ML-Based Electrode Prediction for DBS Programming

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Deep brain stimulation (DBS) programming is time-consuming due to the increased complexity with segmented leads, requiring more time for determining optimal electrode configurations and therapy settings, which prolongs medical visits for both clinicians and patients.

Innovation Solution

The use of machine learning algorithms to analyze sensing data in a simulated environment, visualize results, and automate the selection of stimulation parameters, including identifying the nearest electrodes to a physiological oscillatory source, reduces programming burden and optimizes therapy settings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If segmented leads with additional contacts are used to improve therapy optimization, then therapy effectiveness is improved, but programming time and complexity increase

Engineering Contradiction:

Improvetherapy effectivenessVSAvoidprogramming time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs self-assessment by automatically analyzing sensing data from the segmented lead contacts to identify the optimal electrode configuration. The processor autonomously determines which contacts are nearest to the oscillatory source without requiring manual clinician evaluation of each contact, allowing the system to self-optimize the therapy parameters.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system accelerates the programming process by using machine learning algorithms that rapidly process sensing data and predict optimal electrode configurations. This computational acceleration replaces the slow, manual trial-and-error approach with a fast automated analysis that identifies the best therapy settings in minutes rather than hours.

Inventive Principle:

Principle #38Strong oxidants (Accelerated oxidation)

2Measurement precision

If manual monopolar review technique is used to determine optimal electrode, then electrode selection accuracy is improved, but medical visit duration increases

Engineering Contradiction:

Improveelectrode selection accuracyVSAvoidmedical visit duration

Core Design Contradiction:

Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The system replaces the manual mechanical process of monopolar review with an automated computational system. The processor analyzes sensing data electronically and uses algorithms to determine optimal electrode selection, substituting the clinician's manual evaluation with an automated digital assessment that achieves comparable or superior accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary computational layer between the sensing data and the final electrode selection decision. The processor acts as an intermediary that processes raw sensing data through machine learning algorithms to generate optimized therapy parameters, mediating between the complex segmented lead configuration and the final therapy settings.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Manufacturing precision

If directional stimulation with multiple contacts is implemented to improve therapy precision, then stimulation precision is improved, but device programming complexity increases

Engineering Contradiction:

Improvestimulation precisionVSAvoidprogramming complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system divides the lead into multiple segmented contacts and independently evaluates each contact's proximity to the oscillatory source. By segmenting the analysis into individual contact assessments based on sensing data, the system manages the complexity of directional stimulation while maintaining high precision in electrode selection.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes the parameters used for electrode selection from manual clinical assessment to automated analysis of sensing data characteristics. By transforming the selection criteria into quantifiable parameters derived from electrical sensing, the system simplifies the programming interface while maintaining stimulation precision.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20230263444A1Therapeutic electrode location prediction visualization using machine learning

Publication Date: 2023.08.24 MEDTRONIC INC

AI summary

Systems and methods for programming an implantable medical device comprising a simulated environment with at least one lead having a plurality of electrodes, computing hardware of at least one processor and a memory operably coupled to the at least one processor, and instructions that, when executed on the computing hardware, cause the computing hardware to implement a training sub-system configured to conduct a brain sense survey using the simulated environment, develop at least one machine learning model based on the brain sense survey, apply the at least one machine learning model to in-vivo patient data to determine at least one predicted electrode from the plurality of electrodes relative to an oscillatory source, visualize the at least one predicted electrode, and program a medical device based on the at least one predicted electrode.