Soft Computing

, Volume 21, Issue 2, pp 543–553 | Cite as

Hypoglycemia detection: multiple regression-based combinational neural logic approach

  • Sai Ho Ling
  • Phyo Phyo San
  • Hak Keung Lam
  • Hung T. Nguyen
Methodologies and Application
  • 185 Downloads

Abstract

Hypoglycemia is a common and serious side effect of type 1 diabetes. We measure physiological parameters continuously to provide detection of hypoglycemic episodes in type 1 diabetes mellitus patients using a multiple regression-based combinational neural logic approach. In this work, a neural logic network with multiple regression is applied to the development of non-invasive hypoglycemia monitoring system. It is an alarm system which measures the physiological parameters of electrocardiogram signal (heart rate and corrected QT interval) and determine the onset of hypoglycemia by the use of proposed hybrid neural logic approach. In this clinical application, a combinational neural logic network with multiple regression is systematically designed to hypoglycemia detection based on the characteristic of this application. To optimize the parameter of the hybrid combinational neural logic system, hybrid particle swarm optimization with wavelet mutation is applied to tuned the parameters of the system. To illustrate the effectiveness of the proposed method, hypoglycemia monitoring system which will be practically analyzed using real data sets collected from 15 children (\(14.6 \pm 1.5\) years) with type 1 diabetes at the Department of Health, Government of Western Australia. With the use of proposed method, the best testing sensitivity of 79.07 % and specificity of 53.64 % were obtained.

Keywords

Diabetes Binary logic system Neural network Hypoglycemia Particle swarm optimization 

Notes

Acknowledgments

The authors would like to thank Dr. Nejhdeh Ghevondian, and Assoc. Prof. Timothy Jones for their contribution. This work was supported by a grant from Juvenile Diabetes Research International.

