Dataset Information

In Silico Testing of an Artificial-Intelligence-Based Artificial Pancreas Designed for Use in the Intensive Care Unit Setting.

ABSTRACT:

Background

Effective glucose control in the intensive care unit (ICU) setting has the potential to decrease morbidity and mortality rates which should in turn lead to decreased health care expenditures. Current ICU-based glucose controllers are mathematically derived, and tend to be based on proportional integral derivative (PID) or model predictive control (MPC). Artificial intelligence (AI)-based closed loop glucose controllers may have the ability to achieve control that improves on the results achieved by either PID or MPC controllers.

Method

We conducted an in silico analysis of an AI-based glucose controller designed for use in the ICU setting. This controller was tested using a mathematical model of the ICU patient's glucose-insulin system. A total of 126?000 unique 5-day simulations were carried out, resulting in 107 million glucose values for analysis.

Results

For the 7 control ranges tested, with a sensor error of ±10%, the following average results were achieved: (1) time in control range, 94.2%, (2) time in range 70-140 mg/dl, 97.8%, (3) time in hyperglycemic range (>140 mg/dl), 2.1%, and (4) time in hypoglycemic range (<70 mg/dl), 0.09%. In addition, the average coefficient of variation (CV) was 11.1%.

Conclusions

This in silico study of an AI-based closed loop glucose controller shows that it may be able to improve on the results achieved by currently existing ICU-based PID/MPC controllers. If these results are confirmed in clinical testing, this AI-based controller could be used to create an artificial pancreas system for use in the ICU setting.

SUBMITTER: DeJournett L

PROVIDER: S-EPMC5094333 | biostudies-literature | 2016 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

In Silico Testing of an Artificial-Intelligence-Based Artificial Pancreas Designed for Use in the Intensive Care Unit Setting.

DeJournett Leon L DeJournett Jeremy J

Journal of diabetes science and technology 20161101 6

<h4>Background</h4>Effective glucose control in the intensive care unit (ICU) setting has the potential to decrease morbidity and mortality rates which should in turn lead to decreased health care expenditures. Current ICU-based glucose controllers are mathematically derived, and tend to be based on proportional integral derivative (PID) or model predictive control (MPC). Artificial intelligence (AI)-based closed loop glucose controllers may have the ability to achieve control that improves on t ...[more]

PMID: 27301982

Similar Datasets

Project description:BackgroundEffective glucose control in the intensive care unit (ICU) setting has the potential to decrease morbidity and mortality rates and thereby decrease health care expenditures. To evaluate what constitutes effective glucose control, typically several metrics are reported, including time in range, time in mild and severe hypoglycemia, coefficient of variation, and others. To date, there is no one metric that combines all of these individual metrics to give a number indicative of overall performance. We proposed a composite metric that combines 5 commonly reported metrics, and we used this composite metric to compare 6 glucose controllers.MethodsWe evaluated the following controllers: Ideal Medical Technologies (IMT) artificial-intelligence-based controller, Yale protocol, Glucommander, Wintergerst et al PID controller, GRIP, and NICE-SUGAR. We evaluated each controller across 80 simulated patients, 4 clinically relevant exogenous dextrose infusions, and one nonclinical infusion as a test of the controller's ability to handle difficult situations. This gave a total of 2400 5-day simulations, and 585?604 individual glucose values for analysis. We used a random walk sensor error model that gave a 10% MARD. For each controller, we calculated severe hypoglycemia (<40 mg/dL), mild hypoglycemia (40-69 mg/dL), normoglycemia (70-140 mg/dL), hyperglycemia (>140 mg/dL), and coefficient of variation (CV), as well as our novel controller metric.ResultsFor the controllers tested, we achieved the following median values for our novel controller scoring metric: IMT: 88.1, YALE: 46.7, GLUC: 47.2, PID: 50, GRIP: 48.2, NICE: 46.4.ConclusionThe novel scoring metric employed in this study shows promise as a means for evaluating new and existing ICU-based glucose controllers, and it could be used in the future to compare results of glucose control studies in critical care. The IMT AI-based glucose controller demonstrated the most consistent performance results based on this new metric.

Project description:OBJECTIVE:To determine whether intensive care medicine therapies and testing influence hypothalamic-pituitary-adrenal test results. It is routine in intensive care medicine to measure hypothalamic-pituitary-adrenal function, commonly utilizing the adrenocorticotropic hormone stimulation test to diagnose absolute or relative adrenal insufficiency. DESIGN:Prospective, 96-hr animal study. SETTING:Research laboratory. SUBJECTS:Twenty-four healthy canines. INTERVENTIONS:Animals were randomized into two groups--awake and unrestrained or treated with intensive care medicine therapies, including sedation, intubation, and mechanical ventilation. Animals were further randomized to receive dexamethasone (or placebo) or undergo either a total of four or seven adrenocorticotropic hormone stimulation tests over 96 hrs. MEASUREMENTS AND MAIN RESULTS:Sedation, intubation, and mechanical ventilation transiently increased both basal and postadrenocorticotropic hormone total and free cortisol concentrations >2-fold as compared with baseline for the first 24 hrs (p < or = .05 for both). Performance of seven stimulation tests increased both basal and postadrenocorticotropic hormone total and free cortisol concentrations from baseline by >1.5-fold for the duration of the 96-hr study (p < or = .05). Neither sedation, intubation, and mechanical ventilation nor the performance of more stimulation tests affected delta cortisol measurements (total or free cortisol, p = NS). In contrast, dexamethasone suppressed basal total cortisol concentrations by >2-fold (p < or = .005) at all time points and transiently increased delta total cortisol by approximately 35% during the first 24 hrs of the study (p < or = .05). CONCLUSIONS:Total and free cortisol measurements--whether pre- or post- adrenocorticotropic hormone or as a calculated delta--were altered by intensive care therapies or frequent adrenocorticotropic hormone stimulation testing with one exception. Delta free cortisol was the only hypothalamic-pituitary-adrenal measurement unaffected by sedation, intubation, and mechanical ventilation, completion of more adrenocorticotropic hormone stimulation tests, or dexamethasone therapy. These findings support the need to determine normal ranges for hypothalamic-pituitary-adrenal testing in subjects receiving intensive care medicine before establishing laboratory criteria for the diagnosis of relative adrenal insufficiency.

Dataset Information

In Silico Testing of an Artificial-Intelligence-Based Artificial Pancreas Designed for Use in the Intensive Care Unit Setting.

Background

Method

Results

Conclusions

Publications

In Silico Testing of an Artificial-Intelligence-Based Artificial Pancreas Designed for Use in the Intensive Care Unit Setting.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets