Posture State Responsive Therapy Using Dwell Times
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical devices struggle to accurately classify and respond to a patient's posture and activity states in real-time, leading to potential inappropriate therapy adjustments and instability in treatment delivery.
Innovation Solution
A system that uses sensors to classify posture and activity states by comparing signals to predefined definitions, incorporating dwell times, episode detection, and M-of-N filters to ensure stability and prevent transient changes from triggering therapy adjustments, allowing for programmable and adaptive responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If therapy is adjusted in real-time based on detected posture changes, then therapy adaptability is improved, but therapy stability deteriorates due to transient posture changes triggering inappropriate adjustments
Solution Approach 1:
The system performs preliminary classification of posture states before triggering therapy adjustments. By pre-defining posture classifications and requiring sustained detection of these classifications, the system prepares and validates posture data before using it to modify therapy, preventing transient changes from causing inappropriate adjustments
Solution Approach 2:
The system dynamically adjusts therapy parameters based on detected posture states, allowing the therapy to adapt to changing patient conditions. The system monitors posture continuously and modifies therapy in real-time when sustained posture changes are detected, creating a dynamic response to patient needs
2Measurement precision
If posture classification is performed continuously, then measurement precision is improved, but device complexity increases due to signal processing requirements
Solution Approach 1:
The system segments the continuous signal processing task into discrete posture classifications. By defining specific posture states (e.g., supine, sitting, standing) with distinct signal thresholds, the system breaks down complex continuous analysis into manageable discrete categories, reducing processing complexity while maintaining precision
Solution Approach 2:
The system introduces an intermediary classification layer between raw sensor signals and therapy control. Posture classifications act as intermediaries that simplify the interface between complex sensor data and therapy adjustment logic, making the system more manageable while preserving measurement accuracy
3Stability of the object's composition
If dwell time filtering is applied to prevent transient changes, then therapy stability is improved, but response time deteriorates due to delayed therapy initiation
Solution Approach 1:
The system applies partial filtering by requiring posture changes to be sustained for a threshold duration (dwell time) before triggering therapy adjustments. This partial action filters out transient noise while still allowing genuine posture changes to trigger timely therapy responses, balancing stability with responsiveness
Data Source
AI summary
Techniques related to classifying a posture state of a living body are disclosed. One aspect relates to sensing at least one signal indicative of a posture state of a living body. Posture state detection logic classifies the living body as being in a posture state based on the at least one signal, wherein this classification may take into account at least one of posture and activity state of the living body. The posture state detection logic further determines whether the living body is classified in the posture state for at least a predetermined period of time. Response logic is described that initiates a response as a result of the body being classified in the posture state only after the living body has maintained the classified posture state for at least the predetermined period of time. This response may involve a change in therapy, such as neurostimulation therapy, that is delivered to the living body.