scholarly journals Mass cytometry and artificial intelligence define CD169 as a specific marker of SARS-CoV2-induced acute respiratory distress syndrome

2020 ◽  
Author(s):  
M. Roussel ◽  
J. Ferrant ◽  
F. Reizine ◽  
S. Le Gallou ◽  
J. Dulong ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Acute Respiratory Distress Syndrome ◽  
Respiratory Distress Syndrome ◽  
Respiratory Distress ◽  
Distress Syndrome ◽  
Specific Marker ◽  
Intelligence Analysis ◽  
Mass Cytometry ◽  
Hla Dr ◽  
A Cell

AbstractAcute respiratory distress syndrome (ARDS) is the main complication of COVID-19, requiring admission to Intensive Care Unit (ICU). Despite recent immune profiling of COVID-19 patients, to what extent COVID-19-associated ARDS specifically differs from other causes of ARDS remains unknown, To address this question, we built 3 cohorts of patients categorized in COVID-19negARDSpos, COVID-19posARDSpos, and COVID-19posARDSneg, and compared their immune landscape analyzed by high-dimensional mass cytometry on peripheral blood followed by artificial intelligence analysis. A cell signature associating S100A9/calprotectin-producing CD169pos monocytes, plasmablasts, and Th1 cells was specifically found in COVID-19posARDSpos, unlike COVID-19negARDSpos patients. Moreover, this signature was shared by COVID-19posARDSneg patients, suggesting severe COVID-19 patients, whatever they experienced or not ARDS, displayed similar immune dysfunctions. We also showed an increase in CD14posHLA-DRlow and CD14lowCD16pos monocytes correlated to the occurrence of adverse events during ICU stay. Our study demonstrates that COVID-19-associated ARDS display a specific immune profile, and might benefit from personalized therapy in addition to standard ARDS management.One Sentence SummaryCOVID-19-associated ARDS is biologically distinct from other causes of ARDS.

Analytics with artificial intelligence to advance the treatment of acute respiratory distress syndrome

2020 ◽  
Vol 13 (4) ◽  
pp. 301-312
Author(s):  
Zhongheng Zhang ◽  
Eliano Pio Navarese ◽  
Bin Zheng ◽  
Qinghe Meng ◽  
Nan Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Acute Respiratory Distress Syndrome ◽  
Respiratory Distress Syndrome ◽  
Respiratory Distress ◽  
Distress Syndrome

Phenotypic characterization of alveolar monocyte recruitment in acute respiratory distress syndrome

2000 ◽  
Vol 279 (1) ◽  
pp. L25-L35 ◽  
Author(s):  
Simone Rosseau ◽  
Peter Hammerl ◽  
Ulrich Maus ◽  
Hans-Dieter Walmrath ◽  
Hartwig Schütte ◽  
...  
Keyword(s):  
Acute Respiratory Distress Syndrome ◽  
Respiratory Distress Syndrome ◽  
Respiratory Distress ◽  
Distress Syndrome ◽  
Phenotypic Characterization ◽  
Ki67 Staining ◽  
Hla Dr ◽  
Monocyte Recruitment ◽  
Patient Groups

In 49 acute respiratory distress syndrome (ARDS) patients, the phenotype of alveolar macrophages (AMs) was analyzed by flow cytometry. Bronchoalveolar lavage (BAL) was performed within 24 h after intubation and on days 3– 5, 9– 12, and 18– 21 of mechanical ventilation. The 27E10high/CD11bhigh/CD71low/ 25F9low/HLA DRlow/RM3/1lowAM population in the first BAL indicated extensive monocyte influx into the alveolar compartment. There was no evidence of increased local AM proliferation as assessed by nuclear Ki67 staining. Sequential BAL revealed two distinct patient groups. In one, a decrease in 27E10 and CD11b and an increase in CD71, 25F9, HLA DR, and RM3/1 suggested a reduction in monocyte influx and maturation of recruited cells into AMs, whereas the second group displayed sustained monocyte recruitment. In the first BAL from all patients, monocyte chemoattractant protein (MCP)-1 was increased, and AMs displayed elevated MCP-1 gene expression. In sequential BALs, a decrease in MCP-1 coincided with the disappearance of monocyte-like AMs, whereas persistent upregulation of MCP-1 paralleled ongoing monocyte influx. A highly significant correlation between BAL fluid MCP-1 concentration, the predominance of monocyte-like AMs, and the severity of respiratory failure was noted.

