Journal of diabetes science and technology
-
J Diabetes Sci Technol · Jan 2015
Treating severe hypoglycemia: rapid mixing of lyophilized glucagon and diluent at point of care with the Enject GlucaPen.
Severe hypoglycemia (SH) is a common problem in type 1 diabetes (T1D). Annually, nearly 1 of 5 persons with long-standing T1D will have SH. Though injections of glucagon are effective in treating SH, liquid formulations of glucagon are biochemically very unstable. ⋯ Coupled with the emotional stress of the caregiver, errors in glucagon delivery are very common. For these reasons, workers at Enject, Inc are in the process of developing a device that addresses the shortcomings of this currently approved method of glucagon delivery. The Enject device will store the glucagon powder and the diluent in separate compartments and will rapidly mix and inject the components only upon activation of the pen at the point of care.
-
J Diabetes Sci Technol · Jan 2015
Hypoglycemia prediction using machine learning models for patients with type 2 diabetes.
Minimizing the occurrence of hypoglycemia in patients with type 2 diabetes is a challenging task since these patients typically check only 1 to 2 self-monitored blood glucose (SMBG) readings per day. We trained a probabilistic model using machine learning algorithms and SMBG values from real patients. Hypoglycemia was defined as a SMBG value < 70 mg/dL. ⋯ In the model that incorporated medication information, the prediction window was for the hour of hypoglycemia, and the specificity improved to 90%. Our machine learning models can predict hypoglycemia events with a high degree of sensitivity and specificity. These models-which have been validated retrospectively and if implemented in real time-could be useful tools for reducing hypoglycemia in vulnerable patients.