Camera-Based Neonatal Oxygen Saturation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing neonatal care systems face challenges in accurately and continuously monitoring neonatal patient characteristics, such as oxygen saturation, heart rate, and respiratory rate, especially when access points are open, potentially disrupting the controlled microenvironment.
Innovation Solution
An infant care station equipped with cameras and processors that generate point clouds from video data, train artificial intelligence instructions to detect patient characteristics, and integrate ballistographic and vital measurement devices to predict neonatal characteristics, while also detecting open access points and anomalies in the microenvironment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring devices are used to detect patient characteristics, then measurement accuracy is maintained, but device complexity and patient accessibility are reduced
Solution Approach 1:
The camera system performs multiple functions: capturing visual images for patient monitoring, generating point clouds for 3D analysis, and detecting patient characteristics through AI processing. This multi-functional approach replaces dedicated monitoring devices, reducing overall system complexity while maintaining measurement capabilities.
Solution Approach 2:
The patent introduces AI processing as an intermediary between the camera data and patient characteristic detection. The AI model processes raw camera images and point clouds to extract physiological parameters, enabling accurate measurement without direct contact with the patient and reducing the need for complex traditional sensors.
2Ease of operation
If access points are opened to access neonates, then ease of operation is improved, but microenvironment stability deteriorates
Solution Approach 1:
The system continuously monitors the microenvironment conditions (temperature, humidity, gas composition) and provides feedback to the control system. When access points are opened, the feedback mechanism detects changes and triggers compensatory actions to restore and maintain microenvironment stability, enabling frequent access without compromising the controlled atmosphere.
Solution Approach 2:
The microenvironment control system transitions from a static, fixed-state approach to a dynamic, adaptive approach. The system continuously adjusts temperature, humidity, and gas flow rates based on real-time conditions, allowing the microenvironment to adapt to disturbances from access point openings while maintaining optimal conditions for neonate care.
3Reliability
If continuous monitoring is implemented, then reliability is improved, but energy consumption increases
Solution Approach 1:
The camera system operates in periodic cycles rather than continuous operation. It captures images at intervals sufficient for reliable patient characteristic detection and microenvironment monitoring, then enters low-power states. This periodic operation maintains monitoring reliability while significantly reducing energy consumption compared to truly continuous operation.
Solution Approach 2:
The AI processing system automatically analyzes captured images and detects patient characteristics without requiring constant human intervention or additional processing power. The system self-manages the monitoring workflow, processing only when necessary and using efficient algorithms to minimize computational energy requirements while maintaining reliable detection capability.
Data Source
AI summary
A system for predicting a characteristic of a neonate, the system including a ballistographic monitoring device configured to measure movement of the neonate and create a ballistographic signal from the measured movement, a vital measurement device configured to measure a vitals measurement of the neonate and create a vital signal from the vitals measurement, a camera configured to capture an image of the neonate and create a camera signal from the image, a memory including instructions, and at least one processor to execute the instructions to extract a first feature from the ballistographic signal, extract a second feature from the vital signal, extract a third feature from the camera signal, process the first feature, the second feature, and the third feature using a learning model trained to generate a prediction for a characteristic of the neonate, and display the prediction from the learning model on a user interface.