Project Lead(s): Christian Lehmann
Rapid and accurate medical diagnoses that are based on objective measures are especially challenging in rural areas of developing countries.
Timely knowledge of a patient’s nutritional status or state of infection could notably improve the speed of recovery.
The aim of the project was to further develop a medical tool to be used by healthcare personnel in rural developing countries to improve the quality of care provided to mothers, young children and critically ill patients.
The idea for the project builds on a novel, non-invasive, commercially available technology to study the microcirculation in humans, called sidestream dark field (SDF) imaging. The SDF device is a hand-held video-microscope that can be connected to a laptop computer.
By positioning the probe under the tongue, clear and crisp pictures of the blood flow in the smallest blood vessels of the body (capillaries) can be obtained and quantified.
Parameters of the sublingual microcirculation (e.g., microvascular flow index, functional capillary density) can be used to detect critical health conditions in patients even before changes in lab values are detectable. Also, less acute changes in health conditions, e.g., chronic malnutrition, can be detected in the microcirculation.
The MicroScreen project aimed to develop and validate new software for rapid analysis of the sublingual microcirculation suitable for:
1. Early detection of malnutrition in children and mothers
2. Identification of critically ill patients at risk for medical complications in the challenging environment of developing countries.
Two different automated software packages were tested in 50 septic shock patients, 50 pregnant women and 50 pediatric patients.
Results were analyzed and compared to standard (semi-automated) software.
The results showed promise for an automated system that derives diagnostically important information from microcirculation videos.
Compared to a commercially available software product, the new developed tools seemed to be capable of detecting vessels and quantifying blood flow automatically in near-real time from large datasets derived from critically ill patients.
The next step is the further miniaturization of the camera. The project team plans to apply for Phase II Transition To Scale funding to achieve this.