Home Automated classification of stages of anaesthesia by populations of evolutionary optimized fuzzy rules
Article Open Access

Automated classification of stages of anaesthesia by populations of evolutionary optimized fuzzy rules

  • C. Walther EMAIL logo , A. Wenzel , M. Schneider , M. Trommer , K.-P. Sturm and U. Jaeger
Published/Copyright: September 12, 2015

Abstract

The detection of stages of anaesthesia is mainly performed on evaluating the vital signs of the patient. In addition the frontal one-channel electroencephalogram can be evaluated to increase the correct detection of stages of anaesthesia. As a classification model fuzzy rules are used. These rules are able to classify the stages of anaesthesia automatically and were optimized by multiobjective evolutionary algorithms. As a result the performance of the generated population of fuzzy rule sets is presented. A concept of the construction of an autonomic embedded system is introduced. This system should use the generated rules to classify the stages of anaesthesia using the frontal one-channel electroencephalogram only.

1 Introduction

The detection of stages of anaesthesia is performed by using vital signs like heart rate, blood-pressure or oxygen saturation for example. The anaesthetist is reacting to the values of these signs to de- or increase the concentration of the narcotic drugs to control the stage of anaesthesia of the patient. But the regular used vital signs are not indicating the depth of consciousness directly. In addition the patterns of the electroencephalogram (EEG) indicate the stages of anaesthesia while performing a surgical operation [14]. By assessing these EEG patterns the anaesthetist is getting a meaningful value to estimate the state of the patient. The structure of the electroencephalographic patterns differs throughout the different stages of anaesthesia. So to react to the patterns of EEG directly could be a heavy task for the anaesthetist. A simple EEG-based value is needed to add a robust indicator for classification of stages of anaesthesia. Therefore an automatic approach of a classification-algorithm could be implemented into an embedded system. This system reacts only to the variation of the frontal one-channel pattern of EEG and is indicating three stages of anaesthesia: “Wake”, “Anaesthesia” and “Asphyxia”.

2 Methods

To establish an autonomic device which is able to classify the different stages of anaesthesia the design of a classifier system is necessary in a first step. The training of the classification model should be established before implementing this classification model to an embedded system or microcontroller-based system. So the training itself has to be performed on a standalone computer or computer grid. In a second step the hardware itself has to be constructed. This hardware will capture the frontal one-channel EEG and processes a feature extraction. These features are than presented to the implemented classification approach. At least the classification system will calculate the different stages of anaesthesia and present it to the anaesthetist in a simple way.

2.1 Design of the classification model

The overall database is defined by datasets of the frontal one-channel EEG collected from different patients and chirurgical operations. The training data set is defined by 18 records collected throughout different surgical operations. The validation data set includes 20 additional independent records. In a first step features were extracted and used to train different classification approaches. To enable a linguistic interpretation of the classification system fuzzy rules were selected to evaluate the extracted features sets. By the means of multiobjective evolutionary algorithms simple fuzzy rules were generated [5]. These rules are able to distinguish between the three anaesthetic stages “Wake”, “Anaesthesia” and “Asphyxia”. The number of rules is limited to five rules for each class. To enhance the robustness of the classification system there were populations of rule sets generated. These populations include up to 18 independent rule sets. The population itself was established by the applied training algorithm [4]. The constructed classification system has a very simple structure connected to an appropriate value of robustness. A linguistic interpretation of the rule sets is possible. So there were generated efficient classifiers to support the anaesthetist in defining the actual anaesthetic stage of the patient. In addition by using fuzzy rules a linguistic interpretation could be performed to estimate the importance of the extracted EEG features.

2.2 Construction of the embedded system

An embedded system should be used to analyse the frontal one-channel EEG in an autonomic way. The construction of this device has to be transposed in a simple and efficient way. The generated population of fuzzy rules should be implemented to work as an essential part of the firmware. Therefore some hardware system approaches were presented in [69].

