Evaluation of Acute Tonic Cold Pain From Microwave Transcranial Transmission Signals Using Multi-Entropy Machine Learning Approach

This study aims to improve the accuracy of detecting acute tonic cold pain (CP) perception from microwave transcranial transmission (MTT) signals. Two different types of CP and no-pain (NP) MTT signals are obtained from 15 subjects. Four features, namely, power spectral exponential entropy, improved multiscale permutation entropy, refined composite multiscale dispersion entropy, and refined composite multiscale fuzzy entropy, are extracted in the variational modal decomposition domain. The feature datasets are divided into training datasets and test datasets in a 3:1 ratio. Random forest (RF) and support vector machine (SVM) are selected as classifiers. The training datasets are imported into the classifier, and the optimal training dataset is obtained with a 10-fold cross validation strategy. The feature dimension reduction algorithm of the principal component analysis is used to reduce the complexity of the feature datasets and select the most recognizable features. The classification performance of the test datasets is evaluated by the optimal classifiers. Results showed that the RF classifier performs better than the SVM classifier. The RF classifier provides high values of specificity (91.67%), sensitivity (95.83%), positive predictive value (92.00%), accuracy (93.75%), and area under curve (0.867). The combination of the microwave detection approach and machine learning algorithm can effectively detect brain activity induced by nociceptive stimulation. This approach is important in improving the accuracy of pain detection.