2 results about "Sympathetic nerve activity" patented technology

This invention provides a multi-dimensional monitoring and assessment method for sleep disorders at high altitudes, comprising: S1, concurrently collecting respiratory signals, blood oxygen saturation and pulse wave (PPG), heart rate / ECG, body movement and position, and environmental parameters such as altitude / air pressure and temperature and humidity during nighttime sleep; S3, performing sleep / wake discrimination and detecting apnea, hypoventilation, and blood oxygen desaturation events based on structured data, and statistically analyzing event metrics; S4, calculating the frequency domain characteristics of heart rate variability (HRV) from RR interval sequences to obtain a sympathetic nerve activity proxy index; S5, weightedly fusing the event metrics, oxygenation metrics, and sympathetic proxy into a comprehensive score R and performing hierarchical interpretation; S6, fitting an individualized risk trajectory model to the cross-night scoring sequence and outputting short-term predictions. This method enables the construction of individualized adaptation trajectories and short-term prediction models in a real-world high-altitude environment, shifting from "static results" to "process evaluation."

The application relates to the technical field of signal analysis, in particular to an acute pain evaluation method and system based on EDA signals, which comprises the following steps: collecting electrodermal activity (EDA) signals of a subject; calculating an individual time-varying sympathetic nerve activity (TVSymp) curve; constructing a priori knowledge base containing a standardized pain response sympathetic nerve (SPainSymp) template; inputting the EDA signals and the individual TVSymp curve into a PCVAE model, fusing features and decoupling into pain common features and individual specific features; performing pain intensity classification, and reconstructing a standardized SPainSymp curve by removing individual specific features; and outputting the pain intensity classification result and the dynamic change trend of the standardized SPainSymp curve in real time. The method can effectively decouple and separate the physiological response induced by pain from the individual baseline variation from the mixed EDA signals, and is not interfered by individual differences, and has the characteristics of high accuracy and strong real-time performance.