Real-time model-based fault detection of continuous glucose sensor measurements

IEEE Transactions on Biomedical Engineering

Volumn 64, Issue 7, 2017, Pages 1437-1445

  Turksoy, Kamuran ^a   Roy, Anirban ^b   Cinar, Ali ^a  

^a Illinois Institute of Technology   (United States)

^b Medtronic Diabetes   (United States)

Author keywords

Continuous glucose sensor failures; Fault detection; K nearest neighbor (KNN) classification; Principal component analysis (PCA); Unscented Kalman filter (UKF)

Indexed keywords

ARTIFICIAL ORGANS; COMPUTER AIDED DIAGNOSIS; DIAGNOSIS; GLUCOSE; GLUCOSE SENSORS; INSULIN; KALMAN FILTERS; MOTION COMPENSATION; NEAREST NEIGHBOR SEARCH; PRINCIPAL COMPONENT ANALYSIS;

CONTINUOUS GLUCOSEMONITORING (CGM); FAULT DETECTION ALGORITHM; K NEAREST NEIGHBOR (KNN); K-NEAREST NEIGHBOR CLASSIFICATION; SENSOR FAILURE; STATE AND PARAMETER ESTIMATIONS; STATISTICAL MONITORING; UNSCENTED KALMAN FILTER;

FAULT DETECTION;

FATTY ACID; GLUCOSE; INSULIN; GLUCOSE BLOOD LEVEL;

ARTICLE; BLOOD GLUCOSE MONITORING; CLASSIFICATION ALGORITHM; COMPARTMENT MODEL; EXTENDED MINIMAL MODEL; FATTY ACID BLOOD LEVEL; GLUCOSE BLOOD LEVEL; GLUCOSE SENSOR; HUMAN; INSULIN DEPENDENT DIABETES MELLITUS; INSULIN INFUSION; INSULIN TREATMENT; K NEAREST NEIGHBOR; MAJOR CLINICAL STUDY; MEASUREMENT ERROR; MULTIVARIATE ANALYSIS; NONLINEAR SYSTEM; PRINCIPAL COMPONENT ANALYSIS; UNSCENTED KALMAN FILTER; ALARM MONITOR; ANALYSIS; BIOLOGICAL MODEL; BLOOD; COMPUTER ASSISTED DRUG THERAPY; COMPUTER SIMULATION; COMPUTER SYSTEM; DEVICE FAILURE ANALYSIS; DIABETES MELLITUS, TYPE 1; DIAGNOSTIC ERROR; METABOLISM; PREVENTION AND CONTROL; PROCEDURES; REPRODUCIBILITY; SENSITIVITY AND SPECIFICITY; STATISTICAL MODEL;

BLOOD GLUCOSE; CLINICAL ALARMS; COMPUTER SIMULATION; COMPUTER SYSTEMS; DIABETES MELLITUS, TYPE 1; DIAGNOSTIC ERRORS; DRUG THERAPY, COMPUTER-ASSISTED; EQUIPMENT FAILURE ANALYSIS; HUMANS; INSULIN; MODELS, BIOLOGICAL; MODELS, STATISTICAL; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY;

EID: 85026676593     PISSN: 00189294     EISSN: 15582531     Source Type: Journal    
DOI: 10.1109/TBME.2016.2535412     Document Type: Article

References (44)