3 Results

Populations of fuzzy rule sets were generated by applying the algorithms presented in [4]. In a first step the selection of the linguistic variables and the corresponding rule structure for each fuzzy rule set was optimized. Therefore different Multiobjective Evolutionary Algorithms (MOEA) were used [4]. The Non-dominated Sorting Genetic Algorithm II (NSGAII) presented in [10], the Strength-Pareto Evolutionary Algorithm 2 (SPEA2) and the Indicator-based Evolutionary Algorithm (IBEA) [11, 12] generated populations of fuzzy rule sets. In a second step the number of fuzzy rule sets was reduced by using a genetic algorithm applied for each population. As presented in [4] for each MOEA-specific population a subset of fuzzy rule sets was extracted. The genetic algorithm determined for the NSGAII-optimized population 3 fuzzy rule sets as an optimal classification model. Out of the SPEA2-optimized population also 3 fuzzy sets were specified. The IBEA-optimized population provides 5 fuzzy rule sets after applying the genetic selection algorithm.

In Addition to the results presented in [4] these 11 different fuzzy sets can be used to classify the stages of anaesthesia in common. To raise the efficiency the genetic selection algorithm can be applied to this new population of fuzzy rule sets. The generation count was limited to 500. As a main result of this selection procedure 7 fuzzy rule sets were found to classify the stages of anaesthesia of 20 independent features sets of validation data. The classifi-cation performance of these fuzzy rule sets is presented in table 1.

Table 1

Median performance of the optimized fuzzy rule sets in comparison to the manual classification.

Given ClassificationAutomatic Classification
WakeAnaesthesiaAsphyxia
Wake78.42%8.99%12.22%
Anaesthesia0.34%86.77%12.94%
Asphyxia0.00%12.63%85.65%

The results presented in table 1 illustrate the median values of the decision vectors generated for each cell of 20 performance matrices. The matrices itself correspond to the classification output of each fuzzy set of the produced population. Each line of the table matches the manual rated classification of the experts. Each column represents the median degree of concordance in percentage between the manual rated epochs of EEG and the results received by the population of fuzzy rule sets. The anaesthetic stages “Wake”, “Anaesthesia” and “Asphyxia” indicate an accordance of 78.42%, 86.77% and 85.65%. The given anaesthetic stage “Asphyxia” was not classified as “Wake” by the automatic approach as presented in table 1.

4 Conclusion

By applying the general training algorithm as presented in [4] populations of optimized fuzzy sets were generated. These fuzzy rules are able to classify stages of anaesthesia by evaluating the frontal one-channel electroencephalogram. The fuzzy rules were optimized using the multiobjective evolutionary algorithms NSGAII, SPEA2 and IBEA. For each MOEA an independent population of fuzzy sets was generated. The size of each population was reduced by a genetic algorithm. The remaining fuzzy sets of each population were used to create a new population of effi-cient fuzzy rules. To reduce the computation effort in an additional way the genetic search algorithm was applied again to this new population. The number of fuzzy sets was reduced from 11 to 7. In relation to the results as presented in [4] the performance was raised lightly by using this new reduced fuzzy rule set to classify the validation data set. In a next step this new population of fuzzy rule sets has to be implemented into an embedded system to enable an online classification of anaesthetic stages.

Author's Statement

  1. Conflict of interest: Authors state no conflict of interest. Material and Methods: Informed consent: Informed consent has been obtained from all individuals included in this study. Ethical approval: The research related to human use has been complied with all the relevant national regulations, institutional policies and in accordance the tenets of the Helsinki Declaration, and has been approved by the authors’ institutional review board or equivalent committee.

References

[1] Courtin, R. F.; Bickford, R. G.; Faulconer Jr., A.: The Classification And Significance of Electro-Encephalographic Patterns Produced by Nitrous Oxide-Ether Anesthesia During Surgical Operations, Proceedings of the Staff Meeting Mayo Clin 25, No. 8, pp. 197-206, 1950Search in Google Scholar

[2] Wenzel, A. : Robuste Klassifikation von EEG-Daten durch Neuronale Netze - Untersuchungen am Beispiel der einkanaligen automatischen Schlafstadien- und Narkosetiefenbestimmung, Shaker Verlag Aachen, 2005Search in Google Scholar

[3] Baumgart-Schmitt, R.; Walther C.; Wenzel, A.: Multi criteria evaluation of sleep and anesthesia by neural networks, fuzzy rules, evolutionary algorithms and support vector machines, IFMBE Proceedings, Vol. 25, No. 4, pp. 2254-2255, 200910.1007/978-3-642-03882-2_598Search in Google Scholar

