Electromyogram prediction during anesthesia by using a hybrid intelligent model

  • José-Luis Casteleiro-Roca
  • Marco Gomes
  • Juan Albino Méndez-Pérez
  • Héctor Alaiz-MoretónEmail author
  • María del Carmen Meizoso-López
  • Benigno Antonio Rodríguez-Gómez
  • José Luis Calvo-Rolle
Original Research


In the search for new and more efficient ways to administer drugs, clinicians are turning to engineering tools. The availability of these models to predict physiological variables are a significant factor. A model is set out in this research to predict the EMG (electromyogram) signal during surgery, in patients under general anaesthesia. This prediction hinges on the Bispectral Index™ (BIS) and the infusion rate of the drug propofol. The results of the research are very satisfactory, with error values of less than 0.67 (for a Normalized Mean Squared Error). A hybrid intelligent model is used which combines both clustering and regression algorithms. The resulting model is validated and trained using real data.


EMG BIS™ Clustering MLP SVM 



This study was conducted under the auspices of Research Project DPI2010-18278, supported by the Spanish Ministry of Innovation and Science.


  1. Aláiz-Moretón H, Castejón-Limas M, Casteleiro-Roca J-L, Jove E, Fernández Robles L, Calvo-Rolle JL (2019) A fault detection system for a geothermal heat exchanger sensor based on intelligent techniques. Sensors 19(12):2740. Google Scholar
  2. Bishop C (2006) Pattern recognition and machine learning (information science and statistics). Springer, New YorkzbMATHGoogle Scholar
  3. Bursa M, Lhotska L, Chudacek V, Spilka J, Janku P, Hruban L (2015) Information retrieval from hospital information system: increasing effectivity using swarm intelligence. J Appl Log 13(2, Part A):126–137. Google Scholar
  4. Calvo-Rolle J, Machón-González I, López-García H (2011) Neuro-robust controller for non-linear systems. Dyna 86(3):308–317. Google Scholar
  5. Calvo-Rolle J, Casteleiro-Roca J, Quintián H, Meizoso-Lopez M (2013) A hybrid intelligent system for PID controller using in a steel rolling process. Expert Syst Appl 40(13):5188–5196. Google Scholar
  6. Calvo-Rolle J, Fontenla-Romero Ó, Pérez-Sánchez B, Guijarro-Berdinas B (2014) Adaptive inverse control using an online learning algorithm for neural networks. Informatica 25(3):401–414. Google Scholar
  7. Calvo-Rolle J, Quintian-Pardo H, Corchado E, Meizoso-López M, Ferreiro García R (2015) Simplified method based on an intelligent model to obtain the extinction angle of the current for a single-phase half wave controlled rectifier with resistive and inductive load. J Appl Log 13(1):37–47. Google Scholar
  8. Casteleiro-Roca J, Calvo-Rolle J, Meizoso-López M, Piñón-Pazos A, Rodríguez-Gómez B (2014) New approach for the QCM sensors characterization. Sens Actuators A Phys 207:1–9. Google Scholar
  9. Casteleiro-Roca JL, Calvo-Rolle J, Meizoso-López AMC, Piñón-Pazos Rodríguez-Gómez B (2015a) Bio-inspired model of ground temperature behavior on the horizontal geothermal exchanger of an installation based on a heat pump. Neurocomputing 150:90–98. Google Scholar
  10. Casteleiro-Roca JL, Pérez JAM, Piñón-Pazos AJ, Calvo-Rolle JL, Corchado E (2015b) Modeling the electromyogram (EMG) of patients undergoing anesthesia during surgery. In: 10th International conference on soft computing models in industrial and environmental applications, Springer International Publishing, Cham, pp 273–283.
  11. Casteleiro-Roca J-L, Jove E, Gonzalez-Cava JM, Méndez Pérez JA, Calvo-Rolle JL, Blanco Alvarez F (2018) Hybrid model for the ANI index prediction using remifentanil drug and EMG signal. Neural Comput Appl. Google Scholar
  12. Casteleiro-Roca J-L, Barragán AJ, Segura F, Calvo-Rolle JL, Andújar JM (2019a) Fuel cell output current prediction with a hybrid intelligent system. Complexity. Google Scholar
  13. Casteleiro-Roca J-L, Gómez-González JF, Calvo-Rolle JL, Jove E, Quintián H, Gonzalez Diaz B, Mendez Perez JA (2019b) Short-term energy demand forecast in hotels using hybrid intelligent modeling. Sensors 19(11):2485. Google Scholar
  14. de Cos J, Sanchez F, Ortega F, Montequin V (2008) Rapid cost estimation of metallic components for the aerospace industry. Int J Prod Econ 11(1):470–482. Google Scholar
