Non-invasive in vivo Raman spectroscopy of the skin for diabetes screening

This work describes the application of portable Raman spectroscopy coupled with Artificial Neural Networks (ANN), to discern between diabetic patients and healthy controls, with a high degree of accuracy (Acc=89.7±6.6%). This technique is relatively low-cost, simple and comfortable for the patient, yielding rapid diagnosis. These features make our method a promising screening tool for identifying type 2 diabetes mellitus (dM2) in a non-invasive and automated fashion.