1. E. Renard et al., "Closed-loop insulin delivery using a subcutaneous glucose sensor and intraperitoneal insulin delivery: feasibility study testing a new model for the artificial pancreas", Diabetes Care, vol. 33, no. 1, pp. 121-127, Jan. 2010.
2. R. Hovorka et al., "Manual closed-loop insulin delivery in children and adolescents with type 1 diabetes: A phase 2 randomised crossover trial", Lancet, vol. 375, no. 9716, pp. 743-751, 2010.
3. B. Kovatchev et al., "Multinational study of subcutaneous modelpredictive closed-loop control in type 1 diabetes mellitus: summary of the results", J. Diabetes Sci. Technol., vol. 4, no. 6, pp. 1374-1381, Nov. 2010.
4. D. Elleri et al., "Closed-loop basal insulin delivery over 36 hours in adolescents with type 1 diabetes randomized clinical trial", Diabetes Care, vol. 36, no. 4, pp. 838-844, 2013.
5. K. Turksoy et al., "Multivariable adaptive closed-loop control of an artificial pancreas without meal and activity announcement", Diabetes Technol. Therapeutics, vol. 15, no. 5, pp. 386-400, 2013.
6. R. Nimri et al., "Night glucose control with md-logic artificial pancreas in home setting: A single blind, randomized crossover trialinterim analysis", Pediatric Diabetes, vol. 15, no. 2, pp. 91-99, 2014.
7. M. D. Breton et al., "Adding heart rate signaltoacontrol-to-range artificial pancreas system improves the protection against hypoglycemia during exercise in type 1 diabetes", Diabetes Technol. Therapeutics, vol. 16, pp. 506-511, 2014.
8. K. Turksoy et al., "An integrated multivariable artificial pancreas control system", J. Diabetes Sci. Technol., vol. 8, no. 3, pp. 498-507, 2014.
9. F. H. El-Khatib et al., "Autonomous and continuous adaptation of a bihormonal bionic pancreas in adults and adolescents with type 1 diabetes", J. Clin. Endocrinology Metabolism, vol. 99, no. 5, pp. 1701-1711, 2014.
10. K. Turksoy et al., "Multivariable adaptive identification and control for artificial pancreas systems", IEEE Trans. Biomed. Eng., vol. 61, no. 3, pp. 883-891, Mar. 2014.
11. D. J. DeSalvo et al., "Remote glucose monitoring in camp setting reduces the risk of prolonged nocturnal hypoglycemia", Diabetes Technol. Therapeutics, vol. 16, no. 1, pp. 1-7, 2014.
12. B. P. Kovatchev et al., "Safety of outpatient closed-loop control: First randomized crossover trials of a wearable artificial pancreas", Diabetes Care, vol. 37, no. 7, pp. 1789-1796, 2014.
13. B. W. Bequette, "Fault detection and safety in closed-loop artificial pancreas systems", J. Diabetes Sci. Technol., vol. 8, pp. 1204-1214, 2014.
14. V. Venkatasubramanian et al., "A review of process fault detection and diagnosis: Part I: Quantitative model-based methods", Comput. Chem. Eng., vol. 27, no. 3, pp. 293-311, 2003.
15. A. Cinar et al., Batch Fermentation: Modeling: Monitoring, and Control. Boca Raton, FL, USA: CRC Press, 2003.
16. R. N. Bergman et al., "Physiologic evaluation of factors controlling glucose tolerance in man: Measurement of insulin sensitivity and betacell glucose sensitivity from the response to intravenous glucose." J. Clin. Investigation, vol. 68, no. 6, pp. 1456-1467, 1981.
17. C. Cobelli et al., "Estimation of insulin sensitivity and glucose clearance from minimal model: new insights from labeled IVGTT", Am. J. Physiol. Endocrinol. Metabolism, vol. 250, no. 5, pp. E591-E598, 1986.
18. C. Cobelli et al., "Minimal model sgoverestimation and siunderestimation: Improved accuracy by a Bayesian two-compartment model", Am. J. Physiol. Endocrinol. Metabolism, vol. 277, no. 3, pp. E481-E488, 1999.
19. R. Hovorka et al., "Partitioning glucose distribution/transport, disposal, and endogenous production during ivgtt", Am. J. Physiol. Endocrinol. Metabolism, vol. 282, no. 5, pp. E992-E1007, 2002.
20. A. Roy and R. S. Parker, "Dynamic modeling of free fatty acid, glucose, and insulin: An extended "minimal model"", Diabetes Technol. Therapeutics, vol. 8, no. 6, pp. 617-626, 2006.
21. A. Roy and R. S. Parker, "Dynamic modeling of exercise effects on plasma glucose and insulin levels", J. Diabetes Sci. Technol., vol. 1, no. 3, pp. 338-347, 2007.
