Abnormal blood glucose (BG) concentrations have been associated with negative outcomes in critically ill adults and infants. Diagnosis of hyperglycaemia and hypoglycaemia is by BG measurements, which are typically taken several hours apart due to the clinical effort required. Continuous glucose monitoring (CGM) devices, which take measurements every 5 minutes, have the potential to improve the detection and diagnosis of these glycaemic abnormalities. There have been relatively few successful investigations of CGM devices in the ICU, and one study reported significant sensor noise. If CGM devices are going to be used in the clinical setting to monitor, diagnose and potentially help treat glycaemic abnormalities, clinicians need to know data are reliable and accurate. This study uses CGM data from neonatal infants to develop a tool that will aid clinicians in identifying unusual CGM behaviour. A stochastic model was created to classify CGM measurements with the aim of highlighting unusual CGM behaviour. In addition, the method uses a colour coded CGM trace to convey the information quickly and efficiently, either retrospectively or in real-time. The method has been used to detect unusual hypoglycaemic events and potential sensor degradation, both of which need to be interpreted with care. Overall, while BG measurements are required to make definitive conclusions about glycaemic events, the stochastic model provides another level of information to aid users in interpretation and decision making.