Wearable PPG Trend Analysis for Early COVID-19 Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AI-based early warning systems for COVID-19 detection require multiple sensors and user-reported data, which can be inaccurate and impractical for healthcare workers due to PPE constraints, and provide only instantaneous predictions that do not account for health changes over time.
Innovation Solution
A method and system using photoplethysmography (PPG) data from a wearable device, employing a prediction model with post-processing to derive Positive Instance Ratios (PIR) and trend lines for accurate COVID-19 detection by analyzing heart rate and oxygen saturation dynamics over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors and user-reported data are used for COVID-19 prediction, then measurement precision is improved, but device complexity and ease of operation worsen due to PPE constraints
Solution Approach 1:
The patent extracts and uses only the essential PPG data from wearable devices, eliminating the need for multiple sensors and user-reported data. This extraction approach maintains prediction accuracy while reducing system complexity and making it compatible with PPE constraints for healthcare workers
Solution Approach 2:
The PPG sensor serves multiple functions: it captures physiological data for COVID-19 prediction, monitors heart rate, and tracks oxygen saturation levels. This multi-functionality reduces the need for separate dedicated sensors while maintaining comprehensive monitoring capabilities
2Productivity
If instantaneous AI model output is used for prediction, then productivity is improved, but reliability worsens due to lack of temporal health change context
Solution Approach 1:
The system performs preliminary processing by collecting and storing PPG data over time periods before final prediction analysis. This preliminary data accumulation ensures that when predictions are made, they are based on sufficient temporal context, improving reliability without significantly delaying the prediction output
Solution Approach 2:
The system incorporates feedback mechanisms that continuously monitor health changes over time and adjust predictions accordingly. By feeding temporal health trend information back into the prediction model, the system maintains high reliability while operating at productive speeds
3Loss of information
If real-time data transmission is implemented, then information availability is improved, but harmful factors increase due to interference with ICU electronics
Solution Approach 1:
Instead of continuous real-time transmission, the system implements periodic data transmission at intervals. This approach maintains information availability for monitoring purposes while significantly reducing the frequency of electromagnetic transmissions that could interfere with sensitive ICU electronic equipment
Solution Approach 2:
The system uses local processing and storage as an intermediary layer between data collection and transmission. Data is processed and analyzed locally on the wearable device or nearby server, with only essential results transmitted, thereby reducing transmission frequency and minimizing potential interference with ICU electronics
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
Enables early detection of COVID-19 in healthcare workers by predicting infection trends days in advance, facilitating timely interventions and avoiding clinical complications, without real-time data transmission or additional devices.
Implementation Method 1
receiving photoplethysmography (PPG) data collected by a wearable device of a subject
Data Source
AI summary
The present invention relates to a method and system for early detection of COVID-19. Existing methods require data from multiple sensors for training a prediction model whose output is considered as final prediction which is actually the prediction for a particular day or time instance. However, this prediction doesn't detect actual infection of COVID-19 since it requires monitoring the change in health of the user over consecutive days. Embodiments of present disclosure overcome these challenges by a prediction model for COVID-19 which requires only data from Photoplethysmography (PPG) sensor seamlessly collected from a wearable device still able to provide accurate COVID-19 prediction with application of a post processing technique on the predictions of the prediction model. Since COVID-19 symptoms have an effect on heartrate and oxygen saturation which are effectively captured by PPG sensor data, studying these dynamics during infection period gives insights to perform early detection of COVID-19.