Model individualization for artificial pancreas
Introduction
Type 1 Diabetes Mellitus (T1DM), also known as insulin-dependent or juvenile diabetes, is a metabolic disorder characterized by chronic hyperglycemia that occurs when the pancreas is no longer able to produce insulin. Patients affected by T1DM are dependent on exogenous insulin administration to maintain the Blood Glucose (BG) concentration (also called glycemia) within the so called euglycemic range, which spans from 70 mg/dl to 180 mg/dl. Manual insulin administration is complex since there is the need to estimate the insulin dose to inject subcutaneously both during mealtimes and fasting periods. If the injected insulin is underestimated, the patient can experience hyperglycemia, which is generally associated to BG levels higher than 180–200 mg/dl. In addition, symptoms may not start to become noticeable until even higher BG levels, such as 250–300 mg/dl. Chronic hyperglycemia can produce a wide variety of serious complications over a period of years, including damages to kidneys, nervous system, cardiovascular system, retina, feet/legs and nerves (i.e. diabetic neuropathy). On the other hand, if the injected insulin is overestimated, the patient can experience hypoglycemia, which is associated to a BG level lower than 70 mg/dl. Hypoglycemia can cause tachycardia, shakiness, strong headache, sudden mood changes, hunger, sweating, dizziness and nausea, and, if severe, can lead to seizures, loss of consciousness, coma, or death.
The Artificial Pancreas (AP) is a system thought to automate the exogenous insulin supply and is composed of a subcutaneous glucose sensor, which allows Continuous Glucose Monitoring (CGM), a subcutaneous insulin pump, and a control algorithm. Recently, several research projects on AP were supported by the Juvenile Diabetes Research Foundation, the European Commission, and the National Institutes of Health (see Refs. [1], [2], [3], [4], [5], [6], [7], [8], [9]). The core of the AP is the control algorithm, which is in charge of continually estimating the quantity of insulin to inject in the subcutaneous tissue on the basis of the subcutaneous continuous glucose measurements. A detailed description of the state of the art of the considered AP system can be found in Ref. [10], where the adopted control algorithm is a Model Predictive Control (MPC). MPC synthesizes a controller on the basis of a model that describes the dynamics of the process under control (i.e. the biological dynamics of the patient). A complex metabolic model was first introduced in Ref. [11] and then improved in Ref. [12]. This model is highly nonlinear and time-varying and its implementation in a MPC law is computationally demanding. However, as shown in Refs. [13], [14], a linear time-invariant approximation of glucose–insulin interaction is adequate to capture the essential dynamics to design an effective and safe MPC, while guaranteeing reduced complexity and low computational burden in the MPC implementation. This fact was also confirmed by several clinical trials performed in silico [14], [15], [16], [17], [18], [19], [20] and in vivo [7], [9], [21], [22], [23], [24], [25], [26], [27] through MPC synthesized on the basis of a linear model.
Diabetic patients are characterized by a substantial inter-subject variability that may limit the closed-loop control performance achievable by a non-individualized controller. Thus, a significant step forward would be represented by the controller individualization that, however, is very challenging. The control performance could be limited even by the patient intra-subject variability, which would require a recursively adaptive control law [28]. Different approaches can be considered like multivariable adaptive control [29], [30] or run-to-run strategies used for daily adaptation of basal insulin [31], insulin boluses [32], [33], [34], [35], or MPC cost function [36].
In order to synthesize an individualized MPC, a patient-tailored glucose–insulin model is needed. The Nonparametric (NP) approach for linear models identification presented in Ref. [37] was applied to simulated data. An in silico trial was also performed, demonstrating that the MPC synthesized on the basis of the individualized models significantly improves closed-loop control performance. In addition to the NP approach, a parametric identification technique driven by Constrained Optimization (CO) is presented, where the identified models are characterized by a fixed structure that is postulated as prior knowledge. Models identification and test are based on in silico data collected during closed-loop simulations of clinical protocols designed to produce a sufficient input–output excitation without compromising the patient safety. The identified models are evaluated in terms of prediction performance by means of the Coefficient of Determination (COD), FIT, Positive and Negative Max Errors (PME and NME, respectively), and Root Mean Square Error (RMSE). The resulting performance is compared with the performance achieved by the NP models presented in Ref. [37] and with the average linear model used to synthesize the linear MPC introduced in Ref. [19], which was also used in several clinical experiments.
