Objective identification of pain due to uterine contraction during the first stage of labour using continuous EEG signals and SVM

Abstract

This study aimed to assess the utility of electroencephalography (EEG) as an objective marker of pain during the first stage of labour. EEG and cardiotocography (CTG) data were obtained from 10 parturient women during their first stage of labour. The study subjects reported the extent of their pain experienced due to uterine contractions, which were recorded by the CTG tracing. Simultaneous 16-channel EEG traces were obtained for spectral analysis and a subsequent machine learning classification using Support Vector Machine (SVM) aiming to predict the pain experienced in relation to uterine contractions. It was found that pain due to uterine contraction correlated positively with relative delta and beta band activities and negatively with relative theta and alpha band activities of the EEG signals. SVM using the spectral activities, statistical and non-linear features of the EEG classified the state of pain with 83% accuracy using a classification model generalizable across subjects. Furthermore, dimension reduction using Principal Component Analysis (PCA) successfully reduced the number of features used in the classification while achieving a maximum classification accuracy of 84%. Continuous EEG affords the means to assess objectively maternal pain experienced during the active contraction phase of the first stage of labour. Monitoring of the pain experience using EEG signals may complement the clinical decision-making process behind administration of epidural anaesthesia during labour. We envision future studies to investigate EEG markers of pain in other clinical states, aiming to generalize the use of EEG as an objective method of pain assessment.

Sensor Technologies to Manage the Physiological Traits of Chronic Pain: A Review

“…The electrical biopotentials generated by the human body are signals commonly used in medical diagnosis. The main biopotentials are electrocardiagram (ECG) [82,85], electromyogram (EMG) [11,35,43,215] and electroencephalogram (EEG) [46,50,[216][217][218][219]. Biopotential sensors are usually composed of the following elements: electrodes, used for the transduction of the ionic signals inside the body to electrical signals; an analog conditioning stage for the amplification of the electrical signal, of very low intensity, at measurable levels avoiding electromagnetic interference (EMI); and an analog-digital conversion stage.…”

“…EEG has numerous practical advantages, since it is a non-invasive technique, with high temporal resolution, provides relevant clinical information, is low-cost and requires little maintenance [50]. EEG studies have shown the activation of specific regions of the brain as a result of pain stimuli [216,217].…”

“…Frequency domain analysis, either by fast Fourier transform (FFT), regression models (RM) or wavelet transform (WT) [46], has been employed to study the experience of pain by dynamic analysis of the power in frequency bands [216,218]. Some studies have highlighted the influence of pain in certain frequency bands of the EEG signal, especially in the alpha [50,219] and the gamma [50,232] bands.…”

“…Amplitude changes in the alpha frequency band (8-13 Hz) measured at standardized bilateral temporal scalp electrodes (T7 and T8) are associated with tonic pain [216,233]. Power increases in the gamma band (30-100 Hz) have also been related to pain stimuli [216,218].…”

“…Amplitude changes in the alpha frequency band (8-13 Hz) measured at standardized bilateral temporal scalp electrodes (T7 and T8) are associated with tonic pain [216,233]. Power increases in the gamma band (30-100 Hz) have also been related to pain stimuli [216,218]. Since the gamma band is susceptible to higher frequency noise related to EMG signals of facial muscles and artifacts derived from oculomotor activities, adequate signal filtering must be performed [216,234].…”