“…Another false detection was associated with a sharp rise in glucose following the consumption of a rescue carbohydrate consumed in response to a hypoglycemia treatment. Given the possibility that a false meal detection could increase the risk of hypoglycemia, we calculated LBGI following false meal detections to see whether delivering insulin in response to a false alarm led to increased risk of low glucose(LBGI ≥ 5.0) 11 . The calculated LBGI was zero in three out of the four false detection cases indicating that no low glucose events had occurred.…”
Section: Discussionmentioning
confidence: 99%
“…Several approaches to automated meal detection have been described in the literature, which generally use continuous glucose measurements (CGM) and insulin delivery data, and in some cases physical activity data. Some of the approaches of previously published work include fuzzy logic 7 , Kalman filtering 8-10 , supertwisting observer combined with Kalman filtering 11 , probabilistic models 12 , quantification of the difference between predicted glucose using an autoregressive or other models vs. measured CGM values 13 , and glucose increase detection 14 . Smartwatch gesture-based meal reminders have also been proposed for improved postprandial glycemic control 15 .…”
We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glucose control in the four hours following unannounced meals using a hybrid model predictive control (MPC) algorithm and the RAP system. The RAP system includes a neural network model to automatically detect meals and deliver a recommended meal insulin dose. The meal detection algorithm has a sensitivity of 83.3%, false discovery rate of 16.6%, and mean detection time of 25.9 minutes. While there is no significant difference in incremental area under the curve of glucose, RAP significantly reduces time above range (glucose >180 mg/dL) by 10.8% (P = 0.04) and trends toward increasing time in range (70–180 mg/dL) by 9.1% compared with MPC. Time below range (glucose <70 mg/dL) is not significantly different between RAP and MPC.
“…Another false detection was associated with a sharp rise in glucose following the consumption of a rescue carbohydrate consumed in response to a hypoglycemia treatment. Given the possibility that a false meal detection could increase the risk of hypoglycemia, we calculated LBGI following false meal detections to see whether delivering insulin in response to a false alarm led to increased risk of low glucose(LBGI ≥ 5.0) 11 . The calculated LBGI was zero in three out of the four false detection cases indicating that no low glucose events had occurred.…”
Section: Discussionmentioning
confidence: 99%
“…Several approaches to automated meal detection have been described in the literature, which generally use continuous glucose measurements (CGM) and insulin delivery data, and in some cases physical activity data. Some of the approaches of previously published work include fuzzy logic 7 , Kalman filtering 8-10 , supertwisting observer combined with Kalman filtering 11 , probabilistic models 12 , quantification of the difference between predicted glucose using an autoregressive or other models vs. measured CGM values 13 , and glucose increase detection 14 . Smartwatch gesture-based meal reminders have also been proposed for improved postprandial glycemic control 15 .…”
We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glucose control in the four hours following unannounced meals using a hybrid model predictive control (MPC) algorithm and the RAP system. The RAP system includes a neural network model to automatically detect meals and deliver a recommended meal insulin dose. The meal detection algorithm has a sensitivity of 83.3%, false discovery rate of 16.6%, and mean detection time of 25.9 minutes. While there is no significant difference in incremental area under the curve of glucose, RAP significantly reduces time above range (glucose >180 mg/dL) by 10.8% (P = 0.04) and trends toward increasing time in range (70–180 mg/dL) by 9.1% compared with MPC. Time below range (glucose <70 mg/dL) is not significantly different between RAP and MPC.
“…On the other hand, a metal detector algorithm is proposed based on a super- twisting observer (ST) to detect the faults (meals). More information about the super-twisting observer is available [ 19 ] [ Figure 7 ].…”
Section: Meal Detection and Estimation Techniquesmentioning
OBJECTIVE: The development of an artificial pancreas is an open research problem that faces the challenge of creating a control algorithm capable of dosing insulin automatically and driving blood glucose to healthy levels. Many of these approaches, including artificial intelligence,
are based on techniques that could result in and undesirable outcome because most of them include neither detect meal intake or meal size information. To overcome that issue, some meal count-detection algorithms reported in scientific publications have shown not only a good performance on
blood glucose regulation but fewer hypoglicemia and hyperglycemia events too. METHODS: We reviewed the most relevant authors and publications and main databases (particularly SCOPUS and Google Scholar), focusing on algorithms of detection and estimation of meal intake from multiple
approaches. RESULTS: A wide range of approaches and proposals have been found. The majority of them include trials on in silico patients rather than in vivo ones. Most of procedures require as inputs glucose samples from continuous glucose monitoring devices as basal insulin and bolus
as well. Most of approaches could be grouped by 2 categories: mathematical model based and not model based. CONCLUSION: A combination of methods seems to reach better results.
“…This first contribution led to three journal articles (Sala-Mira et al 2019;Sala-Mira et al 2021;Faccioli et al 2022) The module developed in the first contribution yielded acceptable results against unannounced meals; however, exercise-induced hypoglycemia would unlikely be compensated with this module due to the long offset action of insulin. Thus, a new module was designed to overcome this limitation by suggesting carbohydrate intake (Chapter 7).…”
Section: Discussionmentioning
confidence: 99%
“…Sala-Mira et al (2019) also presented and validated a preliminary implementation of the meal detector and the bolusing algorithm. Finally, the improvements of the meal detector algorithm described in Chapter 5 (e.g., implicit discretization or noise reduction) were presented inFaccioli et al (2021) andFaccioli et al (2022), including more comprehensive validations than the one included in Chapter 3.…”
A todas las personas que me han ayudado, apoyado y aguantado. Muchas gracias.To all the people who have helped, supported, and put up with me. Thank you very much.Mindazoknak, akik segítettek, támogatottak és eltűrtek engem. Nagyon szépen köszönjük.
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.