UNASSIGNED: Post-Transplant Diabetes Mellitus (PTDM) affects 20%-40% of lung transplant recipients within five years, impacting rejection, infection, cardiovascular events, and mortality. Continuous glucose monitoring (CGM) is used in diabetes but not well-studied in PTDM.
UNASSIGNED: This study assessed CGM performance in detecting hypoglycemia and hyperglycemia post-lung transplantation, compared to self-monitoring blood glucose.
UNASSIGNED: A prospective pilot study included 15 lung transplant patients (mean age 58.6 years; 53.3% men; 73.3% with pre-transplantation diabetes) managing hyperglycemia with insulin. Patients used a blinded CGM and self-monitored glucose for ten days. Data were categorized (% time in range, % high, % very high, % low, % very low) and compared using paired t-tests.
UNASSIGNED: CGM showed superior hyperglycemia detection. Mean differences for \"% very high\", \"% high\", and \"% high and % very high\" were 7.12 (95% CI, 1.8-12.4), 11.1 (95% CI, 3.5-18.8), and 18.3 (95% CI: 7.37-29.24), respectively. No significant difference was found for \"% low and % very low\". All patients reported a positive CGM experience.
UNASSIGNED: CGM use post-lung transplantation seems feasible and offers advantages in detecting hyperglycemia and in optimizing glucose management. Study limitations include a small sample size, requiring larger studies to assess glycemic control, hypoglycemia detection, and transplant outcomes.

Predicting glucose values on the basis of insulin and food intakes is a difficult task that people with diabetes need to do daily. This is necessary as it is important to maintain glucose levels at appropriate values to avoid not only short-term, but also long-term complications of the illness. Artificial intelligence in general and machine learning techniques in particular have already lead to promising results in modeling and predicting glucose concentrations. In this work, several machine learning techniques are used for the modeling and prediction of glucose concentrations using as inputs the values measured by a continuous monitoring glucose system as well as also previous and estimated future carbohydrate intakes and insulin injections. In particular, we use the following four techniques: genetic programming, random forests, k-nearest neighbors, and grammatical evolution. We propose two new enhanced modeling algorithms for glucose prediction, namely (i) a variant of grammatical evolution which uses an optimized grammar, and (ii) a variant of tree-based genetic programming which uses a three-compartment model for carbohydrate and insulin dynamics. The predictors were trained and tested using data of ten patients from a public hospital in Spain. We analyze our experimental results using the Clarke error grid metric and see that 90% of the forecasts are correct (i.e., Clarke error categories A and B), but still even the best methods produce 5 to 10% of serious errors (category D) and approximately 0.5% of very serious errors (category E). We also propose an enhanced genetic programming algorithm that incorporates a three-compartment model into symbolic regression models to create smoothed time series of the original carbohydrate and insulin time series.