[4] Walther, C.: Multikriteriell evolutionär optimierte Anpassung von unscharfen Modellen zur Klassifikation und Vorhersage auf der Basis hirnelektrischer Narkose-Potentiale, Shaker Verlag Aachen, 2012Search in Google Scholar

[5] Walther, C.; Baumgart-Schmitt, R.; Menz, C.; Trommer, D.; Krautwald, M.; Sturm, K.-P.; Jäger, U.: Multi-criteria Model-driven Feature Selection Using Fuzzy Ruled Classification Of Stages Of Anaesthesia, Proceedings of the 55th International Scientific Colloquium, Ilmenau, Germany, pp. 519-522, 2010Search in Google Scholar

[6] Fraenzel, N.; Weichert, F.; Wenzel, A.; Ament, C.: A prototyping system for smart wheelchairs, Biomedizinische Technik, Vol. 59, pp. 902-905, 2014Search in Google Scholar

[7] Faenger, B.; Becker, F.; Brandl, M.; Fränzel, N.; Holder, S.; Köhring, S.; Lutherdt, S.; Michaelis, A.; Weichert, F.; Schumann, N. P.; Scholle, H. C.; Zimmermann, K.; Augsburg, K.; Ament, C.; Linß, G.; Witte, H.; Pezoldt, K.; Wenzel, A.: Mobil-itätssysteme für Best Ager (50plus): Neue Präventionsansätze. In: Dienstbühl, I.; Scholle, H. C.; Stadeler, M.: Prävention von arbeitsbedingten Gesundheitsgefahren und Erkrankungen: 20. Erfurter Tage, pp. 363-367, 2014Search in Google Scholar

[8] Menz, C.: Entwicklung einer Softwarebasis zur Echtzeitanalyse von EEG-Daten auf einer Mikrocontrollerplattform, Project Report, University of Applied Sciences Schmalkalden, Germany, 2010Search in Google Scholar

[9] Hess T.; Hopf, M.: Entwicklung eines mikrocontrollerbasierten Systems zur Signalextraktion, Verarbeitung und echzeitfähigen Klassifikation von biometrischen Signalen, Project Report, University of Applied Sciences Schmalkalden, Germany, 2011Search in Google Scholar

[10] Deb, K.; Pratap, A.; Agarwal, S.; Meyarivan, T.: A Fast Elitist Multi-Objective Genetic Algorithm: NSGA-II, IEEE Transactions on Evolutionary Computation 6, pp. 182-197, 200010.1109/4235.996017Search in Google Scholar

[11] Zitzler, E.; Laumanns, M.; Thiele, L.: SPEA2: Improving the Strength Pareto Evolutionary Algorithm, Research Report, Swiss Federal Institute of Technology (ETH) Zurich, 2001Search in Google Scholar

[12] Zitzler, E.; Künzli, S.: Indicator-based Selection in Multiobjective Search, Proceedings of the 8th International Conference on Parallel Problem Solving from Nature (PPSN VIII), Springer, pp. 832-842, 200410.1007/978-3-540-30217-9_84Search in Google Scholar

Published Online: 2015-9-12
Published in Print: 2015-9-1

© 2015 by Walter de Gruyter GmbH, Berlin/Boston

This article is distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Articles in the same Issue

