Meal Detection and Carbohydrate Estimation Using Continuous Glucose Sensor Data

Abstract

A meal detection and meal-size estimation algorithm is developed for use in artificial pancreas (AP) control systems for people with type 1 diabetes. The algorithm detects the consumption of a meal and estimates its carbohydrate (CHO) amount to determine the appropriate dose of insulin bolus for a meal. It can be used in AP systems without manual meal announcements, or as a safety feature for people who may forget entering meal information manually. Using qualitative representation of the filtered continuous glucose monitor signal, a time period labeled as meal flag is identified. At every sampling time during this time period, a fuzzy system estimates the amount of CHO. Meal size estimator uses both glucose sensor and insulin data. Meal insulin bolus is based on estimated CHO. The algorithm does not change the basal insulin rate. Thirty in silico subjects of the UVa/Padova simulator are used to illustrate the performance of the algorithm. For the evaluation dataset, the sensitivity and false positives detection rates are 91.3% and 9.3%, respectively, the absolute error in CHO estimation is 23.1%, the mean blood glucose level is 142 mg/dl, and glucose concentration stays in target range (70-180 mg/dl) for 76.8% of simulation duration on average.

Artificial Intelligence for Diabetes Management and Decision Support: Literature Review

“…Meal detection is important in AP systems that do not permit manual meal announcements and as a safety system for patients who may forget to enter meal information manually. Turksoy et al have also investigated the development of a meal detection system based on analysis of CGM signals using an unscented Kalman filter and a fuzzy system to estimate the carbohydrates content [ 118 - 120 ]. Their approach was validated in silico with 30 T1D patients using the UVA/Padova simulator, which revealed a sensitivity of 91.3% and an error of 23.1% in carbohydrate estimation; and in vivo using data from 11 T1D patients, which revealed a sensitivity of 93.5% for meals and 68.0% for snacks.…”

Automatic Detection and Estimation of Unannounced Meals for Multivariable Artificial Pancreas System

“…Employing a fuzzy-logic-based model as the estimator precludes the use of mathematical insulin-glucose dynamic models. A discussion of the details for various steps of the algorithm is provided in Samadi et al 25 In the algorithm flowchart ( Fig. 1), the notion of meal flag plays an important role.…”

“…23 A physiological parameter-invariant meal detector was proposed by defining a design score equivalent to the confidence level in the occurrence of meal based on the minimal glucose-insulin model. 24 In our previous work, we introduced an automated meal detection algorithm based on fuzzy qualitative analysis of CGM data, 25 and an estimation technique that quantifies CHO amount in unannounced meals using CSII pump and CGM data. We compared our automated meal detection and CHO estimation algorithm with a meal announced approach by using the virtual patients of the University of Virginia/Padova (UVa/Padova) metabolic simulator.…”

Towards an Artificial Pancreas: Software Architectural Model and Implementation for Personalized Insulin Administration

“…Samadi et al [20] showed the algorithm for detecting meals and estimating their size in the form of carbohydrate amount.…”