Bed Sensor Motion Intensity Estimation via Learning Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional patient movement monitoring systems are intrusive and inefficient, particularly for patients with conditions requiring continuous monitoring, as they rely solely on sensors attached to the body, which can burden the patient and provide incomplete motion intensity data.
Innovation Solution
A system that incorporates sensors into the bed, such as load sensors under the bed or bed legs, to complement sensors on the patient, using a learning model to predict motion intensity by assuming a greater sensing range for bed sensors compared to body sensors, thereby providing non-invasive and comprehensive data collection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are attached to the patient's body for monitoring, then motion intensity data can be collected, but the patient experiences burden and discomfort
Solution Approach 1:
The patent introduces bed sensors as an intermediary device to collect motion intensity data indirectly through the bed structure, eliminating the need for direct body attachment. The bed sensors detect patient movements via changes in bed surface characteristics, providing the same measurement function without the harmful effect of burdening the patient.
Solution Approach 2:
The patent creates a copy of the motion detection function by placing sensors in the bed environment rather than on the patient. The bed sensors capture motion patterns that are then processed to reconstruct motion intensity data equivalent to what body sensors would provide, but without direct contact with the patient.
2Measurement precision
If only body sensors are used for monitoring, then motion data is collected, but the sensing range is limited compared to bed sensors
Solution Approach 1:
The patent merges the sensing capabilities of bed sensors with body sensors to create a comprehensive monitoring system. The bed sensors provide broad area coverage while body sensors provide localized precision measurements, and their data is integrated to achieve both extensive sensing range and high measurement precision simultaneously.
3Ease of operation
If bed sensors are used to monitor patient movement, then non-invasive monitoring is achieved, but the system complexity increases due to model learning requirements
Solution Approach 1:
The patent transforms the complex problem of interpreting raw bed sensor data into a more manageable form by changing the parameter representation. The system learns optimal parameter transformations that map bed sensor readings to meaningful motion intensity metrics, simplifying the interpretation process while maintaining accuracy.
Data Source
AI summary
A computer-implemented method for learning a model to predict movements of a person in bed is presented. The method includes receiving first data from a plurality of first sensors installed on a bed patient support apparatus, receiving second data from a plurality of second sensors installed on the person, and learning a model to predict the second data based on the first data by assuming a sensing range of motion intensity by the plurality of first sensors is greater than a sensing range of motion intensity by the plurality of second sensors.