  1. Research Article
  2. Development and characterization of superparamagnetic coatings
  3. Research Article
  4. The development of an experimental setup to measure acousto-electric interaction signal
  5. Research Article
  6. Stability analysis of ferrofluids
  7. Research Article
  8. Investigation of endothelial growth using a sensors-integrated microfluidic system to simulate physiological barriers
  9. Research Article
  10. Energy harvesting for active implants: powering a ruminal pH-monitoring system
  11. Research Article
  12. New type of fluxgate magnetometer for the heart’s magnetic fields detection
  13. Research Article
  14. Field mapping of ballistic pressure pulse sources
  15. Research Article
  16. Development of a new homecare sleep monitor using body sounds and motion tracking
  17. Research Article
  18. Noise properties of textile, capacitive EEG electrodes
  19. Research Article
  20. Detecting phase singularities and rotor center trajectories based on the Hilbert transform of intraatrial electrograms in an atrial voxel model
  21. Research Article
  22. Spike sorting: the overlapping spikes challenge
  23. Research Article
  24. Separating the effect of respiration from the heart rate variability for cases of constant harmonic breathing
  25. Research Article
  26. Locating regions of arrhythmogenic substrate by analyzing the duration of triggered atrial activities
  27. Research Article
  28. Combining different ECG derived respiration tracking methods to create an optimal reconstruction of the breathing pattern
  29. Research Article
  30. Atrial and ventricular signal averaging electrocardiography in pacemaker and cardiac resynchronization therapy
  31. Research Article
  32. Estimation of a respiratory signal from a single-lead ECG using the 4th order central moments
  33. Research Article
  34. Compressed sensing of multi-lead ECG signals by compressive multiplexing
  35. Research Article
  36. Heart rate monitoring in ultra-high-field MRI using frequency information obtained from video signals of the human skin compared to electrocardiography and pulse oximetry
  37. Research Article
  38. Synchronization in wireless biomedical-sensor networks with Bluetooth Low Energy
  39. Research Article
  40. Automated classification of stages of anaesthesia by populations of evolutionary optimized fuzzy rules
  41. Research Article
  42. Effects of sampling rate on automated fatigue recognition in surface EMG signals
  43. Research Article
  44. Closed-loop transcranial alternating current stimulation of slow oscillations
  45. Research Article
  46. Cardiac index in atrio- and interventricular delay optimized cardiac resynchronization therapy and cardiac contractility modulation
  47. Research Article
  48. The role of expert evaluation for microsleep detection
  49. Research Article
  50. The impact of baseline wander removal techniques on the ST segment in simulated ischemic 12-lead ECGs
  51. Research Article
  52. Metal artifact reduction by projection replacements and non-local prior image integration
  53. Research Article
  54. A novel coaxial nozzle for in-process adjustment of electrospun scaffolds’ fiber diameter
  55. Research Article
  56. Processing of membranes for oxygenation using the Bellhouse-effect
  57. Research Article
  58. Inkjet printing of viable human dental follicle stem cells
  59. Research Article
  60. The use of an icebindingprotein out of the snowflea Hypogastrura harveyi as a cryoprotectant in the cryopreservation of mesenchymal stem cells
  61. Research Article
  62. New NIR spectroscopy based method to determine ischemia in vivo in liver – a first study on rats
  63. Research Article
  64. QRS and QT ventricular conduction times and permanent pacemaker therapy after transcatheter aortic valve implantation
  65. Research Article
  66. Adopting oculopressure tonometry as a transient in vivo rabbit glaucoma model
  67. Research Article
  68. Next-generation vision testing: the quick CSF
  69. Research Article
  70. Improving tactile sensation in laparoscopic surgery by overcoming size restrictions
  71. Research Article
  72. Design and control of a 3-DOF hydraulic driven surgical instrument
  73. Research Article
  74. Evaluation of endourological tools to improve the diagnosis and therapy of ureteral tumors – from model development to clinical application
  75. Research Article
  76. Frequency based assessment of surgical activities
  77. Research Article
  78. “Hands free for intervention”, a new approach for transoral endoscopic surgery
  79. Research Article
  80. Pseudo-haptic feedback in medical teleoperation
  81. Research Article
  82. Feasibility of interactive gesture control of a robotic microscope
  83. Research Article
  84. Towards structuring contextual information for workflow-driven surgical assistance functionalities
  85. Research Article
  86. Towards a framework for standardized semantic workflow modeling and management in the surgical domain
  87. Research Article
  88. Closed-loop approach for situation awareness of medical devices and operating room infrastructure
  89. Research Article
  90. Kinect based physiotherapy system for home use
  91. Research Article