References

  1. Alexakis C, Nyongesa HO, Saatchi R (2003) Feature extraction and classification of electrocardiogram (ECG) signals related to hypoglycaemia. In: Proceeding of computers in cardiology, pp 537–540Google Scholar
  2. Alexakis C, Nyongesa HO, Saatchi R (2006) A knowledge-based electrocardiogram monitoring system for detection of the onset of nocturnal hypoglycaemia in type 1 diabetic patients. In: Proceeding of computers in cardiology, p 58Google Scholar
  3. Altman DG, Bland JM (1994) Statistics Notes: Diagnostic tests 1: sensitivity and specificity. Clin Chem 308:1552–1552Google Scholar
  4. Amaral CF, Brischwein M, Wolf B (2009) Multiparameter techniques for non-invasive measurement of blood glucose. Sensors Actuators B: Chem 140(1):12–16CrossRefGoogle Scholar
  5. Castano J, Wang YZ, Chuang D (2000) Blood glucose dependence of visual flicker threshold. Diabetes Technol Ther 2:31–43CrossRefGoogle Scholar
  6. Chan KY, Ling SH, Dillon TS, Nguyen HT (2010) Classification of hypoglycemic episodes for type 1 diabetes mellitus based on neural networks. In: IEEE congress on evolutionary computation, pp 1–5Google Scholar
  7. Chen CJ, Chen TC, Ou JC (2006) Power system stabilizer using a new recurrent neural network for multi-machine. In: Power and energy conference, pp 68-72Google Scholar
  8. Duning T, Ellger B (1996) Is hypoglycaemia dangerous? Best Pract Res Clin Anaesthesiol 23(4):473–485CrossRefGoogle Scholar
  9. Freedman DA (2005) Statistical models: theory and practice. Cambridge University Press, New YorkCrossRefMATHGoogle Scholar
  10. Ghevondian N, Nguyen HT (1997) Using fuzzy logic reasoning for monitoring hypoglycaemia in diabetic patients. In: Proceeding of the 19th annual international conference of the IEEE Engineering in Medicine and Biology Society, vol 3, pp 1108–1111Google Scholar
  11. Ghevondian N, Nguyen HT, Colagiuri S (2001) A novel fuzzy neural network estimator for predicting hypoglycaemia in insulin-induced subjects. In: Proceeding of the 23rd annual international conference of the IEEE Engineering in Medicine and Biology Society, vol 2, pp 1657-1660Google Scholar
  12. Gill GV, Woodward A, Casson IF, Weston PJ (2009) Cardiac arrhythmia and nocturnal hypoglycaemia in type 1 diabetes: the ’dead in bed’ syndrome revisited. Diabetologia 52(1):42–45CrossRefGoogle Scholar
  13. Hansen KA, Duck SC (1983) Teledyne sleep sentry: evaluation in pediatric patients for detection of nocturnal hypoglycemia. Diabetes Care 6(6):597–600CrossRefGoogle Scholar
  14. Hastings G, Ghevondian N, Nguyen HT (1998) A self-organising fuzzy estimator for hypoglycaemia monitoring in diabetic patients. In: Proceeding of the 20th annual international conference of the IEEE Engineering in Medicine and Biology Society, pp 1371–1374Google Scholar
  15. Iaione F, Marques JL (2005) Methodology for hypoglycaemia detection based on the processing, analysis and classification of the electroencephalogram. Med Biol Eng Comput 43(4):501–507CrossRefGoogle Scholar
  16. Johansen K, Ellegaard S, Wex S (1986) Detection of nocturnal hypoglycemia in insulin-treated diabetics by a skin temperature: skin conductance meter. Acta Med Scand 220(3):213–217CrossRefGoogle Scholar
  17. Juhl CB, Hojlund K, Elsborg R (2010) Automated detection of hypoglycemia-induced EEG changes recorded by subcutaneous electrodes in subjects with type 1 diabetes. Diabetes Res Clin Pract 88(1):22–28CrossRefGoogle Scholar
  18. Klonoff DC (2001) The need for hypoglycemia detection and prevention in type 1 diabetes. Diabetes Technol Ther 3(4):567–570CrossRefGoogle Scholar
  19. Lam HK, Leung FHF (2007) Design and training for combinational neural-logic systems. IEEE Trans Ind Electron 54(1):612–619CrossRefGoogle Scholar
  20. Lam HK, Leung FHF (2009) Design and training for combinational neural-logic systems. IEEE Trans Ind Electron 54(1):612–619CrossRefGoogle Scholar
  21. Lee SP, Yeoh L, Harris ND (2004) Influence of autonomic neuropathy on QTc interval lengthening during hypoglycemia in type 1 diabetes. Diabetes 53:1535–1542CrossRefGoogle Scholar
  22. Leung FHF, Lam HK, Ling SH, Tam PKS (2003) Tuning of the structure and parameters of neural network using an improved genetic algorithm. IEEE Trans Neural Netw 14(1):79–88CrossRefGoogle Scholar
  23. Ling SH, Nguyen HT (2011) Genetic-algorithm-based multiple regression with guzzy inference system for detection of nocturnal hypoglycemic episodes. IEEE Trans Inf Technol Biomed 15(2):308–315CrossRefGoogle Scholar
