Abstract: Systems, methods, apparatuses, and computer program products for non-invasive glucose monitoring. A method may include continuously capturing a photoplethysmography signal of a patient in real-time. The method may also include inputting a blood pressure measurement, demographic information, and the photoplethysmography signal into a mobile application. The method may further include transmitting, as input information, the blood pressure measurement, the demographic information, and the photoplethysmography signal to a cloud server. In addition, the method may include generating, based on the input information, a glucose prediction of the patient.

Abstract: A machine learning model for stratification of early diabetic foot complication using thermogram images is provided that is operable to predictively diagnose a risk for diabetic foot ulceration formation via receiving a thermogram of a foot; identifying, via a machine learning model, a risk factor of diabetic foot ulceration on the foot; and outputting, from the machine learning model, the risk factor as a diagnosis.