Unannounced Meal Detection for Artificial Pancreas Systems Using Extended Isolation Forest

This study aims at developing an unannounced meal detection method for artificial pancreas, based on a recent extension of Isolation Forest. The proposed method makes use of features accounting for individual Continuous Glucose Monitoring (CGM) profiles and benefits from a two-threshold decision rule detection. The advantage of using Extended Isolation Forest (EIF) instead of the standard one is supported by experiments on data from virtual diabetic patients, showing good detection accuracy with acceptable detection delays.

[1]  Øyvind Stavdahl,et al.  Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1 , 2020, IEEE Journal of Biomedical and Health Informatics.

[2]  R. Hovorka,et al.  Partitioning glucose distribution/transport, disposal, and endogenous production during IVGTT. , 2002, American journal of physiology. Endocrinology and metabolism.

[3]  Pierre Jallon,et al.  Closed-loop insulin delivery in adults with type 1 diabetes in real-life conditions: a 12-week multicentre, open-label randomised controlled crossover trial. , 2019, The Lancet. Digital health.

[4]  Beatriz Ricarte,et al.  Sliding-mode disturbance observers for an artificial pancreas without meal announcement , 2019, Journal of Process Control.

[5]  Benoit Boulet,et al.  An Unannounced Meal Detection Module for Artificial Pancreas Control Systems , 2019, 2019 American Control Conference (ACC).

[6]  Claudio Cobelli,et al.  Data-Driven Anomaly Recognition for Unsupervised Model-Free Fault Detection in Artificial Pancreas , 2020, IEEE Transactions on Control Systems Technology.

[7]  Ali Cinar,et al.  Meal Detection in Patients With Type 1 Diabetes: A New Module for the Multivariable Adaptive Artificial Pancreas Control System , 2016, IEEE Journal of Biomedical and Health Informatics.

[8]  Garry M. Steil,et al.  Identification of Intraday Metabolic Profiles during Closed-Loop Glucose Control in Individuals with Type 1 Diabetes , 2009, Journal of diabetes science and technology.

[9]  Josep Vehí,et al.  Unannounced Meals in the Artificial Pancreas: Detection Using Continuous Glucose Monitoring , 2018, Sensors.

[10]  Y. Z. Ider,et al.  Quantitative estimation of insulin sensitivity. , 1979, The American journal of physiology.

[11]  Qian Wang,et al.  A Variable State Dimension Approach to Meal Detection and Meal Size Estimation: In Silico Evaluation Through Basal-Bolus Insulin Therapy for Type 1 Diabetes , 2017, IEEE Transactions on Biomedical Engineering.

[12]  R. Rabasa-Lhoret,et al.  The challenges of achieving postprandial glucose control using closed‐loop systems in patients with type 1 diabetes , 2018, Diabetes, obesity & metabolism.

[13]  Peter Christen,et al.  A note on using the F-measure for evaluating record linkage algorithms , 2017, Statistics and Computing.

[14]  Robert J. Brunner,et al.  Extended Isolation Forest , 2018, IEEE Transactions on Knowledge and Data Engineering.

[15]  Zhi-Hua Zhou,et al.  Isolation Forest , 2008, 2008 Eighth IEEE International Conference on Data Mining.