Exacerbation Risk Prediction Using Exertion Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing exacerbation risk prediction systems for respiratory diseases, such as COPD, fail to accurately predict exacerbations as they do not consider biological information during exertion and only focus on data at rest, leading to insufficient prediction accuracy.
Innovation Solution
An exacerbation risk prediction system that acquires and analyzes biological information, patient information, and environmental data, using a learning model to predict exacerbation risk, which includes respiratory rate, waveform, exhaled gas components, and environmental factors like temperature and humidity, to provide timely warnings and adjust environmental conditions to mitigate risks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If only data at rest is used for prediction, then the system complexity is reduced, but the prediction accuracy deteriorates
Solution Approach 1:
The patent segments biological information into two distinct categories: data at rest and data on exertion. This segmentation allows the system to collect comprehensive data from multiple states without overwhelming the prediction model with undifferentiated information, thereby maintaining prediction accuracy while managing system complexity through structured data organization
Solution Approach 2:
The patent adds a new dimension to the prediction system by incorporating temporal and activity-state dimensions. Instead of single-point measurements, the system collects data across different time points and activity states (rest vs. exertion), transforming the prediction approach from static to multi-dimensional analysis, which significantly improves prediction accuracy
2Measurement precision
If biological information on exertion is included, then the prediction accuracy is improved, but the data collection complexity increases
Solution Approach 1:
The patent employs a multi-functional data collection system that can operate in different modes (rest and exertion) using the same underlying infrastructure. The biological information acquisition unit is designed to universally collect data across various activity states, eliminating the need for separate specialized systems for each state and thereby managing data collection complexity while improving prediction accuracy
Solution Approach 2:
The system transitions from static data collection (only at rest) to dynamic data collection (both at rest and on exertion). By implementing dynamic monitoring capabilities that adapt to different activity states, the system captures more comprehensive physiological information without requiring permanently complex collection mechanisms, thus improving prediction accuracy while keeping data collection complexity manageable
Data Source
AI summary
An exacerbation risk prediction system predicts an exacerbation risk of a patient suffering from a respiratory disease. The exacerbation risk prediction system includes an oxygen concentrator that supplies oxygen to the patient through a cannula, an acquisition unit that acquires first information including biological information of the patient wearing the cannula on exertion and at rest and patient information regarding a disease state, a storage that stores the first information, a prediction unit that predicts the exacerbation risk based on the first information, and a learning unit that learns the first information and an evaluation regarding exacerbation in association with each other. The biological information is at least one of respiratory rate, respiratory waveform, and exhaled gas component amount. The biological information is acquired from the oxygen concentrator. The prediction unit predicts the exacerbation risk by inputting the first information to a learning model created by the learning unit.