Non-invasive measurement of blood lactate in humans using microwave sensors

There is a growing demand for non-invasive point of care devices to monitor metabolites in blood such as lactate. In hospital environments, having such tools would reduce the risk of infection, increase the frequency of measurement and ensure timely intervention only when necessary. In sports situations, such tools will enhance training of athletes, and enable more effecting training regimes to be prescribed. This work demonstrates the use of novel electromagnetic wave lactate sensors on cyclists, 34 in total, in a controlled environment. Sensors attached to the arm and legs of participants gathered spectral data, blood samples were measured using a Lactate Pro V2, as well as temperature and heart rate data being collected. Using pairwise mutual information and neural networks, a predictive model is shown to give a good correlation (R = 0.78) between the standard invasive and novel non-invasive microwave based blood lactate measurements, with an error of 13.4% in the range of 0-12 mmol/L.