3D kernel-density stochastic model for more personalized glycaemic control: development and in-silico validation

Abstract

BackgroundThe challenges of glycaemic control in critically ill patients have been debated for 20 years. While glycaemic control shows benefits inter- and intra-patient metabolic variability results in increased hypoglycaemia and glycaemic variability, both increasing morbidity and mortality. Hence, current recommendations for glycaemic control target higher glycaemic ranges, guided by the fear of harm. Lately, studies have proven the ability to provide safe, effective control for lower, normoglycaemic, ranges, using model-based computerised methods. Such methods usually identify patient-specific physiological parameters to personalize titration of insulin and/or nutrition. The Stochastic-Targeted (STAR) glycaemic control framework uses patient-specific insulin sensitivity and a stochastic model of its future variability to directly account for both inter- and intra-patient variability in a risk-based insulin-dosing approach.ResultsIn this study, a more personalized and specific 3D version of the stochastic model used in STAR is compared to the current 2D stochastic model, both built using kernel-density estimation methods. Fivefold cross validation on 681 retrospective patient glycaemic control episodes, totalling over 65,000 h of control, is used to determine whether the 3D model better captures metabolic variability, and the potential gain in glycaemic outcome is assessed using validated virtual trials. Results show that the 3D stochastic model has similar forward predictive power, but provides significantly tighter, more patient-specific, prediction ranges, showing the 2D model over-conservative > 70% of the time. Virtual trial results show that overall glycaemic safety and performance are similar, but the 3D stochastic model reduced median blood glucose levels (6.3 [5.7, 7.0] vs. 6.2 [5.6, 6.9]) with a higher 61% vs. 56% of blood glucose within the 4.4–6.5 mmol/L range.ConclusionsThis improved performance is achieved with higher insulin rates and higher carbohydrate intake, but no loss in safety from hypoglycaemia. Thus, the 3D stochastic model developed better characterises patient-specific future insulin sensitivity dynamics, resulting in improved simulated glycaemic outcomes and a greater level of personalization in control. The results justify inclusion into ongoing clinical use of STAR.

Understanding insulin and nutrition administration in glycemic control with the right side of the brain

“…SI can vary signi cantly between and within critically ill patients [8,37,89]. Figures 6-8 describe the impact of SI variability on glycemic outcome and safety, and demonstrate the potential need to manage nutrition delivery to mitigate hypo-and hyper-glycemic risk.…”

“…Figures 6-8 describe the impact of SI variability on glycemic outcome and safety, and demonstrate the potential need to manage nutrition delivery to mitigate hypo-and hyper-glycemic risk. Figure 7 illustrates the risk of SI variability, where critically ill patients have signi cant variability in their hour-hour insulin sensitivity, particularly early in ICU stay [89,105]. Hypoglycemic risk from rising SI ( ) can result in moderate or severe hypoglycemia in up to 10% of hours in the rst 1-3 days of stay, depending on insulin dose [106].…”

“…Clinically, it is possible to quantify and thus account for this variability, creating an objective means to reduce hypoglycemic and hyperglycemic risk [89,105,[107][108][109][110].…”

“…ICU patients display signi cant intra-patient metabolic, and thus outcome glycemic, variability [8,37,89]. Figure 7 the outcome effects of variability in insulin sensitivity, .…”

Risk and reward: extending stochastic glycaemic control intervals to reduce workload

“…This outcome also emphasises the importance of accurately characterising intrapatient variability, where improved predictions would improve GC outcome. Ongoing studies are assessing the benefits of using more complex stochastic models [35,[43][44][45], and are currently being tested in clinical trials to validate the results. However, as this is a first study analysing longer treatment intervals, the well-proven original stochastic model approach is used here.…”