Neural Network Learning Engine for Adaptive Cardiac Therapy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Implantable cardiac devices typically provide limited and non-customized therapies based on a small set of observable parameters, and their computational capabilities are hindered by increased power consumption, preventing the utilization of more complex data processing strategies.

Innovation Solution

A neural network-based learning engine system is implemented in cardiac devices, comprising a cardiac device module for data collection and therapy application, an artificial neural network processing module for training and validation, and a communications link to determine optimal treatment therapies by processing patient data and adjusting operating parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If more complex data processing strategies are implemented to provide customized therapies, then adaptability and treatment efficacy are improved, but power consumption increases

Engineering Contradiction:

Improvecustomized therapy adaptationVSAvoidpower consumption

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system segments the neural network processing into two distinct modules: a training module that operates offline to learn from patient data, and a runtime module that operates online to execute optimized therapy decisions. This segmentation allows complex learning computations to be performed once during training without continuously consuming power during runtime operation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The training module performs preliminary learning and computation before the device needs to operate with patients. By pre-training the neural network on historical patient data and optimizing therapy parameters in advance, the system prepares computational models that can be executed efficiently during runtime without requiring continuous complex processing.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If more complex computations are performed to optimize therapy selection, then treatment efficacy is improved, but device complexity increases

Engineering Contradiction:

Improvetreatment efficacyVSAvoidcomputational complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system extracts the complex learning and optimization computations from the runtime operation. By separating the training module (which handles complex computations) from the runtime module (which executes simplified decisions), the patent removes computational complexity from the device's operational burden while maintaining high treatment efficacy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The runtime neural network module is a simplified copy or instance of the training module's learned models. Rather than replicating complex training computations in the device, the system uses a streamlined version that executes pre-learned patterns, reducing operational complexity while maintaining therapeutic effectiveness.

Inventive Principle:

Principle #26Copying

3Device complexity

If a small set of observable parameters is used for therapy decisions, then device complexity is reduced, but adaptability to individual patients deteriorates

Engineering Contradiction:

Improveparameter monitoring complexityVSAvoidpatient-specific therapy optimization

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The system incorporates feedback loops where patient responses to therapies are continuously monitored and fed back into the training module. This feedback mechanism allows the neural network to learn from actual patient outcomes and refine its therapy recommendations, enabling adaptability to individual patients without requiring complex real-time parameter monitoring.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system dynamically changes and optimizes therapy parameters based on learned patterns from patient data rather than relying on a fixed set of observable parameters. By allowing the neural network to identify and weight different parameters adaptively during training, the system achieves high adaptability without requiring the device to continuously monitor and process a large predefined set of parameters.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS7983744B2Neural network based learning engine to adapt therapies

Publication Date: 2011.07.19 CARDIAC PACEMAKERS INC

AI summary

A system for implementing a cardiac device having adaptive treatment therapies utilizing a neural network based learning engine is disclosed. The system includes an implantable cardiac device module and an external data processing system for specifying the operating characteristics of the cardiac device module. Both the cardiac device module and the external processing system possess an artificial neural network to specify the operation of the cardiac device module as it provides adaptive treatment therapies. The external data processing system includes a complete neural network module that trains and validates the operation of the neural network to match the optimal treatment options with a received set of collected patient data. A runtime neural network module that provides real time operation of the neural network using collected patient data is located within the cardiac device module. The cardiac device module and the external processing module are connected via a communication link.