  24. Ling SH, Iu HHC, Leung FHF, Chan KY (2008) Improved hybrid PSO-based wavelet neural network for modelling the development of fluid dispensing for electronic packaging. IEEE Trans Ind Electron 55(9):3447–3460CrossRefGoogle Scholar
  25. Ling SH, Nuryani N, Nguyen HT (2010) Evolved fuzzy reasoning model for hypoglycaemic detection. In: Proceeding of the 32th annual international conference of the IEEE Engineering in Medicine and Biology Society, pp 4662–4665Google Scholar
  26. Maia FFR, Arajo LR (2007) Efficacy of continuous glucose monitoring system (CGMS) to detect postprandial hyperglycemia and unrecognized hypoglycemia in type 1 diabetic patients. Diabetes Res Clin Pract 75(1):30–34CrossRefGoogle Scholar
  27. Maia FFR, Arajo LR (2007) Nocturnal hypoglycemia in patients with insulin-treated diabetes. Diabetes Res Clin Pract 75(1):30–34CrossRefGoogle Scholar
  28. Murphy NP, Ford-Adams ME, Ong KK (2004) Prolonged cardiac repolarisation during spontaneous nocturnal hypoglycaemia in children and adolescents with type 1 diabetes. Diabetologia 47:1940–1947CrossRefGoogle Scholar
  29. Nguyen HT, Ghevondian N, Jones TW (2006) Neural-network detection of hypoglycemic episodes in children with type 1 diabetes using physiological parameters. In: Proceedings of 28th annual international conference of the IEEE Engineering in Medicine and Biology Society, pp 6053–6056Google Scholar
  30. Nguyen HT, Ghevondian N, Nguyen ST, Jones TW (2007) Detection of hypoglycemic episodes in children with type 1 diabetes using an optimal Bayesian neural network algorithm. In: Proceedings of the international conference of IEEE Engineering in Medicine and Biology Society, pp 3140–3143Google Scholar
  31. Nguyen HT, Ghevondian N, Jones TW (2008) Detection of nocturnal hypoglycemic episodes (natural occurrence) in children with type 1 diabetes using an optimal Bayesian neural network algorithm. In: Proceeding of the 30th annual international conference of the IEEE Engineering in Medicine and Biology Society, pp 1311–1314Google Scholar
  32. Nuryani N, Ling SH, Nguyen HT (2011) Electrocardiographic signals and swarm-based support vector machine for hypoglycemia detection. Ann Biomed Eng 40(4):934–945CrossRefGoogle Scholar
  33. Nguyen LL, Su S, Nguyen HT (2012) Identification of Hypoglycemia and Hyperglycemia in Type 1 Diabetic Patients Using ECG Parameters. In: Proceeding of the 34th annual international conference of the IEEE Engineering in Medicine and Biology Society, pp 2716–2719Google Scholar
  34. Ryan C, Gurtunca N, Becker D (2005) Hypoglycemia: a complication of diabetes therapy in children. Semin Pediatr Neurol 12(3):163–177CrossRefGoogle Scholar
  35. Tanenberg RJ, Newton CA, Drake AJ (2010) Confirmation of hypoglycemia in the dead-in-bed syndrome, as captured by a retrospective continuous glucose monitoring system. Endocr Pract 16(2):244–248CrossRefGoogle Scholar
  36. Tierneya MJ, Pottsa RO, Jovanovicb L (2001) Clinical evaluation of the GlucoWatch biographer: a continual, non-invasive glucose monitor for patients with diabetes. Biosensors Bioelectron 16(9):621–629CrossRefGoogle Scholar
  37. Weinstein RL (2007) Accuracy of the freestyle navigator CGMS: comparison with frequent laboratory measurements. Diabetes Care 30:1125–1130Google Scholar
  38. Windrow B, Lehr MA (1990) 30 years of adaptive neural networks: perception, madaline and backpropagation. Proc IEEE 78(9):1415–1442CrossRefGoogle Scholar
  39. Xu J, Yang G, Man H, He H (2013) L 1 graph based on sparse coding for feature selection. Adv Neural Netw 7951:594–601Google Scholar
  40. Xua J, Heb H, Mana H (2012) DCPE co-training for classification. Neurocomputing 86(1):75–85CrossRefGoogle Scholar
  41. Yao J, Gan Q, Zhang DX, Li J (1998) Pruning algorithm in wavelet neural network for ECG signal classification. In: Proceedings of the 20th annual international conference of the IEEE Engineering in Medicine and Biology Society, vol 3, pp 1482–1485Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Sai Ho Ling
    • 1
  • Phyo Phyo San
    • 2
  • Hak Keung Lam
    • 3
  • Hung T. Nguyen
    • 1
  1. 1.Faculty of Engineering and Information Technology, Centre for Health TechnologiesUniversity of Technology SydneyUltimoAustralia
  2. 2.Data Analytics DepartmentInstitute for Infocomm ResearchSingaporeSingapore
  3. 3.Division of EngineeringKing’s College LondonLondonUK

Personalised recommendations