  92. Evaluating the microsoft kinect skeleton joint tracking as a tool for home-based physiotherapy
  93. Research Article
  94. Integrating multimodal information for intraoperative assistance in neurosurgery
  95. Research Article
  96. Respiratory motion tracking using Microsoft’s Kinect v2 camera
  97. Research Article
  98. Using smart glasses for ultrasound diagnostics
  99. Research Article
  100. Measurement of needle susceptibility artifacts in magnetic resonance images
  101. Research Article
  102. Dimensionality reduction of medical image descriptors for multimodal image registration
  103. Research Article
  104. Experimental evaluation of different weighting schemes in magnetic particle imaging reconstruction
  105. Research Article
  106. Evaluation of CT capability for the detection of thin bone structures
  107. Research Article
  108. Towards contactless optical coherence elastography with acoustic tissue excitation
  109. Research Article
  110. Development and implementation of algorithms for automatic and robust measurement of the 2D:4D digit ratio using image data
  111. Research Article
  112. Automated high-throughput analysis of B cell spreading on immobilized antibodies with whole slide imaging
  113. Research Article
  114. Tissue segmentation from head MRI: a ground truth validation for feature-enhanced tracking
  115. Research Article
  116. Video tracking of swimming rodents on a reflective water surface
  117. Research Article
  118. MR imaging of model drug distribution in simulated vitreous
  119. Research Article
  120. Studying the extracellular contribution to the double wave vector diffusion-weighted signal
  121. Research Article
  122. Artifacts in field free line magnetic particle imaging in the presence of inhomogeneous and nonlinear magnetic fields
  123. Research Article
  124. Introducing a frequency-tunable magnetic particle spectrometer
  125. Research Article
  126. Imaging of aortic valve dynamics in 4D OCT
  127. Research Article
  128. Intravascular optical coherence tomography (OCT) as an additional tool for the assessment of stent structures
  129. Research Article
  130. Simple concept for a wide-field lensless digital holographic microscope using a laser diode
  131. Research Article
  132. Intraoperative identification of somato-sensory brain areas using optical imaging and standard RGB camera equipment – a feasibility study
  133. Research Article
  134. Respiratory surface motion measurement by Microsoft Kinect
  135. Research Article
  136. Improving image quality in EIT imaging by measurement of thorax excursion
  137. Research Article
  138. A clustering based dual model framework for EIT imaging: first experimental results
  139. Research Article
  140. Three-dimensional anisotropic regularization for limited angle tomography
  141. Research Article
  142. GPU-based real-time generation of large ultrasound volumes from freehand 3D sweeps
  143. Research Article
  144. Experimental computer tomograph
  145. Research Article
  146. US-tracked steered FUS in a respiratory ex vivo ovine liver phantom
  147. Research Article
  148. Contribution of brownian rotation and particle assembly polarisation to the particle response in magnetic particle spectrometry
  149. Research Article
  150. Preliminary investigations of magnetic modulated nanoparticles for microwave breast cancer detection
  151. Research Article
  152. Construction of a device for magnetic separation of superparamagnetic iron oxide nanoparticles
  153. Research Article
  154. An IHE-conform telecooperation platform supporting the treatment of dementia patients
  155. Research Article
  156. Automated respiratory therapy system based on the ARDSNet protocol with systemic perfusion control
  157. Research Article
  158. Identification of surgical instruments using UHF-RFID technology
  159. Research Article
  160. A generic concept for the development of model-guided clinical decision support systems
  161. Research Article
  162. Evaluation of local alterations in femoral bone mineral density measured via quantitative CT
  163. Research Article
  164. Creating 3D gelatin phantoms for experimental evaluation in biomedicine
  165. Research Article
  166. Influence of short-term fixation with mixed formalin or ethanol solution on the mechanical properties of human cortical bone
  167. Research Article
  168. Analysis of the release kinetics of surface-bound proteins via laser-induced fluorescence
  169. Research Article
  170. Tomographic particle image velocimetry of a water-jet for low volume harvesting of fat tissue for regenerative medicine
  171. Research Article
  172. Wireless medical sensors – context, robustness and safety
  173. Research Article
  174. Sequences for real-time magnetic particle imaging
  175. Research Article
  176. Speckle-based off-axis holographic detection for non-contact photoacoustic tomography
  177. Research Article
  178. A machine learning approach for planning valve-sparing aortic root reconstruction
  179. Research Article
  180. An in-ear pulse wave velocity measurement system using heart sounds as time reference
  181. Research Article
