Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence
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 alter...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-10-01
|
Series: | Critical Care |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13054-022-04190-y |
_version_ | 1798029943653793792 |
---|---|
author | Matthias Peter Hilty Emanuele Favaron Pedro David Wendel Garcia Yavuz Ahiska Zuhre Uz Sakir Akin Moritz Flick Sesmu Arbous Daniel A. Hofmaenner Bernd Saugel Henrik Endeman Reto Andreas Schuepbach Can Ince |
author_facet | Matthias Peter Hilty Emanuele Favaron Pedro David Wendel Garcia Yavuz Ahiska Zuhre Uz Sakir Akin Moritz Flick Sesmu Arbous Daniel A. Hofmaenner Bernd Saugel Henrik Endeman Reto Andreas Schuepbach Can Ince |
author_sort | Matthias Peter Hilty |
collection | DOAJ |
description | 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. |
first_indexed | 2024-04-11T19:33:16Z |
format | Article |
id | doaj.art-ad35dfa3719247249a2e1924bde36922 |
institution | Directory Open Access Journal |
issn | 1364-8535 |
language | English |
last_indexed | 2024-04-11T19:33:16Z |
publishDate | 2022-10-01 |
publisher | BMC |
record_format | Article |
series | Critical Care |
spelling | doaj.art-ad35dfa3719247249a2e1924bde369222022-12-22T04:06:57ZengBMCCritical Care1364-85352022-10-0126111110.1186/s13054-022-04190-yMicrocirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligenceMatthias Peter Hilty0Emanuele Favaron1Pedro David Wendel Garcia2Yavuz Ahiska3Zuhre Uz4Sakir Akin5Moritz Flick6Sesmu Arbous7Daniel A. Hofmaenner8Bernd Saugel9Henrik Endeman10Reto Andreas Schuepbach11Can Ince12Institute of Intensive Care Medicine, University Hospital of ZurichDepartment of Intensive Care, Erasmus MC, University Medical CenterInstitute of Intensive Care Medicine, University Hospital of ZurichActive Medical BVDepartment of Intensive Care, Leiden University Medical CenterDepartment of Intensive Care, Haga HospitalDepartment of Anesthesiology, Center of Anesthesiology and Intensive Care Medicine, University Medical Center Hamburg-EppendorfDepartment of Intensive Care, Leiden University Medical CenterInstitute of Intensive Care Medicine, University Hospital of ZurichDepartment of Anesthesiology, Center of Anesthesiology and Intensive Care Medicine, University Medical Center Hamburg-EppendorfDepartment of Intensive Care, Erasmus MC, University Medical CenterInstitute of Intensive Care Medicine, University Hospital of ZurichDepartment of Intensive Care, Erasmus MC, University Medical CenterAbstract 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.https://doi.org/10.1186/s13054-022-04190-yMicrocirculationCOVID-19Deep learningNeuronal networkArtificial intelligence |
spellingShingle | Matthias Peter Hilty Emanuele Favaron Pedro David Wendel Garcia Yavuz Ahiska Zuhre Uz Sakir Akin Moritz Flick Sesmu Arbous Daniel A. Hofmaenner Bernd Saugel Henrik Endeman Reto Andreas Schuepbach Can Ince Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence Critical Care Microcirculation COVID-19 Deep learning Neuronal network Artificial intelligence |
title | Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence |
title_full | Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence |
title_fullStr | Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence |
title_full_unstemmed | Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence |
title_short | Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence |
title_sort | microcirculatory alterations in critically ill covid 19 patients analyzed using artificial intelligence |
topic | Microcirculation COVID-19 Deep learning Neuronal network Artificial intelligence |
url | https://doi.org/10.1186/s13054-022-04190-y |
work_keys_str_mv | AT matthiaspeterhilty microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT emanuelefavaron microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT pedrodavidwendelgarcia microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT yavuzahiska microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT zuhreuz microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT sakirakin microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT moritzflick microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT sesmuarbous microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT danielahofmaenner microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT berndsaugel microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT henrikendeman microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT retoandreasschuepbach microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence AT canince microcirculatoryalterationsincriticallyillcovid19patientsanalyzedusingartificialintelligence |