Section snippets
Methods
Given the large inter-subject variability, a significant improvement of blood-glucose control is expected using a control law individualized on patient-specific glucose–insulin responses instead of resorting to an average model [14], [19]. Two methods devoted to the patient glucose–insulin dynamics identification are presented in this section. Both the identification approaches are used to identify 100 linear models representing the dynamics of the 100 virtual patients of the adult population
Results
The testing results achieved by the presented individualization techniques applied to 100 adult virtual patients of the UVA/Padova simulator are shown in Table 4. In view of using the individualized models on an infinite horizon MPC [19], their quality has been evaluated in simulation. For this purpose, the NP models have been tested by considering the inputs u(k) and d(k) of (6) but not the past glucose values. It is evident that the identified models obtain a better prediction performance and
Conclusions
The identified individualized models significantly improve the prediction performance with respect to the linearized average model. The NP models provide the best performance, but are characterized by a non-fixed number of internal states that depend on the chosen realization technique. On the other hand, the postulated parametric structure of the CO models has a fixed number of internal states. While the CO approach does not guarantee the identification of a “valid” model, it requires a
References (41)
Challenges and recent progress in the development of a closed-loop artificial pancreas
Annu. Rev. Control
(2012)- et al.
Manual closed-loop insulin delivery in children and adolescent with type 1 diabetes: a phase 2 randomised crossover trial
Lancet
(2010) - et al.
Home use of closed-loop insulin delivery for overnight glucose control in adults with type 1 diabetes: a 4-week, multicentre, randomised crossover study
Lancet Diabetes Endocrinol
(2014) - et al.
2 month evening and night closed-loop glucose control in patients with type 1 diabetes under free-living conditions: a randomised crossover trial
Lancet Diabetes Endocrinol
(2015) - et al.
A novel nonparametric approach for the identification of the glucose-insulin system in type 1 diabetic patients
- et al.
Model predictive control of glucose concentration in type I diabetic patients: an in silico trial
Biomed. Signal Process. Control
(2009) - et al.
MPC based artificial pancreas: strategies for individualization and meal compensation
Annu. Rev. Control
(2012) - et al.
A constrained model predictive controller for an artificial pancreas
- et al.
Automatic adaptation of basal therapy for type 1 diabetic patients: a run-to-run approach
- et al.
Method for automatic adjustment of an insulin bolus calculator: in silico robustness evaluation under intra-day variability
Comput. Methods Programs Biomed
(2015)
A nonparametric approach for model individualization in an artificial pancreas
IFAC-PapersOnLine
A new kernel-based approach for linear system identification
Automatica
Prediction error identification of linear systems: a nonparametric Gaussian regression approach
Automatica
Diabetes: models, signals, and control
IEEE Rev. Biomed. Eng
A bihormonal closed-loop artificial pancreas for type 1 diabetes
Sci. Transl. Med
Fully-automated closed-loop insulin delivery versus semi-automated hybrid control in pediatric patients with type 1 diabetes using an artificial pancreas
Diabetes Care
Outpatient glycemic control with a bionic pancreas in type 1 diabetes
N. Engl. J. Med
Multicentre outpatient dinner/overnight reduction of hypoglycemia and increased time of glucose in target with a wearable artificial pancreas using multi-modular model predictive control algorithm in adults with type 1 diabetes
Diabetes Obes. Metab
Artificial pancreas: from in-silico to in-vivo
In silico preclinical trials: a proof of concept in closed-loop control of type 1 diabetes
J. Diabetes Sci. Technol
Cited by (40)
Robust adaptive observer-based control of blood glucose level for type 1 diabetic patient
2024, Biocybernetics and Biomedical EngineeringPersonalized hybrid artificial pancreas using unidirectional sliding-modes control algorithm
2022, Biocybernetics and Biomedical EngineeringGlucose forecasting using genetic programming and latent glucose variability features
2021, Applied Soft ComputingBlood glucose concentration prediction based on kernel canonical correlation analysis with particle swarm optimization and error compensation
2020, Computer Methods and Programs in Biomedicine
This paper is submitted to a Special Issue of Computer Methods and Programs in Biomedicine following the IFAC BMS 2015 meeting in Berlin.