1
|
Hilty MP, Favaron E, Wendel Garcia PD, Ahiska Y, Uz Z, Akin S, Flick M, Arbous S, Hofmaenner DA, Saugel B, Endeman H, Schuepbach RA, Ince C. Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence. Crit Care 2022; 26:311. [PMID: 36242010 PMCID: PMC9568900 DOI: 10.1186/s13054-022-04190-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2022] [Accepted: 10/10/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND The sublingual microcirculation presumably exhibits disease-specific changes in function and morphology. Algorithm-based quantification of functional microcirculatory hemodynamic variables in handheld vital microscopy (HVM) has recently allowed identification of hemodynamic alterations in the microcirculation associated with COVID-19. In the present study we hypothesized that supervised deep machine learning could be used to identify previously unknown microcirculatory alterations, and combination with algorithmically quantified functional variables increases the model's performance to differentiate critically ill COVID-19 patients from healthy volunteers. METHODS Four international, multi-central cohorts of critically ill COVID-19 patients and healthy volunteers (n = 59/n = 40) were used for neuronal network training and internal validation, alongside quantification of functional microcirculatory hemodynamic variables. Independent verification of the models was performed in a second cohort (n = 25/n = 33). RESULTS Six thousand ninety-two image sequences in 157 individuals were included. Bootstrapped internal validation yielded AUROC(CI) for detection of COVID-19 status of 0.75 (0.69-0.79), 0.74 (0.69-0.79) and 0.84 (0.80-0.89) for the algorithm-based, deep learning-based and combined models. Individual model performance in external validation was 0.73 (0.71-0.76) and 0.61 (0.58-0.63). Combined neuronal network and algorithm-based identification yielded the highest externally validated AUROC of 0.75 (0.73-0.78) (P < 0.0001 versus internal validation and individual models). CONCLUSIONS We successfully trained a deep learning-based model to differentiate critically ill COVID-19 patients from heathy volunteers in sublingual HVM image sequences. Internally validated, deep learning was superior to the algorithmic approach. However, combining the deep learning method with an algorithm-based approach to quantify the functional state of the microcirculation markedly increased the sensitivity and specificity as compared to either approach alone, and enabled successful external validation of the identification of the presence of microcirculatory alterations associated with COVID-19 status.
Collapse
Affiliation(s)
- Matthias Peter Hilty
- grid.412004.30000 0004 0478 9977Institute of Intensive Care Medicine, University Hospital of Zurich, Rämistrasse 100, 8091 Zurich, Switzerland ,grid.5645.2000000040459992XDepartment of Intensive Care, Erasmus MC, University Medical Center, Rotterdam, The Netherlands
| | - Emanuele Favaron
- grid.5645.2000000040459992XDepartment of Intensive Care, Erasmus MC, University Medical Center, Rotterdam, The Netherlands
| | - Pedro David Wendel Garcia
- grid.412004.30000 0004 0478 9977Institute of Intensive Care Medicine, University Hospital of Zurich, Rämistrasse 100, 8091 Zurich, Switzerland
| | | | - Zuhre Uz
- grid.10419.3d0000000089452978Department of Intensive Care, Leiden University Medical Center, Leiden, The Netherlands
| | - Sakir Akin
- grid.413591.b0000 0004 0568 6689Department of Intensive Care, Haga Hospital, The Hague, The Netherlands
| | - Moritz Flick
- grid.13648.380000 0001 2180 3484Department of Anesthesiology, Center of Anesthesiology and Intensive Care Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Sesmu Arbous
- grid.10419.3d0000000089452978Department of Intensive Care, Leiden University Medical Center, Leiden, The Netherlands
| | - Daniel A. Hofmaenner
- grid.412004.30000 0004 0478 9977Institute of Intensive Care Medicine, University Hospital of Zurich, Rämistrasse 100, 8091 Zurich, Switzerland
| | - Bernd Saugel
- grid.13648.380000 0001 2180 3484Department of Anesthesiology, Center of Anesthesiology and Intensive Care Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Henrik Endeman
- grid.5645.2000000040459992XDepartment of Intensive Care, Erasmus MC, University Medical Center, Rotterdam, The Netherlands
| | - Reto Andreas Schuepbach
- grid.412004.30000 0004 0478 9977Institute of Intensive Care Medicine, University Hospital of Zurich, Rämistrasse 100, 8091 Zurich, Switzerland
| | - Can Ince
- grid.5645.2000000040459992XDepartment of Intensive Care, Erasmus MC, University Medical Center, Rotterdam, The Netherlands
| |
Collapse
|