Non-Invasive Hemoglobin Prediction via Smartphone PPG Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing hematologic diseases, such as anemia and sickle cell disease, are invasive, costly, inconvenient, and not readily accessible, especially for children and those in developing countries, with existing non-invasive point-of-care tools being expensive and having poor performance.
Innovation Solution
A non-invasive method and system using near-infrared light to measure blood hemoglobin levels by acquiring time-based series of images of the finger, processing Photoplethysmography (PPG) signals, and employing a predictive model to calculate hemoglobin levels, which can be performed using a smartphone or hand-held device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive laboratory plasma hemoglobin testing is used, then measurement precision is improved, but ease of operation deteriorates due to needle insertion and patient discomfort
Solution Approach 1:
The patent replaces the mechanical invasive blood drawing system with an optical imaging system. A smartphone camera captures images of the conjunctival mucosa, and image processing algorithms analyze the visual characteristics to estimate hemoglobin levels, eliminating needles and invasive procedures while maintaining measurement capability
Solution Approach 2:
The patent uses the conjunctival mucosa as an intermediary tissue to indirectly measure hemoglobin levels. Instead of directly sampling blood, the system analyzes the optical properties of the thin conjunctival tissue, which reflects underlying blood characteristics, providing a non-invasive measurement pathway
2Ease of operation
If point-of-care hemoglobin assessment systems are used, then ease of operation is improved, but device complexity and cost increase
Solution Approach 1:
The patent leverages the smartphone as a multi-functional device that already possesses camera, processor, and display capabilities. By developing a mobile application that utilizes these existing components, the system avoids the need for dedicated expensive hardware, making the device accessible to widespread populations
Solution Approach 2:
The patent creates a digital copy of the hemoglobin measurement function through software algorithms that process images captured by the smartphone camera. This software-based approach replicates laboratory analysis capabilities without requiring physical laboratory equipment, reducing device complexity and cost
3Ease of operation
If smartphone-based conjunctival analysis is used, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent divides the conjunctival image into multiple regions of interest and analyzes specific visual features within each region. By segmenting the image and focusing on characteristic patterns, the system extracts more reliable measurement data, improving precision while maintaining the simplicity of smartphone-based operation
Solution Approach 2:
The patent implements image processing algorithms that enhance and normalize the captured conjunctival images, compensating for variations in lighting, camera quality, and anatomical differences. This feedback mechanism adjusts the analysis to maintain consistent measurement precision across different users and conditions
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
Provides a cost-effective, easy-to-use, and accessible means to determine hemoglobin levels, improving diagnostic access and patient management for hematologic diseases.
Implementation Method 1
illuminated from the dorsal side of the finger with a near infrared light responsive to blood hemoglobin
Implementation Method 2
A time series signal is generated from each block, and at least one Photoplethysmography (PPG) cycle is identified from each of the time series signals
Data Source
AI summary
An image-based hemoglobin estimation tool for measuring hemoglobin can be embedded in handheld devices such as smartphones, and similar known and to be developed technology. The hand-held device acquires video data of a finger illuminated from the dorsal surface by a first near infrared light responsive to hemoglobin and a second near infrared light near responsive to plasma. The acquired video is segmented into frames and processed to produce a Photoplethysmography (PPG) waveform. The features of the PPG waveform can then be identified, and the waveform and corresponding features evaluated by a predictive hemoglobin model. The predictive hemoglobin model can be provided at a remote computer, enabling non-invasive hemoglobin analysis from point of care locations. Near infrared lights of 850 nm and 1070 nm are particularly effective in the process.