scholarly journals Using Artificial Intelligence for Automatic Segmentation of CT Lung Images in Acute Respiratory Distress Syndrome

2021 ◽  
Vol 12 ◽  
Author(s):  
Peter Herrmann ◽  
Mattia Busana ◽  
Massimo Cressoni ◽  
Joachim Lotz ◽  
Onnen Moerer ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Acute Respiratory Distress Syndrome ◽  
Respiratory Distress Syndrome ◽  
Respiratory Distress ◽  
Distress Syndrome ◽  
Manual Segmentation ◽  
Tissue Mass ◽  
Test Set ◽  
Lung Segmentation ◽  
Tissue Fraction

Knowledge of gas volume, tissue mass and recruitability measured by the quantitative CT scan analysis (CT-qa) is important when setting the mechanical ventilation in acute respiratory distress syndrome (ARDS). Yet, the manual segmentation of the lung requires a considerable workload. Our goal was to provide an automatic, clinically applicable and reliable lung segmentation procedure. Therefore, a convolutional neural network (CNN) was used to train an artificial intelligence (AI) algorithm on 15 healthy subjects (1,302 slices), 100 ARDS patients (12,279 slices), and 20 COVID-19 (1,817 slices). Eighty percent of this populations was used for training, 20% for testing. The AI and manual segmentation at slice level were compared by intersection over union (IoU). The CT-qa variables were compared by regression and Bland Altman analysis. The AI-segmentation of a single patient required 5–10 s vs. 1–2 h of the manual. At slice level, the algorithm showed on the test set an IOU across all CT slices of 91.3 ± 10.0, 85.2 ± 13.9, and 84.7 ± 14.0%, and across all lung volumes of 96.3 ± 0.6, 88.9 ± 3.1, and 86.3 ± 6.5% for normal lungs, ARDS and COVID-19, respectively, with a U-shape in the performance: better in the lung middle region, worse at the apex and base. At patient level, on the test set, the total lung volume measured by AI and manual segmentation had a R2 of 0.99 and a bias −9.8 ml [CI: +56.0/−75.7 ml]. The recruitability measured with manual and AI-segmentation, as change in non-aerated tissue fraction had a bias of +0.3% [CI: +6.2/−5.5%] and −0.5% [CI: +2.3/−3.3%] expressed as change in well-aerated tissue fraction. The AI-powered lung segmentation provided fast and clinically reliable results. It is able to segment the lungs of seriously ill ARDS patients fully automatically.

COVID-19 – eine vaskuläre Systemerkrankung

2020 ◽  
Vol 49 (10) ◽  
pp. 418-421
Author(s):  
Christopher Werlein ◽  
Peter Braubach ◽  
Vincent Schmidt ◽  
Nicolas J. Dickgreber ◽  
Bruno Märkl ◽  
...  
Keyword(s):  
Acute Respiratory Distress Syndrome ◽  
Respiratory Distress Syndrome ◽  
Respiratory Distress ◽  
Distress Syndrome

ZUSAMMENFASSUNGDie aktuelle COVID-19-Pandemie verzeichnet mittlerweile über 18 Millionen Erkrankte und 680 000 Todesfälle weltweit. Für die hohe Variabilität sowohl der Schweregrade des klinischen Verlaufs als auch der Organmanifestationen fanden sich zunächst keine pathophysiologisch zufriedenstellenden Erklärungen. Bei schweren Krankheitsverläufen steht in der Regel eine pulmonale Symptomatik im Vordergrund, meist unter dem Bild eines „acute respiratory distress syndrome“ (ARDS). Darüber hinaus zeigen sich jedoch in unterschiedlicher Häufigkeit Organmanifestationen in Haut, Herz, Nieren, Gehirn und anderen viszeralen Organen, die v. a. durch eine Perfusionsstörung durch direkte oder indirekte Gefäßwandschädigung zu erklären sind. Daher wird COVID-19 als vaskuläre Multisystemerkrankung aufgefasst. Vor dem Hintergrund der multiplen Organmanifestationen sind klinisch-pathologische Obduktionen eine wichtige Grundlage der Entschlüsselung der Pathomechanismen von COVID-19 und auch ein Instrument zur Generierung und Hinterfragung innovativer Therapieansätze.

Sign in / Sign up

Export Citation Format

Share Document