  15. de Cos FJ, García Nieto P, Martínez Torres J, Taboada Castro J (2010) Analysis of lead times of metallic components in the aerospace industry through a supported vector machine model. Math Comput Model 52(7–8):1177–1184. Google Scholar
  16. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, New YorkzbMATHGoogle Scholar
  17. Cui S, Duan L, Qiao Y, Xiao Y (2018) Learning EEG synchronization patterns for epileptic seizure prediction using bag-of-wave features. J Ambient Intell Humaniz Comput. Google Scholar
  18. Ferreiro García R, Calvo Rolle J, Romero Gomez M, DeMiguel Catoira A (2013) Expert condition monitoring on hydrostatic self-levitating bearings. Expert Syst Appl 40(8):2975–2984. Google Scholar
  19. Ferreiro García R, Calvo-Rolle J, Pérez Castelo J, Romero Gomez M (2014) On the monitoring task of solar thermal fluid transfer systems using NN based models and rule based techniques. Eng Appl Artif Intell 27:129–136. Google Scholar
  20. García Nieto P, Martínez Torres J, de Cos Juez F, Sánchez Lasheras F (2012) Using multivariate adaptive regression splines and multilayer perceptron networks to evaluate paper manufactured using eucalyptus globulus. Appl Math Comput 219(2):755–763. Google Scholar
  21. Ghanghermeh A, Roshan G, Orosa J, Calvo-Rolle J, Costa Á (2013) New climatic indicators for improving urban sprawl: a case study of Tehran city. Entropy 15(3):999–1013. Google Scholar
  22. González Gutiérrez C, Sánchez Rodríguez ML, Fernández Díaz RÁ, Calvo Rolle JL, Roqueñí Gutiérrez N, Javier de Cos Juez F (2018) Rapid tomographic reconstruction through GPU-based adaptive optics. Log J IGPL 27(2):214–226MathSciNetGoogle Scholar
  23. Guo Y, Li X, Bai G, Ma J (2012) Time series prediction method based on LS-SVR with modified Gaussian RBF. In: Neural information processing, pp 9–17.
  24. Heiberger R, Neuwirth E (2009) Polynomial regression. In: R through Excel, use R. Springer, New York, pp 269–284.
  25. Hemmerling T, Arbeid E, Wehbe M, Cyr S, Taddei R, Zaouter C, Reilly C (2013) Evaluation of a novel closed-loop total intravenous anaesthesia drug delivery system: a randomized controlled trial. Br J Anaesth 110(6):1031–1039Google Scholar
  26. Jiang Y, Zhang T, Gou Y, He L, Bai H, Hu C (2018) High-resolution temperature and salinity model analysis using support vector regression. J Ambient Intell Humaniz Comput. Google Scholar
  27. Jove E, Blanco-Rodríguez P, Casteleiro-Roca JL, Moreno-Arboleda J, López-Vázquez JA, de Cos Juez FJ, Calvo-Rolle JL (2018a) Attempts prediction by missing data imputation in engineering degree. In: International joint conference SOCO’17-CISIS’17-ICEUTE’17 León, Spain, September 6–8, 2017, proceeding, Springer International Publishing, Cham, pp 167–176Google Scholar
  28. Jove E, Gonzalez-Cava JM, Casteleiro-Roca J-L, Méndez-Pérez J-A, Antonio Reboso-Morales J, Javier Pérez-Castelo F, de Cos Javier, Juez F, Luis Calvo-Rolle J (2018b) Modelling the hypnotic patient response in general anaesthesia using intelligent models. Log J IGPL 27(2):189–201MathSciNetGoogle Scholar
  29. Jove E, Gonzalez-Cava JM, Casteleiro-Roca JL, Pérez JAM, Calvo-Rolle JL, de Cos Juez FJ (2018c) An intelligent model to predict ANI in patients undergoing general anesthesia. In: International joint conference SOCO’17-CISIS’17-ICEUTE’17 León, Spain, September 6–8, 2017, proceeding, Springer International Publishing, Cham, pp 492–501Google Scholar
  30. Jove E, López JAV, Fernández-Ibáñez I, Casteleiro-Roca JL, Calvo-Rolle JL (2018d) Hybrid intelligent system topredict the individual academic performance of engineering students. Int J Eng Educ 34(3):895–904Google Scholar
  31. Kaski S, Sinkkonen J, Klami A (2005) Discriminative clustering. Neurocomputing 69(1–3):18–41. Google Scholar
  32. Lemaître G, Martí R, Freixenet J, Vilanova JC, Walker PM, Meriaudeau F (2015) Computer-aided detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review. Comput Biol Med 60:8–31. Google Scholar
  33. Machon-Gonzalez I, Lopez-Garcia H, Calvo-Rolle J (2010) A hybrid batch SOM-NG algorithm. In: Neural networks (IJCNN), the 2010 international joint conference on, pp 1–5.
  34. Manuel Vilar-Martinez X, Aurelio Montero-Sousa J, Luis Calvo-Rolle J, Luis Casteleiro-Roca J (2014) Expert system development to assist on the verification of “TACAN” system performance. Dyna 89(1):112–121Google Scholar
