“…Although AI and control engineering have converged to some extent as the two fields incrementally exchange methods, here we will focus on studies dealing with closed-loop algorithms based on AI techniques. We direct interested readers to a recent comprehensive review on AP systems [ 10 ].…”
BackgroundArtificial intelligence methods in combination with the latest technologies, including medical devices, mobile computing, and sensor technologies, have the potential to enable the creation and delivery of better management services to deal with chronic diseases. One of the most lethal and prevalent chronic diseases is diabetes mellitus, which is characterized by dysfunction of glucose homeostasis.ObjectiveThe objective of this paper is to review recent efforts to use artificial intelligence techniques to assist in the management of diabetes, along with the associated challenges.MethodsA review of the literature was conducted using PubMed and related bibliographic resources. Analyses of the literature from 2010 to 2018 yielded 1849 pertinent articles, of which we selected 141 for detailed review.ResultsWe propose a functional taxonomy for diabetes management and artificial intelligence. Additionally, a detailed analysis of each subject category was performed using related key outcomes. This approach revealed that the experiments and studies reviewed yielded encouraging results.ConclusionsWe obtained evidence of an acceleration of research activity aimed at developing artificial intelligence-powered tools for prediction and prevention of complications associated with diabetes. Our results indicate that artificial intelligence methods are being progressively established as suitable for use in clinical daily practice, as well as for the self-management of diabetes. Consequently, these methods provide powerful tools for improving patients’ quality of life.
“…Although AI and control engineering have converged to some extent as the two fields incrementally exchange methods, here we will focus on studies dealing with closed-loop algorithms based on AI techniques. We direct interested readers to a recent comprehensive review on AP systems [ 10 ].…”
BackgroundArtificial intelligence methods in combination with the latest technologies, including medical devices, mobile computing, and sensor technologies, have the potential to enable the creation and delivery of better management services to deal with chronic diseases. One of the most lethal and prevalent chronic diseases is diabetes mellitus, which is characterized by dysfunction of glucose homeostasis.ObjectiveThe objective of this paper is to review recent efforts to use artificial intelligence techniques to assist in the management of diabetes, along with the associated challenges.MethodsA review of the literature was conducted using PubMed and related bibliographic resources. Analyses of the literature from 2010 to 2018 yielded 1849 pertinent articles, of which we selected 141 for detailed review.ResultsWe propose a functional taxonomy for diabetes management and artificial intelligence. Additionally, a detailed analysis of each subject category was performed using related key outcomes. This approach revealed that the experiments and studies reviewed yielded encouraging results.ConclusionsWe obtained evidence of an acceleration of research activity aimed at developing artificial intelligence-powered tools for prediction and prevention of complications associated with diabetes. Our results indicate that artificial intelligence methods are being progressively established as suitable for use in clinical daily practice, as well as for the self-management of diabetes. Consequently, these methods provide powerful tools for improving patients’ quality of life.
“…[20][21][22] However, it appears that CL systems perform markedly better at night because daytime glycaemia is constantly challenged by casual events, such as meals of varied composition and exercise bouts of varying intensities and/or frequencies. 6 Thus, we decided to investigate the efficacy of the Diabeloop CL system in challenging real-life situations such as very large meals, which amplify hyperglycaemic excursions, a risk factor for chronic vascular complications [23][24][25] (see also high glycaemic variability as an aggravating factor for diabetes complications 24,[26][27][28] ).…”
Section: Discussionmentioning
confidence: 99%
“…Tight control of blood glucose (BG) reduces the risk of long‐term complications in type 1 diabetes (T1D), and automated insulin delivery (AID) systems have been proven safe and efficient to reduce BG variability . In particular, the Diabeloop (Paris, France) single‐hormone, closed‐loop (CL) AID device runs an original model predictive control (MPC) algorithm, which has proven safety and efficacy and has been validated in previous studies …”
Section: Introductionmentioning
confidence: 99%
“…Tight control of blood glucose (BG) reduces the risk of long-term complications in type 1 diabetes (T1D), 1,2 and automated insulin delivery (AID) systems have been proven safe and efficient to reduce BG variability. [3][4][5][6][7][8] In particular, the Diabeloop (Paris, France) single-hormone, closed-loop (CL) AID device runs an original model predictive control (MPC) algorithm, which has proven safety and efficacy and has been validated in previous studies. [9][10][11] In "real-life" conditions, daytime meals and postprandial hyperglycaemic excursions are difficult to control, 12,13 as is the BG variability associated with overnight fasting and physical exercise.…”
Aims
To compare closed‐loop (CL) and open‐loop (OL) systems for glycaemic control in patients with type 1 diabetes (T1D) exposed to real‐life challenging situations (gastronomic dinners or sustained physical exercise).
Methods
Thirty‐eight adult patients with T1D were included in a three‐armed randomized pilot trial (Diabeloop WP6.2 trial) comparing glucose control using a CL system with use of an OL device during two crossover 72‐hour periods in one of the three following situations: large (gastronomic) dinners; sustained and repeated bouts of physical exercise (with uncontrolled food intake); or control (rest conditions). Outcomes included time in spent in the glucose ranges of 4.4‐7.8 mmol/L and 3.9‐10.0 mmol/L, and time in hypo‐ and hyperglycaemia.
Results
Time spent overnight in the tight range of 4.4 to 7.8 mmol/L was longer with CL (mean values: 63.2% vs 40.9% with OL; P ≤ .0001). Time spent during the day in the range of 3.9 to 10.0 mmol/L was also longer with CL (79.4% vs 64.1% with OL; P ≤ .0001). Participants using the CL system spent less time during the day with hyperglycaemic excursions (glucose >10.0 mmol/L) compared to those using an OL system (17.9% vs 31.9%; P ≤ .0001), and the proportions of time spent during the day with hyperglycaemic excursions of those using the CL system in the gastronomic dinner and physical exercise subgroups were of similar magnitude to those in the control subgroup (18.1 ± 6.3%, 17.2 ± 8.1% and 18.4 ± 12.5%, respectively). Finally, times spent in hypoglycaemia were short and not significantly different among the groups.
Conclusions
The Diabeloop CL system is superior to OL devices in reducing hyperglycaemic excursions in patients with T1D exposed to gastronomic dinners, or exposed to physical exercise followed by uncontrolled food and carbohydrate intake.
“…Effects of alcohol may be delayed, with increased risk of hypoglycemia as long as 24-48 hours after consumption. This delay may be due in part to the reduction in nocturnal growth hormone secretion after alcohol consumption [58][59][60]. Moreover, after alcohol is metabolized, hepatic insulin sensitivity is increased, leading to the restoration of glycogen stores and reduction in blood glucose levels [61].…”
As wearable healthcare monitoring systems advance, there is immense potential for biological sensing to enhance the management of type 1 diabetes (T1D). The aim of this work is to describe the ongoing development of biomarker analytes in the context of T1D. Technological advances in transdermal biosensing offer remarkable opportunities to move from research laboratories to clinical point‐of‐care applications. In this review, a range of analytes, including glucose, insulin, glucagon, cortisol, lactate, epinephrine, and alcohol, as well as ketones such as beta‐hydroxybutyrate, will be evaluated to determine the current status and research direction of those analytes specifically relevant to T1D management, using both in‐vitro and on‐body detection. Understanding state‐of‐the‐art developments in biosensing technologies will aid in bridging the gap from bench‐to‐clinic T1D analyte measurement advancement.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.