Hypoglycemia is a significant adverse outcome in patients with type 2 diabetes and has been associated with increased morbidity, mortality, and cost of care.1 In addition, hypoglycemia is a major limiting factor for the optimization of insulin therapy. In patients with frequent self-monitored blood glucose (SMBG) measurements or those who employ continuous glucose monitors, statistical methods may be used to predict hypoglycemia. For example, Rodbard found that hypoglycemia risk can be estimated using mean, standard deviation, coefficient of variation, and the nature of the glucose distribution.2 Kovatchev et al introduced a measure of BG variability called "average daily risk range," which strongly correlated to hypoglycemia. Most patients with type 2 diabetes have only sparse SMBG data, which do not lend themselves to statistical methods. Our goal is to be able to accurately predict an individual's risk for hypoglycemia using sparse data, and by employing mobile health technology to provide the appropriate preventive actions for patients and caregivers.For predictions to be clinically useful, the accuracy of the prediction should have significant confidence. Predictions should provide a forecast for a time window that is sufficient to enable meaningful preventive interventions. Predictions should be enabled with BG data alone; other clinical information, when available, can be used if the accuracy of the prediction increases. And finally, the prediction algorithm should require only approximately 1 to 2 SMBG values per day, which is typical for patients with type 2 diabetes MethodsWe employed machine learning methods for our prediction algorithms (see Figure 1). Machine learning is useful when there is a large amount of example data and when the rules for prediction are unclear. In the case of hypoglycemia, we felt that though physicians were able to intuitively estimate the risk of hypoglycemia, they weren't able to explain 554260D STXXX10.1177/1932296814554260Journal Background: 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.

The functional properties of the amino terminus (NT) of the corticotropin releasing factor (CRF) receptor type 1 (R1) were studied by use of murine (m) CRFR1 and rat (r) parathyroid hormone (PTH)/parathyroid hormone-related peptide receptor (PTH1R) chimeras. The chimeric receptor CXP, in which the NT of mCRFR1 was annealed to the TMs of PTH1R, and the reciprocal hybrid, PXC, bound radiolabeled analogues of sauvagine and PTH(3--34), respectively. Neither hybrid bound radiolabeled CRF or PTH(1--34). CRF and PTH(1--34) weakly stimulated intracellular cAMP accumulation in COS-7 cells transfected with PXC and CXP, respectively. Thus the NT is required for ligand binding and the TMs are required for agonist-stimulated cAMP accumulation. Replacing individual intercysteine segments of PXC with their mCRFR1 counterparts did not rescue CRF or sauvagine radioligand binding or stimulation of cAMP accumulation. Replacement of residues 1--31 of mCRFR1 with their PTH1R counterparts resulted in a chimeric receptor, PEC, which had normal CRFR1 functional properties. In addition, a series of chimeras (F1PEC--F6PEC) were generated by replacement of the NT intercysteine residues of PEC with their PTH1R counterparts. Only F1PEC, F2PEC, and F3PEC showed detectable CRF and sauvagine radioligand binding. All of the PEC chimeras except F5PEC increased cAMP accumulation. These data indicate that the Cys(68)(-)Glu(109) domain is important for binding and that the Cys(87)(-)Cys(102) region plays an important role in CRFR1 activation.

No subcutaneous insulin regimen implemented approximately 1 day after cardiac surgery showed significantly better control of blood glucose over the 3-day study period. Further studies are needed to determine optimal formulae for effecting an early transition to subcutaneous insulin after cardiac surgery or whether it is preferable and/or necessary to continue intravenous insulin therapy for an additional period of time.

No abstract