Adaptive system identification for estimating future glucose concentrations and hypoglycemia alarms

• Published in: Automatica (Oxford) Vol. 48; no. 8; pp. 1892 - 1897
• Main Authors: Eren-Oruklu, Meriyan, Cinar, Ali, Rollins, Derrick K., Quinn, Lauretta
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.08.2012; Elsevier
• Subjects: Adaptive systems; Alarms; Algorithms; Applied sciences; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Control theory. Systems; Estimating; Exact sciences and technology; Glucose; Hypoglycemia; Identification algorithms; Mathematical models; Modeling and identification; Modelling and identification; Monitors; Parameter and state estimation; Recursive estimation; Software; Identification algorithms; Modeling and identification; Parameter and state estimation; Recursive estimation; Endocrinopathy; Human; Parameter estimation; On line; Event detection; Adaptive system; Variability; Time series; Activity; Metabolic diseases; N body system; Glucose; Metabolism; Modeling; Least squares method; Alarm; Recursive method; System identification; Sensor array; State estimation
• ISSN: 0005-1098; 1873-2836
• DOI: 10.1016/j.automatica.2012.05.076

Many patients with diabetes experience high variability in glucose concentrations that includes prolonged hyperglycemia or hypoglycemia. Models predicting a subject’s future glucose concentrations can be used for preventing such conditions by providing early alarms. This paper presents a time-series model that captures dynamical changes in the glucose metabolism. Adaptive system identification is proposed to estimate model parameters which enable the adaptation of the model to inter-/intra-subject variation and glycemic disturbances. It consists of on-line parameter identification using the weighted recursive least squares method and a change detection strategy that monitors variation in model parameters. Univariate models developed from a subject’s continuous glucose measurements are compared to multivariate models that are enhanced with continuous metabolic, physical activity and lifestyle information from a multi-sensor body monitor. A real life application for the proposed algorithm is demonstrated on early (30 min in advance) hypoglycemia detection.