Extended Clustering of Physiological Signals for Memory Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Implanted medical devices face limitations in memory capacity and battery life, leading to the loss of important physiologic data due to insufficient memory allocation management, particularly in detecting and storing neurological events like seizures, where only a subset of detected events exhibit behavioral manifestations.
Innovation Solution
The implementation of a method to generate extended clusters of data from multiple physiologic signals, including EEG and cardiac signals, that overlap or barely overlap in time, allowing for the selective storage and reporting of relevant data, even when memory space is limited, by using a combination of monitoring elements and data structures with age-based and priority-based allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If memory capacity is increased to store more physiologic data, then data retention is improved, but device complexity and cost increase
Solution Approach 1:
The patent segments memory allocation into multiple priority levels (first priority, second priority, third priority) with different allocation strategies. Critical seizure data receives guaranteed storage space, while less critical data uses available remaining capacity. This segmentation allows efficient memory utilization without requiring excessive total memory capacity.
Solution Approach 2:
The system dynamically changes memory allocation parameters based on detected event severity. When seizures are detected, the system adjusts allocation to prioritize seizure-related physiologic data, automatically modifying storage parameters without requiring increased physical memory capacity.
2Loss of information
If all detected seizure events are stored, then data completeness is improved, but memory capacity requirements increase
Solution Approach 1:
The patent applies different storage qualities to different data types based on their clinical importance. Critical seizure data receives high-priority guaranteed allocation, while non-critical data receives lower-priority allocation from remaining space. This local quality differentiation ensures important data is preserved without storing all data at equal quality levels.
Solution Approach 2:
The system implements a priority-based discarding mechanism where less critical data is discarded or overwritten when memory is full, while critical seizure data is protected. Lower priority data can be recovered or re-stored when memory becomes available, optimizing the use of limited memory capacity.
3Reliability
If memory allocation is optimized for critical events, then reliability is improved, but storage of non-critical data deteriorates
Solution Approach 1:
The patent implements dynamic memory allocation that adjusts in real-time based on detected events. During normal operation, more memory is available for non-critical data. When seizures are detected, the system dynamically shifts allocation to prioritize seizure data, ensuring reliability for critical events while still providing storage for non-critical data during normal periods.
Solution Approach 2:
The system uses feedback from seizure detection to continuously adjust memory allocation. The detection of neurological events provides feedback that triggers reallocation of memory resources, ensuring that critical data always has adequate storage while non-critical data can utilize available capacity during normal operation.
4Measurement precision
If extended clusters with overlapping time periods are created, then data accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent performs preliminary clustering and organization of physiologic data into extended time periods before final analysis. By pre-organizing data with overlapping time windows that capture complete seizure events, the system reduces processing complexity during critical analysis phases while maintaining high data accuracy.
Data Source
AI summary
Methods of generating an extended cluster are disclosed. A first cluster including data representative of a first signal indicative of an abnormal physiological symptom is generated. A second signal is detected as representing a second abnormal physiological symptom and the second abnormal physiological symptom continues after the first abnormal physiological symptom ends. An extended cluster including the data from the first signal and the second signal is generated that extends from the time when the first abnormal physiological symptom occurs to the time when the second abnormal physiological symptom ends. The first and the extended cluster may include data of both the first and second signals the entire period of the clusters. If desired, the first signal or the second signal may be provided from a sensor implanted in a patient's brain tissue.