Flexible Thermal Patch for Core Body Temperature Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wearable noninvasive core body temperature monitoring devices are limited by their invasive nature, power requirements, and accuracy, particularly in resource-limited settings, and lack integration with machine learning algorithms for precise temperature prediction.
Innovation Solution
A flexible, foldable thermal device with multiple temperature sensors and a machine learning algorithm that uses environmental context data to predict core body temperature, allowing for wireless, low-power operation and accurate monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If heat flux measurements are used for noninvasive core body temperature monitoring, then accuracy is improved, but power consumption increases and requires connection to electrical outlet
Solution Approach 1:
The heater component is extracted from the system, transitioning from active heat flux measurement to passive thermal conduction measurement. This removes the power-consuming element while retaining temperature monitoring capability through simplified thermal sensor arrays that measure temperature gradients without requiring external heating.
Solution Approach 2:
The active heating mechanism is replaced with passive thermal conduction principles. Instead of using a heater to create thermal gradients, the system relies on natural thermal conduction through the substrate and insulating layers, substituting mechanical/electrical energy input with passive physical processes.
2Measurement precision
If multiple temperature sensors are used to enhance accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The sensing function is segmented into multiple independent temperature sensors distributed across the patch, each measuring local temperature at different positions. This segmentation allows accurate reconstruction of thermal gradients and core body temperature through distributed measurement points without requiring complex individual sensor elements.
Solution Approach 2:
The temperature sensors serve multiple functions: measuring skin surface temperature, detecting thermal gradients through the substrate, and providing data for machine learning algorithms. This multi-functionality reduces the need for separate specialized components, simplifying the overall device architecture while maintaining high measurement precision.
3Measurement precision
If invasive monitoring devices are used, then measurement precision is improved, but ease of operation and adaptability worsen
Solution Approach 1:
The invasive measurement capability is copied and replicated through multiple noninvasive temperature sensors positioned on the skin surface. By measuring temperature at multiple external points and using thermal conduction principles, the system reconstructs core body temperature without requiring physical insertion into the body, thus achieving invasive-level accuracy through noninvasive means.
Solution Approach 2:
The device uses a flexible substrate with thin insulating and sensing layers that can conform to the skin surface. This flexible, thin-film construction enables easy application and removal without invasive procedures, while the close contact with skin ensures accurate thermal measurement through the flexible interface.
4Measurement precision
If machine learning algorithms are integrated for temperature prediction, then measurement precision is improved, but device complexity and power consumption increase
Solution Approach 1:
The machine learning model is trained beforehand using extensive temperature data to learn the relationship between sensor readings and core body temperature. This preliminary training phase allows the model to be deployed as a pre-processed algorithm that requires minimal real-time computation, reducing both device complexity and power consumption during actual operation while maintaining high prediction accuracy.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The device provides accurate and continuous core body temperature monitoring with reduced power consumption, suitable for resource-limited settings and integration with machine learning for enhanced prediction accuracy, addressing the limitations of existing technologies.
Implementation Method 1
a thermally conducting material disposed within the thermal zone and beneath the pair of copper semi-circular components
Implementation Method 2
a first insulating material disposed in a covering relationship on the thermal zone... a second insulating material disposed in a covering relationship on the bottom layer of the patch
Implementation Method 3
an annular copper ring circumferentially disposed around a thermally conducting material... a pair of copper semi-circular components disposed within the annular copper ring
Data Source
AI summary
Provided herein are thermal devices and single-use temperature measurement devices to predict and to monitor core body temperature in a subject, such as a patient. The devices utilize a plurality of thermal or temperature sensors disposed on a patch and insulated one from the other and a connection to a machine learning algorithm for prediction and monitoring. Also provided are systems and methods using the thermal device or temperature monitoring device and the machine learning algorithm to predict and measure core body temperature in the subject.