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 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.

Association of COVID-19 Vaccinations With Intensive Care Unit Admissions and Outcome of Critically Ill Patients With COVID-19 Pneumonia in Lombardy, Italy

“…Indeed, the reported crude mortality ranged from 23% to 33% for vaccinated patients and 22% and 29% for unvaccinated patients. 15,16 In Italy, because of safety concerns, a substantial number of individuals were vaccinated with…”

“…[11][12][13][14] Two multicenter studies conducted in Spain and Switzerland reported that fully vaccinated patients with COVID-19 admitted to an ICU had more comorbidities, greater exposure to immunosuppressive drugs, lower ICU length of stay but similar ICU mortality compared with unvaccinated patients. 15,16 However, in both studies, the number of vaccinated and unvaccinated patients admitted during the Alpha and Delta variant waves may have been unbalanced.…”

Bedside Hyperspectral Imaging and Organ Dysfunction Severity in Critically Ill COVID-19 Patients—A Prospective, Monocentric Observational Study

“…To bridge the gap from research to clinical application for microcirculatory monitoring, the application of artificial intelligence is an emerging field of interest. Previously, Hilty et al showed that a deep learning-based model successfully differentiates critically ill COVID-19 patients from healthy volunteers in sublingual microcirculation microscopy [30]. Due to its technical features to analyze tissue morphology and composition, HSI is increasingly evaluated for automated artificial intelligence applications [9,31].…”

The future of intensive care: the study of the microcirculation will help to guide our therapies

“…It is expected that AI will play a central role in the translation of the evaluation of the clinical condition of the virtual patient and to predict response to clinical interventions. This is achievable, for example, for the case of the microcirculation, by integrating AI methodologies with algorithmic analysis of microcirculatory images able to differentially diagnose specific alterations in the phenotype of the microcirculation known to be corrected by specific therapeutic interventions [ 53 ]. AI will allow to have a global vision of macrocirculatory and microcirculatory parameters and to better analyze their response to interventions.…”