x
pii: 10.1186/s13054-021-03808-x
pmc: PMC8590869
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
388Informations de copyright
© 2021. The Author(s).
Références
N Engl J Med. 2001 Nov 8;345(19):1368-77
pubmed: 11794169
Crit Care. 2020 Aug 6;24(1):488
pubmed: 32762765
Sci Transl Med. 2015 Aug 5;7(299):299ra122
pubmed: 26246167
J Crit Care. 2020 Feb;55:145-148
pubmed: 31731173
Curr Opin Crit Care. 2009 Jun;15(3):234-8
pubmed: 19387339
Curr Opin Crit Care. 2012 Aug;18(4):350-7
pubmed: 22732434
Saudi J Anaesth. 2020 Apr-Jun;14(2):192-199
pubmed: 32317874
J Am Med Inform Assoc. 2017 May 1;24(3):488-495
pubmed: 27707820
JAMA. 2020 Mar 17;323(11):1052-1060
pubmed: 32065827
AMIA Jt Summits Transl Sci Proc. 2017 Jul 26;2017:82-91
pubmed: 28815112
Ann Intensive Care. 2019 Jan 30;9(1):20
pubmed: 30701448
Nat Med. 2020 Mar;26(3):364-373
pubmed: 32152583
Sci Data. 2016 May 24;3:160035
pubmed: 27219127
NPJ Digit Med. 2021 Mar 30;4(1):62
pubmed: 33785839