22. S. S. Kanderian et al., "Identification of intraday metabolic profiles during closed-loop glucose control in individuals with type 1 diabetes", J. Diabetes Sci. Technol., vol. 3, no. 5, pp. 1047-1057, 2009.
23. S. J. Julier and J. K. Uhlmann, "Unscented filtering and nonlinear estimation", Proc. IEEE, vol. 92, no. 3, pp. 401-422, Mar. 2004.
24. E. A. Wan and R. Van Der Merwe, "The unscented Kalman filter for nonlinear estimation", in Proc. IEEE Adaptive Syst. Signal Process., Commun. Control Symp., 2000, pp. 153-158.
25. J. Bondia et al., "Using support vector machines to detect therapeutically incorrect measurements by the Minimed CGMS", J. Diabetes Sci. Technol., vol. 2, no. 4, pp. 622-629, 2008.
26. Y. Leal et al., "Detection of correct and incorrect measurements in realtime continuous glucose monitoring systems by applying a postprocessing support vector machine", IEEE Trans. Biomed. Eng., vol. 60, no. 7, pp. 1891-1899, Jul. 2013.
27. Q. Shen et al., "Online dropout detection in subcutaneously implanted continuous glucose monitoring", in Proc. IEEE Am. Control Conf., 2010, pp. 4373-4378.
28. G. Campetelli et al., "Improvementsonnoninvasive blood glucose biosensors using wavelets for quick fault detection", J. Sensors, vol. 2011, art. 368015, 2011.
29. A. Facchinetti et al., "Detecting failures of the glucose sensor-insulin pump system: Improved overnight safety monitoring for type-1 diabetes", in Proc. IEEE Eng. Med. Biol. Soc. Conf., 2011, pp. 4947-4950.
30. N. Baysal et al., "A novel method to detect pressure-induced sensor attenuations (PISA) in an artificial pancreas", J. Diabetes Sci. Technol., vol. 8, no. 6, pp. 1091-1096, 2014.
31. M. Signal et al., "Using stochastic modelling to identify unusual continuous glucose monitor measurements and behaviour, in newborn infants", Biomed. Eng. Online, vol. 11, no. 1, p. 45, 2012.
32. N. Baysal et al., "Detecting sensor and insulin infusion set anomalies in an artificial pancreas", in Proc. IEEE Am. Control Conf., 2013, pp. 2929-2933.
33. Y. Leal et al., "Principal component analysis in combination with casebased reasoning for detecting therapeutically correct and incorrect measurements in continuous glucose monitoring systems", Biomed. Signal Process. Control, vol. 8, no. 6, pp. 603-614, 2013.
34. A. Cinar et al., Chemical Process Performance Evaluation. Boca Raton, FL, USA: CRC Press, 2007.
35. R. Kandepu et al., "Applying the unscented Kalman filter for nonlinear state estimation", J. Process Control, vol. 18, no. 7, pp. 753-768, 2008.
36. C. Dalla Man et al., "The UVA/Padova type 1 diabetes simulator new features", J. Diabetes Sci. Technol., vol. 8, no. 1, pp. 26-34, 2014.
37. R. Van Der Merwe, "Sigma-point Kalman filters for probabilistic inference in dynamic state-space models", Ph. D. dissertation, Oregon Health Sci. Univ., Portland, OR, USA, 2004.
38. M. de Bock et al., "Day and night glucose control using a hybrid closed loop system for the management of type 1 diabetes", Int. J. Pediatric Endocrinol., vol. 2015, no. Suppl 1, p. P26, 2015.
39. A. Roy et al., "Physiological and technical stress test for medtronic's artificial pancreas system in a supervised outpatient setting", Diabetes Technol. Therapeutics, vol. 17, pp. A18-A18, 2015.
40. J. Kropff et al., "Accuracy of two continuous glucose monitoring systems: A head-to-head comparison under clinical research centre and daily life conditions", Diabetes, Obesity Metabolism, vol. 17, no. 4, pp. 343-349, 2015.
41. J. MacGregor and A. Cinar, "Monitoring, fault diagnosis, fault-tolerant control and optimization: Data driven methods", Comput. Chem. Eng., vol. 47, pp. 111-120, 2012.
42. V. Venkatasubramanian et al., "A review of process fault detection and diagnosis: Part iii: Process history based methods", Comput. Chem. Eng., vol. 27, no. 3, pp. 327-346, 2003.
43. M. Eren-Oruklu et al., "Adaptive system identification for estimating future glucose concentrations and hypoglycemia alarms", Automatica, vol. 48, no. 8, pp. 1892-1897, 2012.
44. K. Turksoy et al., "Hypoglycemia early alarm systems based on multivariable models", Ind. Eng. Chem. Res., vol. 52, no. 35, pp. 12329-12336, 2013.