A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph

Abstract

Pediatric diabetes I is an endemic and an especially difficult disease; indeed, at this point, there does not exist a cure, but only careful management that relies on anticipating hypoglycemia. The changing physiology of children producing unique blood glucose signatures, coupled with inconsistent activities, e.g., playing, eating, napping, makes "forecasting" elusive. While work has been done for adult diabetes I, this does not successfully translate for children. In the work presented here, we adopt a reinforcement approach by leveraging the de Bruijn graph that has had success in detecting patterns in sequences of symbols-most notably, genomics and proteomics. We translate a continuous signal of blood glucose levels into an alphabet that then can be used to build a de Bruijn, with some extensions, to determine blood glucose states. The graph allows us to "tune" its efficacy by computationally ignoring edges that provide either no information or are not related to entering a hypoglycemic episode. We can then use paths in the graph to anticipate hypoglycemia in advance of about 30 minutes sufficient for a clinical setting and additionally find actionable rules that accurate and effective. All the code developed for this study can be found at: https://github.com/KurbanIntelligenceLab/dBG-Hypoglycemia-Forecast .

Fig. 1

(Left) shows critical pathways that cause hypoglycemia–insulin cannot be decreased and glucagon cannot be increased. (Right) physiological response. The graphic exposes both the complexity and challenges in determining this state which is often defined only by plasma glucose between 55-70 mg/dl often occurring when therapeutic intervention includes meglitinides, sulfonylureas, or insulin since drugs themselves are among the most common causes. Glu (glucose), INS (insuline), EPI (epinephrine).

Fig. 2

A sample time series for adolescent T1D showing BG levels. The green region is normal (safe), yellow is the margin between normal and abnormal, and red is abnormal where BG levels are life-threatening. The problem is of two types: classify, but also forecasting. (A) shows a collection of paths that lead to the abnormal region. (B, C) looks as though they will be in the abnormal, but are not.

Fig. 3

(I) A dBG for 4-tuples over . Observe the Eularian path (A,B,, P) that captures all tuples. Many properties exist like reflection of graph. The de Bruijn sequence itself is lower left, A the start and P the end and is the most efficient encoding. By moving of this so-called drum, each 4-tuple can be recovered. (II) A snapshot of 15 minute intervals of a pediatric patient BG levels. We selected one that was reasonably easy to visualize, but even this one exhibits challenges in data. (III) A representation of the discretization and symbolics for II. Observe that the sharp changes in II. are still captured representing idiosyncrasies of the patient–perhaps exercise, eating, napping, signal problems. (IV) This shows a portion of our dBG representation. The path is shown (A,B,,I) given unique four-tuples with edges showing counts that characterize patterns beginning with 10.

Fig. 4

(Left) A high-level visualization of a dBG with 97 nodes and 167 edges using all available patients. The dBG is pruned with 10 uniform weight threshold. There are three BG regions: hyperglycemic, normal, and hypoglycemic. Dark blue nodes correspond to hypoglycemic values, while red nodes denote hyperglycemic values. (White arrows) Edge thickness indicates the frequency of the k-tuples, offering visual insight into their prevalence. (Brown arrows) There are only a few paths between the three regions and interestingly, all paths must path through normal BG. These ingress/egress paths are at the kernel of rules for anticipating hypoglycemia. (Right) Evaluation of patient results using leave-one-out cross-validation. We assessed the Balanced Accuracy, Precision, Sensitivity, and Specificity for all patients employing the leave-one-out cross-validation method. The average scores across all patients were 0.844, 0.268, 0.801, and 0.887 for these metrics, respectively. Additionally, the model achieved an F1 score of 0.402 and an Area Under the Curve of 0.89. These evaluations were conducted using adaptive pruning and with the parameters .

Algorithm 1

AdaptivePruning.

Algorithm 2

GetProbability.

Fig. 5

Timelines of alert predictions for P21. Correct and wrong predictions are marked with different colors. Gray data points are not used for evaluation, possibly due to the patient already being in a hypoglycemic state or gaps in the timeline. The upper timeline uses our dBG model, while the lower timeline uses the supervision ruleset along with the dBG model. Parameters: .

Fig. 6

Forecast times for every hypoglycemia case across all patients. The figure excludes 10 instances where our model did not issue warnings for hypoglycemic cases. Despite these, our model consistently forecasts hypoglycemia with a notable 30-minute lead time in the majority of cases, as denoted by the thick green marker in the figure.