Identification of moyamoya disease based on cerebral oxygen saturation signals using machine learning methods

Stroke analysis and recognition in functional near-infrared spectroscopy signals using machine learning methods

Stroke is a high-incidence disease with high disability and mortality rates. It is a serious public health problem worldwide. Shortened onset-to-image time is very important for the diagnosis and treatment of stroke. Functional near-infrared spectroscopy (fNIRS) is a noninvasive monitoring tool with real-time, noninvasive, and convenient features. In this study, we propose an automatic classification framework based on cerebral oxygen saturation signals to identify patients with hemorrhagic stroke, patients with ischemic stroke, and normal subjects. The reflected fNIRS signals were used to detect the cerebral oxygen saturation and the relative value of oxygen and deoxyhemoglobin concentrations of the left and right frontal lobes. The wavelet time-frequency analysis-based features from these signals were extracted. Such features were used to analyze the differences in cerebral oxygen saturation signals among different types of stroke patients and healthy humans and were selected to train the machine learning models. Furthermore, an important analysis of the features was performed. The accuracy of the models trained was greater than 85%, and the accuracy of the models after data augmentation was greater than 90%, which is of great significance in distinguishing patients with hemorrhagic stroke or ischemic stroke. This framework has the potential to shorten the onset-to-diagnosis time of stroke.

Study of Motion Sickness Model Based on fNIRS Multiband Features during Car Rides

Motion sickness is a common physiological discomfort phenomenon during car rides. In this paper, the functional near-infrared spectroscopy (fNIRS) technique was used in real-world vehicle testing. The fNIRS technique was utilized to model the relationship between changes in blood oxygenation levels in the prefrontal cortex of passengers and motion sickness symptoms under different motion conditions. To enhance the accuracy of motion sickness classification, the study utilized principal component analysis (PCA) to extract the most significant features from the test data. Wavelet decomposition was used to extract the power spectrum entropy (PSE) features of five frequency bands highly related to motion sickness. The correlation between motion sickness and cerebral blood oxygen levels was modeled by a 6-point scale calibration for the subjective evaluation of the degree of passenger motion sickness. A support vector machine (SVM) was used to build a motion sickness classification model, achieving an accuracy of 87.3% with the 78 sets of data. However, individual analysis of the 13 subjects showed a varying range of accuracy from 50% to 100%, suggesting the presence of individual differences in the relationship between cerebral blood oxygen levels and motion sickness symptoms. Thus, the results demonstrated that the magnitude of motion sickness during the ride was closely related to the change in the PSE of the five frequency bands of cerebral prefrontal blood oxygen, but further studies are needed to investigate individual variability.