Closed-Loop Spinal Cord Stimulation Using Electrospinogram Artifact Prediction
Solution Overview
Problem
Current implantable neurostimulator devices, such as Spinal Cord Stimulation (SCS) systems, face challenges in effectively adjusting stimulation parameters to optimize neural responses without causing patient perception, as traditional methods rely on detectable Evoked Compound Action Potentials (ECAPs) which may not be present at sub-perception thresholds.
Innovation Solution
The implementation of a method that senses stimulation artifacts and uses a prediction model to adjust stimulation parameters, maintaining predicted neural features within a set-range or relative to a set-point, utilizing control models like Kalman filtering or PID controllers, even when ECAPs are not detectable, by correlating ECAP and stimulation artifact features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional ECAP detection methods are used to adjust stimulation parameters, then neural response can be directly measured, but the method fails when stimulation is below perception threshold where ECAPs are not detectable
Solution Approach 1:
The patent introduces stimulation artifact features as an intermediary proxy to infer neural response characteristics. Instead of directly measuring ECAPs which are undetectable at sub-perception thresholds, the system uses the stimulation artifact (a measurable signal) and its features (amplitude, duration, shape) as a mediator to indirectly determine neural response properties through correlation and prediction models.
Solution Approach 2:
The patent replaces the direct neural signal detection mechanism (ECAP measurement) with an alternative measurement approach (stimulation artifact analysis). By substituting the mechanical/electrical direct measurement system with a correlational prediction system that uses artifact features to infer neural responses, the system can operate effectively below perception thresholds where direct ECAP detection fails.
2Measurement precision
If stimulation parameters are increased to make ECAPs detectable, then neural response can be measured, but patient perception increases causing discomfort
Solution Approach 1:
The patent implements a feedback control system that continuously monitors stimulation artifact features and uses prediction models to infer neural response characteristics. This feedback loop allows the system to adjust stimulation parameters in real-time to maintain optimal neural engagement below perception thresholds, preventing both under-stimulation and over-stimulation that would cause patient discomfort.
Solution Approach 2:
The patent dynamically changes stimulation parameters (amplitude, frequency, pulse width) based on real-time analysis of stimulation artifact features. By continuously adjusting these parameters to maintain the neural response within an optimal range inferred from artifact characteristics, the system keeps stimulation below perception thresholds while ensuring therapeutic effectiveness.
3Manufacturing precision
If closed-loop control using predicted neural features is implemented, then stimulation precision is improved, but device complexity increases
Solution Approach 1:
The patent implements a self-service control system where the implantable pulse generator automatically analyzes its own stimulation artifacts and adjusts its parameters without external intervention. The device uses built-in sensors and processing circuits to continuously monitor artifact features, run prediction models, and autonomously optimize stimulation parameters, reducing the need for complex external monitoring and manual programming.
Solution Approach 2:
The patent incorporates prediction models that are pre-trained and stored within the device, allowing it to immediately begin inferring neural response characteristics from stimulation artifact features without requiring time-consuming real-time training. This preliminary preparation of predictive algorithms and correlation data enables rapid, precise control decisions while keeping the computational burden manageable.
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
This approach allows for effective adjustment of stimulation therapy at sub-perception thresholds, maintaining desired neural responses without patient perception, enhancing the precision and comfort of spinal cord stimulation.
Implementation Method 1
sensing signals formed by an electric field induced in the tissue by the stimulation
Implementation Method 2
sensing signals formed by an electric field induced in the tissue by the stimulation, and evoked compound action potentials
Data Source
AI summary
Methods and systems for providing closed loop control of stimulation provided by an implantable stimulator device are disclosed herein. The disclosed methods and systems use a neural feature prediction model to predict a neural feature, which is used as a feedback control variable for adjusting stimulation. The predicted neural feature is determined based on one or more stimulation artifact features. The disclosed methods and systems can be used to provide closed loop feedback in situations, such as sub-perception therapy, when neural features cannot be readily directly measured.