Continous monitoring of blood glucose using photophlythesmograph signal

Diabetes, is a lifelong disease caused due to the decreased ability of the beta cells in the pancreas to produce insulin. At present blood glucose can be self monitored using a invasive glucose meter. This process involves pricking of finger by lancet, the blood from the pricked finger is extracted and chemical analysis is done using disposable blood strips. Invasive testing of blood glucose leads to risk of infection as finger is pricked at least three times a day. The ache and uneasiness has also lead to the development of non invasive blood glucose monitoring using photophlythesmographic signal. A photoplethysmographic (PPG) signal is obtained from a patient and various parameters that correlate with the value of blood glucose in the body are extracted. Clinical parameters of the patient are also received and both of these are trained using various machine learning algorithm and the algorithm showing best results is considered.