Article (Scientific journals)
Virtual patients for mechanical ventilation in the intensive care unit
Zhou, C.; Chase, J. G.; Knopp, J. et al.
2021In Computer Methods and Programs in Biomedicine, 199
Peer Reviewed verified by ORBi
 

Files


Full Text
1-s2.0-S0169260720317454-main-2.pdf
Publisher postprint (19.27 MB)
Request a copy

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Digital twins; Hysteresis loop analysis; Hysteresis model; Lung mechanics; Mechanical ventilation; Virtual patient; Biological organs; Forecasting; Hysteresis; Hysteresis loops; Intensive care units; Mechanics; Physiological models; Pressure control; Ventilation; Accurate prediction; Accurate response; Nonlinear changes; Nonlinear hysteresis; Patient specific; Virtual patient models; Virtual patients; Patient treatment; Computer Simulation; Humans; Respiration, Artificial; Respiratory Mechanics; Ventilator-Induced Lung Injury
Abstract :
[en] Background: Mechanical ventilation (MV) is a core intensive care unit (ICU) therapy. Significant inter- and intra- patient variability in lung mechanics and condition makes managing MV difficult. Accurate prediction of patient-specific response to changes in MV settings would enable optimised, personalised, and more productive care, improving outcomes and reducing cost. This study develops a generalised digital clone model, or in-silico virtual patient, to accurately predict lung mechanics in response to changes in MV. Methods: An identifiable, nonlinear hysteresis loop model (HLM) captures patient-specific lung dynamics identified from measured ventilator data. Identification and creation of the virtual patient model is fully automated using the hysteresis loop analysis (HLA) method to identify lung elastances from clinical data. Performance is evaluated using clinical data from 18 volume-control (VC) and 14 pressure-control (PC) ventilated patients who underwent step-wise recruitment maneuvers. Results: Patient-specific virtual patient models accurately predict lung response for changes in PEEP up to 12 cmH2O for both volume and pressure control cohorts. R2 values for predicting peak inspiration pressure (PIP) and additional retained lung volume, Vfrc in VC, are R2=0.86 and R2=0.90 for 106 predictions over 18 patients. For 14 PC patients and 84 predictions, predicting peak inspiratory volume (PIV) and Vfrc yield R2=0.86 and R2=0.83. Absolute PIP, PIV and Vfrc errors are relatively small. Conclusions: Overall results validate the accuracy and versatility of the virtual patient model for capturing and predicting nonlinear changes in patient-specific lung mechanics. Accurate response prediction enables mechanically and physiologically relevant virtual patients to guide personalised and optimised MV therapy. © 2020
Disciplines :
Anesthesia & intensive care
Author, co-author :
Zhou, C.;  School of Civil Aviation, Northwestern Polytechnical University, China, Department of Mechanical Engineering, University of Canterbury, New Zealand
Chase, J. G.;  Department of Mechanical Engineering, University of Canterbury, New Zealand
Knopp, J.;  Department of Mechanical Engineering, University of Canterbury, New Zealand
Sun, Q.;  Department of Mechanical Engineering, University of Canterbury, New Zealand
Tawhai, M.;  Auckland Bio-Engineering Institute (ABI), University of Auckland, New Zealand
Möller, K.;  Institute for Technical Medicine, Furtwangen University, Villingen-Schwenningen, Germany
Heines, S. J.;  Department of Intensive Care, School of Medicine, Maastricht University, Maastricht, Netherlands
Bergmans, D. C.;  Department of Intensive Care, School of Medicine, Maastricht University, Maastricht, Netherlands
Shaw, G. M.;  Department of Intensive Care, Christchurch, New Zealand
Desaive, Thomas  ;  Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > Thermodynamique des phénomènes irréversibles
Language :
English
Title :
Virtual patients for mechanical ventilation in the intensive care unit
Publication date :
2021
Journal title :
Computer Methods and Programs in Biomedicine
ISSN :
0169-2607
eISSN :
1872-7565
Publisher :
Elsevier Ireland Ltd
Volume :
199
Peer reviewed :
Peer Reviewed verified by ORBi
Funders :
TEC - Tertiary Education Commission
Funding text :
This work was supported by the NZ Tertiary Education Com- mission (TEC) fund MedTech CoRE (Centre of Research Excellence; #3705718) and the NZ National Science Challenge 7, Science for Technology and Innovation (2019-S3-CRS). The authors also ac- knowledge support from the EU H2020 R&I programme (MSCA- RISE-2019 call) under grant agreement #872488 —DCPM.
Available on ORBi :
since 09 February 2022

Statistics


Number of views
69 (6 by ULiège)
Number of downloads
1 (1 by ULiège)

Scopus citations®
 
51
Scopus citations®
without self-citations
14
OpenCitations
 
27
OpenAlex citations
 
62

Bibliography


Similar publications



Contact ORBi