  35. Méndez J, Marrero A, Reboso J, León A (2016) Adaptive fuzzy predictive controller for anesthesia delivery. Control Eng Pract 46:1–9Google Scholar
  36. Pérez JAM, Torres S, Reboso JA, Reboso H (2011) Estrategias de control en la práctica de anestesia. Revista Iberoamericana Autom Inf Ind RIAI 8(3):241–249. Google Scholar
  37. Qin A, Suganthan P (2005) Enhanced neural gas network for prototype-based clustering. Pattern Recognit 38(8):1275–1288. Google Scholar
  38. Quintián H, Calvo-Rolle J, Corchado E (2014) A hybrid regression system based on local models for solar energy prediction. Informatica 25(2):265–282Google Scholar
  39. Quintián H, Casteleiro-Roca J-L, Perez-Castelo FJ, Calvo-Rolle JL, Corchado E (2016) Hybrid intelligent model for fault detection of a lithium iron phosphate power cell used in electric vehicles. In: International conference on hybrid artificial intelligence systems, pp 751–762Google Scholar
  40. Quintián-Pardo H, Calvo-Rolle JL, Fontenla-Romero O (2012) Application of a low cost commercial robot in task of tracking of objects. Dyna 175:24–33Google Scholar
  41. Reboso J, Mendez J, Reboso H, León A (2012) Design and implementation of a closed-loop control system for infusion of propofol guided by bispectral index (BIS). Acta Anaesthesiol Scand 56(8):1032–1041Google Scholar
  42. Rynkiewicz J (2012) General bound of overfitting for MLP regression models. Neurocomputing 90:106–110. Google Scholar
  43. Sánchez SS, Vivas AM, Obregón JS, Ortega MR, Jambrina CC, Marco ILT, Jorge EC (2009) Monitorización de la sedación profunda. El monitor BIS. Enfermería Intensiva 20(4):159–166. Google Scholar
  44. Sigl J, Chamoun N (1994) An introduction to bispectral analysis for the electroencephalogram. J Clin Monit 10(6):392–404Google Scholar
  45. Steinwart I, Christmann A (2008) Support vector machines. Springer Publishing Company, Incorporated, New YorkzbMATHGoogle Scholar
  46. Suykens J, Vandewalle J (1999) Least squares support vector machine slassifiers. Neural Process Lett 9(3):293–300. Google Scholar
  47. Vapnik V (1995) The nature of statistical learning theory. Springer, New YorkzbMATHGoogle Scholar
  48. Vega Vega R, Quintián H, Calvo-Rolle JL, Herrero Á, Corchado E (2018) Gaining deep knowledge of android malware families through dimensionality reduction techniques. Log J IGPL 27(2):160–176MathSciNetGoogle Scholar
  49. Vrbaški M, Doroslovački R, Kupusinac A, Stokić E, Ivetić D (2019) Lipid profile prediction based on artificial neural networks. J Ambient Intell Humaniz Comput. Google Scholar
  50. Wang L, Wu J (2012) Neural network ensemble model using PPR and LS-SVR for stock market forecasting. Adv Intell Comput. Google Scholar
  51. Wang R, Wang A, Song Q (2012) Research on the alkalinity of sintering process based on LS-SVM algorithms. Advances in computer science and information engineering. Springer, New York, pp 449–454. Google Scholar
  52. Wasserman P (1993) Advanced methods in neural computing. Wiley, New YorkzbMATHGoogle Scholar
  53. Wu X (2007) Optimal designs for segmented polynomial regression models and web-based implementation of optimal design software. State University of New York, Stony BrookGoogle Scholar
  54. Ye J, Xiong T (2007) SVM versus least squares SVM. J Mach Learn Res 2:644–651 (Proceedings Track) Google Scholar
  55. Zeng Z, Wang J (2010) Advances in neural network research and applications. Springer Publishing Company, Incorporated, New YorkGoogle Scholar
  56. Zhang Z, Chan S (2011) On kernel selection of multivariate local polynomial modelling and its application to image smoothing and reconstruction. J Signal Process Syst 64(3):361–374. Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • José-Luis Casteleiro-Roca
    • 1
  • Marco Gomes
    • 2
  • Juan Albino Méndez-Pérez
    • 3
  • Héctor Alaiz-Moretón
    • 4
    Email author
  • María del Carmen Meizoso-López
    • 1
  • Benigno Antonio Rodríguez-Gómez
    • 1
  • José Luis Calvo-Rolle
    • 1
  1. 1.Dpto. de Ingeniería IndustrialUniversity of A CoruñaA CoruñaSpain
  2. 2.ALGORITMI CentreUniversity of MinhoBragaPortugal
  3. 3.Dpto. de Ingeniería de Sistemas y Automática y Arquitectura y Tecnología de ComputadoresUniversity of La LagunaSan Cristóbal de La Laguna Spain
  4. 4.Dpto. de Ingeniería Eléctrica y de Sistemas y AutomáticaUniversity of LeónLeónSpain

Personalised recommendations