Super–twisting-based meal detector for type 1 diabetes management: Improvement and assessment in a real-life scenario

Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence

“…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.…”

“…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 .…”

Artificial Pancreas: A Review of Meal Detection and Carbohydrates Counting Techniques

“…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 ].…”

New Contributions Towards Meal and Exercise Announcement-Free Artificial Pancreas Systems

“…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).…”

“…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.…”