Abstract
Objectives: Reliable automated handheld vital microscopy image sequence analysis and the identification of disease states and effects of therapy are prerequisites for the routine use of quantitative sublingual microcirculation measurements at the point-of-care. The present study aimed to clinically validate the recently introduced MicroTools software in a large multicentral database of perioperative and critically ill patients and to use this automatic algorithm to data-mine and identify the sublingual microcirculatory variable changes in response to disease and therapy.
Design: Retrospective algorithm-based image analysis and data-mining within a large international database of sublingual capillary microscopy. Algorithm-based analysis was compared with manual analysis for validation. Thereafter, MicroTools was used to identify the functional microcirculatory alterations associated with disease conditions and identify therapeutic options for recruiting functional microcirculatory variables.
Setting: Ten perioperative/ICU/volunteer studies in six international teaching hospitals.
Patients: The database encompass 267 adult and pediatric patients undergoing surgery, treatment for sepsis, and heart failure in the ICU and healthy volunteers.
Interventions: Perioperative and ICU standard of care.
Measurements and main results: One thousand five hundred twenty-five handheld vital microscopy image sequences containing 149,257 microscopy images were analyzed. 3.89 × 10 RBC positions were tracked by the algorithm in real time, and offline manual analysis was performed. Good correlation and trending ability were found between manual and automatic total and functional capillary density (r = 0.6-0.8; p < 0.0001). RBC tracking within the database demonstrated changes in functional capillary density and/or RBC velocity in septic shock, heart failure, hypovolemia, obstructive shock, and hemodilution and thus detected the presence of a disease condition. Therapies recruiting the microcirculatory diffusion and convection capacity associated with systemic vasodilation and an increase in cardiac output were separately identified.
Conclusions: Algorithm-based analysis of the sublingual microcirculation closely matched manual analysis across a broad spectrum of populations. It successfully identified a methodology to quantify microcirculatory alterations associated with disease and the success of capillary recruitment, improving point-of-care application of microcirculatory-targeted resuscitation procedures.