The Effectiveness Assessment of Massage Therapy Using Entropy-Based EEG Features Among Lumbar Disc Herniation Patients Comparing With Healthy Controls

Abstract

Massage therapy (MT) is a useful complementary and alternative therapy widely used in treating low back pain (LBP), including lumbar disc herniation (LDH). However, few studies revealed the quantitative entropy-based features of electroencephalography (EEG) for the MT effectiveness for the LDH patients. This study investigated the immediate effects of Chinese massage on four EEG rhythms, using the eight entropy-based features (approximation entropy (ApEn), Sample Entropy (SampEn), wavelet entropy (WaveEn), Hilbert-Huang Transform Marginal spectrum entropy (HHTMSEn), normalized energy, permutation entropy (PE), Fuzzy entropy (FuzzyEn), and Inherent fuzzy entropy (IFE)) in the 26 LDH patients and 24 healthy controls. Results showed that after MT in LDH group, ApEn, SampEn, WaveEn, PE, FuzzyEn, and IFE features of the delta rhythm decreased, the normalized energy of delta rhythm significantly increased in the left hemisphere and theta/alpha rhythms significantly decreased. Furthermore, HHTMSEn feature of theta and beta rhythms showed the significant difference for two groups (LDH and control group) in two states (before and after massage). Ten classifiers were applied in classifying two groups or two states in one group, and most of them reached high averaged accuracies and the area under the curve (AUC), even with different length per epoch (1024, 512, and 256 points). It indicated that the entropy-based features and permutation disalignment index (PDI) of EEG rhythms could be promising indices of the massage effectiveness for LDH patients and control group. Rhythms' SampEn scalp topography in two groups showed the significant different complexity change between two states (before and after massage). INDEX TERMS Massage therapy (MT), electroencephalograpy (EEG), Lumbar disc herniation (LDH), sample entropy (SampEn), Hilbert-Huang transform marginal spectrum entropy (HHTMSEn), wavelet entropy (WaveEn), permutation entropy (PE), fuzzy entropy (FuzzyEn), inherent fuzzy entropy (IFE).

Accurate classification of pain experiences using wearable electroencephalography in adolescents with and without chronic musculoskeletal pain

“…Vatankhah et al found that no-pain and cold thermal pain classification accuracy was 14% higher using approximate entropy vs. spectral features ( 54 ). The superior classification accuracy of entropy-based features aligns with our results, as well as other studies demonstrating changes in PE outcomes in relation to pain ( 60 , 61 ). Our study also aligns with prior CPT studies reporting changes in theta activity in relation to pain stimulation ( 27 , 28 , 30 ).…”

Medical Data Analysis of Lumbar Disc Herniation Patients after Traditional Chinese Medicine Rehabilitation Intervention Lumbar Function Recovery

“…With the development of economy, the progress of society and the change of people's life and work style, the age of onset of the disease is becoming younger and younger [ 6 ]. Li et al believe that due to its long course and easy repetition, it seriously affects the daily life and work of LDH patients, brings huge pain and certain economic burden to patients, and also causes psychological and mental pressure to patients [ 7 ]. Hu et al found that the basic pathological factor of LDH is the imbalance between inorganic and organic components in the intervertebral disc, and the acute and chronic injury of the waist, the increase of intervertebral disc pressure caused by long-term fixed sitting posture, lumbar puncture, genetics, age, etc.…”

Research on Feature Extraction of Ship-Radiated Noise Based on Multiscale Fuzzy Dispersion Entropy

“…Entropy is a nonlinear dynamical index [17,18] that has been widely used in recent years for various applications including ship-radiated noise feature extraction, by virtue of its ability to provide a measure of the uncertainty and irregularity of nonlinear signals [19][20][21][22][23][24], and many scholars have improved entropy in various aspects in order to improve its performance. In 2002, Bandt and Pompe [25] proposed the concept of permutation entropy (PE) for describing the complexity of time series and chaotic dynamical systems, which is also widely used in various types of hydroacoustic signal feature extraction due to its simpler algorithm, faster computation, and better noise immunity.…”