Closed-Loop Spinal Neuromodulation With ECAP Artifact Removal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing spinal cord stimulation (SCS) systems face issues with noisy or improperly classified control signals, leading to inadequate treatment of pain and function restoration after spinal cord injuries due to misidentification of non-ECAP signals as ECAPs and the presence of stimulation artifacts in ECAPs.
Innovation Solution
A neurostimulation system with electrodes, a waveform generator, and computing devices that accurately classify ECAPs from non-ECAPs and outliers, and remove stimulation artifacts using a machine learning model and a novel SAND method to enhance closed-loop neuromodulation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional neural signal classification methods are used, then the system is simpler to implement, but the accuracy of ECAP identification deteriorates due to misclassification of non-ECAP signals
Solution Approach 1:
The patent segments the neural signal analysis into distinct stages: raw signal acquisition, artifact removal using SAND method, feature extraction, and classification using machine learning models. This segmentation allows each stage to be optimized independently, improving overall ECAP identification accuracy while managing system complexity through modular processing steps.
Solution Approach 2:
The patent introduces intermediary processing steps between signal acquisition and classification, specifically the SAND artifact removal method and feature extraction stage. These intermediaries prepare the raw neural signals by removing stimulation artifacts and extracting relevant features, thereby improving the input quality for the classification algorithm and enhancing ECAP identification accuracy.
2Reliability
If stimulation artifacts are not removed, then the processing pipeline is shorter, but the reliability of control signals deteriorates due to contaminated ECAP measurements
Solution Approach 1:
The patent applies the extraction principle by removing stimulation artifacts from neural signals using the SAND method. This separation of the desired ECAP signal from unwanted stimulation artifacts ensures that only clean, reliable neural responses are used for closed-loop control, directly improving control signal reliability while maintaining manageable processing complexity through efficient artifact removal algorithms.
3Measurement precision
If machine learning models are used for classification, then the accuracy of neural signal identification improves, but the computational requirements and processing time increase
Solution Approach 1:
The patent performs preliminary actions by removing stimulation artifacts and extracting relevant features before feeding signals to machine learning classification models. This preprocessing reduces the complexity of the classification task and improves model efficiency, thereby reducing processing time while maintaining high classification accuracy for ECAP identification.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Improves the accuracy of spinal cord stimulation by ensuring that only clean ECAPs are used as control signals, thereby providing more effective pain management and functional restoration.
Implementation Method 1
cause the waveform generator to electrically excite the plurality of stimulation electrodes
Implementation Method 2
receive, from the plurality of recording electrodes, a neural signal; determine that the neural signal is an electrically evoked compound action potential ('ECAP')
Data Source
AI summary
A neurostimulation system includes a plurality of stimulation electrodes, a plurality of recording electrodes, a waveform generator in electrical communication with the plurality of stimulation electrodes, and one or more computing devices in electrical communication with the plurality of recording electrodes and the waveform generator. The one or more computing devices cause the waveform generator to electrically excite the plurality of stimulation electrodes of the plurality of stimulation electrodes. After electrically exciting the stimulation electrodes, a neural signal is received from the plurality of recording electrodes. The neural signal is determined to be an electrically evoked compound action potential (“ECAP”) by determining one or more features of the neural signal. One or more stimulation parameters are determined based on one or more characteristics of the ECAP. The waveform generator is then caused to electrically excite the plurality of stimulation electrodes according to the one or more stimulation parameters.