  182. Measuring different oxygenation levels in a blood perfusion model simulating the human head using NIRS
  183. Research Article
  184. Multisegmental fusion of the lumbar spine a curse or a blessing?
  185. Research Article
  186. Numerical analysis of the biomechanical complications accompanying the total hip replacement with NANOS-Prosthetic: bone remodelling and prosthesis migration
  187. Research Article
  188. A muscle model for hybrid muscle activation
  189. Research Article
  190. Mathematical, numerical and in-vitro investigation of cooling performance of an intra-carotid catheter for selective brain hypothermia
  191. Research Article
  192. An ideally parameterized unscented Kalman filter for the inverse problem of electrocardiography
  193. Research Article
  194. Interactive visualization of cardiac anatomy and atrial excitation for medical diagnosis and research
  195. Research Article
  196. Virtualizing clinical cases of atrial flutter in a fast marching simulation including conduction velocity and ablation scars
  197. Research Article
  198. Mesh structure-independent modeling of patient-specific atrial fiber orientation
  199. Research Article
  200. Accelerating mono-domain cardiac electrophysiology simulations using OpenCL
  201. Research Article
  202. Understanding the cellular mode of action of vernakalant using a computational model: answers and new questions
  203. Research Article
  204. A java based simulator with user interface to simulate ventilated patients
  205. Research Article
  206. Evaluation of an algorithm to choose between competing models of respiratory mechanics
  207. Research Article
  208. Numerical simulation of low-pulsation gerotor pumps for use in the pharmaceutical industry and in biomedicine
  209. Research Article
  210. Numerical and experimental flow analysis in centifluidic systems for rapid allergy screening tests
  211. Research Article
  212. Biomechanical parameter determination of scaffold-free cartilage constructs (SFCCs) with the hyperelastic material models Yeoh, Ogden and Demiray
  213. Research Article
  214. FPGA controlled artificial vascular system
  215. Research Article
  216. Simulation based investigation of source-detector configurations for non-invasive fetal pulse oximetry
  217. Research Article
  218. Test setup for characterizing the efficacy of embolic protection devices
  219. Research Article
  220. Impact of electrode geometry on force generation during functional electrical stimulation
  221. Research Article
  222. 3D-based visual physical activity assessment of children
  223. Research Article
  224. Realtime assessment of foot orientation by Accelerometers and Gyroscopes
  225. Research Article
  226. Image based reconstruction for cystoscopy
  227. Research Article
  228. Image guided surgery innovation with graduate students - a new lecture format
  229. Research Article
  230. Multichannel FES parameterization for controlling foot motion in paretic gait
  231. Research Article
  232. Smartphone supported upper limb prosthesis
  233. Research Article
  234. Use of quantitative tremor evaluation to enhance target selection during deep brain stimulation surgery for essential tremor
  235. Research Article
  236. Evaluation of adhesion promoters for Parylene C on gold metallization
  237. Research Article
  238. The influence of metallic ions from CoCr28Mo6 on the osteogenic differentiation and cytokine release of human osteoblasts
  239. Research Article
  240. Increasing the visibility of thin NITINOL vascular implants
  241. Research Article
  242. Possible reasons for early artificial bone failure in biomechanical tests of ankle arthrodesis systems
  243. Research Article
  244. Development of a bending test procedure for the characterization of flexible ECoG electrode arrays
  245. Research Article
  246. Tubular manipulators: a new concept for intracochlear positioning of an auditory prosthesis
  247. Research Article
  248. Investigation of the dynamic diameter deformation of vascular stents during fatigue testing with radial loading
  249. Research Article
  250. Electrospun vascular grafts with anti-kinking properties
  251. Research Article
  252. Integration of temperature sensors in polyimide-based thin-film electrode arrays
  253. Research Article
  254. Use cases and usability challenges for head-mounted displays in healthcare
  255. Research Article
  256. Device- and service profiles for integrated or systems based on open standards
  257. Research Article
  258. Risk management for medical devices in research projects
  259. Research Article
  260. Simulation of varying femoral attachment sites of medial patellofemoral ligament using a musculoskeletal multi-body model
  261. Research Article
  262. Does enhancing consciousness for strategic planning processes support the effectiveness of problem-based learning concepts in biomedical education?
  263. Research Article
  264. SPIO processing in macrophages for MPI: The breast cancer MPI-SNLB-concept
  265. Research Article
  266. Numerical simulations of airflow in the human pharynx of OSAHS patients
Downloaded on 18.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/cdbme-2015-0020/html
Scroll to top button