Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Noninvasive Arterial Pressure Monitoring during Anesthesia.

Anesthesiology·2026

Same author

Higher versus Routine Intraoperative Blood Pressure Targets in Noncardiac Surgery: A Systematic Review and Meta-analysis with Trial Sequential Analysis of Randomized Trials.

Anesthesiology·2026

Same author

Agreement of minimally invasive pulse wave analysis with pulmonary artery and transpulmonary thermodilution cardiac output measurements in perioperative and intensive care medicine: a systematic review and meta-analysis.

British journal of anaesthesia·2026

Same author

Postoperative hypotension in patients recovering from noncardiac surgery: a prospective, blinded observational study.

British journal of anaesthesia·2026

Same author

Intervals for Oscillometric Arterial Pressure Monitoring during Noncardiac Surgery: The "2.5-Minute versus 5-Minute" Randomized Clinical Trial.

Anesthesiology·2026

Same author

Underdamping: An elephant in the room?

Intensive care medicine·2026

Search research articles

Related Experiment Video

Updated: Aug 25, 2025

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care

Published on: May 10, 2024

Microcirculatory alterations in critically ill COVID-19 patients analyzed using artificial intelligence.

Matthias Peter Hilty^1,2, Emanuele Favaron³, Pedro David Wendel Garcia⁴

¹Institute of Intensive Care Medicine, University Hospital of Zurich, Rämistrasse 100, 8091, Zurich, Switzerland. matthias.hilty@usz.ch.

Critical Care (London, England)

|October 14, 2022

Summary

Deep learning models can identify COVID-19 in sublingual microcirculation images. Combining deep learning with functional analysis significantly improves accuracy in detecting critical illness, outperforming individual methods.

Keywords:

Artificial intelligence COVID-19 Deep learning Microcirculation Neuronal network

More Related Videos

Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies

Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies

Published on: November 19, 2020

Intravital Widefield Fluorescence Microscopy of Pulmonary Microcirculation in Experimental Acute Lung Injury Using a Vacuum-Stabilized Imaging System

Intravital Widefield Fluorescence Microscopy of Pulmonary Microcirculation in Experimental Acute Lung Injury Using a Vacuum-Stabilized Imaging System

Published on: April 6, 2022

Related Experiment Videos

Last Updated: Aug 25, 2025

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care

Published on: May 10, 2024

Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies

Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies

Published on: November 19, 2020

Intravital Widefield Fluorescence Microscopy of Pulmonary Microcirculation in Experimental Acute Lung Injury Using a Vacuum-Stabilized Imaging System

Intravital Widefield Fluorescence Microscopy of Pulmonary Microcirculation in Experimental Acute Lung Injury Using a Vacuum-Stabilized Imaging System

Published on: April 6, 2022

Area of Science:

Medical Imaging
Artificial Intelligence in Medicine
Microcirculation Research

Background:

Sublingual microcirculation changes are linked to various diseases.
Handheld vital microscopy (HVM) with algorithmic analysis can detect COVID-19-related microcirculatory alterations.
Deep machine learning may uncover novel microcirculatory changes and improve COVID-19 patient differentiation.

Purpose of the Study:

To develop and validate a deep learning model for identifying COVID-19 in sublingual microcirculation.
To assess if combining deep learning with algorithmic quantification enhances diagnostic performance.
To differentiate critically ill COVID-19 patients from healthy controls using microcirculatory analysis.

Main Methods:

Trained neuronal networks on HVM image sequences from COVID-19 patients and healthy volunteers across four cohorts.
Quantified functional microcirculatory hemodynamic variables using an algorithmic approach.
Validated models internally and externally, comparing algorithm-based, deep learning-based, and combined approaches.

Main Results:

Trained a deep learning model capable of differentiating COVID-19 patients from healthy volunteers using sublingual HVM images.
The combined deep learning and algorithmic model achieved the highest externally validated Area Under the Receiver Operating Characteristic curve (AUROC) of 0.75.
The combined approach demonstrated superior sensitivity and specificity compared to individual methods in external validation.

Conclusions:

A deep learning model can successfully differentiate critically ill COVID-19 patients from healthy individuals based on sublingual HVM.
Combining deep learning with algorithmic quantification of microcirculatory function significantly improves diagnostic accuracy.
This integrated approach enables robust external validation for identifying microcirculatory alterations associated with COVID-19.