Neural network approach for non-invasive detection of hyperglycemia using electrocardiographic signals

Hyperglycemia or high blood glucose (sugar) level is a common dangerous complication among patients with Type 1 diabetes mellitus (T1DM). Hyperglycemia can cause serious health problems if left untreated such as heart disease, stroke, vision and nerve problems. Based on the electrocardiographic (ECG) parameters, we have identified hyperglycemic and normoglycemic states in T1DM patients. In this study, a classification unit is introduced with the approach of feed forward multi-layer neural network to detect the presences of hyperglycemic/normoglycemic episodes using ECG parameters as inputs. A practical experiment using the real T1DM patients´ data sets collected from Department of Health, Government of Western Australia is studied. Experimental results show that proposed ECG parameters contributed significantly to the good performance of hyperglycemia detections in term of sensitivity, specificity and geometric mean (70.59%, 65.38%, and 67.94%, respectively). From these results, it is proved that hyperglycemic events in T1DM can be detected non-invasively and effectively by using ECG signals and ANN approach.