Individualized Disease Timeline Modeling for Screening Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for assessing passenger screening protocols for cross-border travel during the COVID-19 pandemic have been ineffective in minimizing disease translocation risks due to their reliance on generic infectious disease test performance models that do not account for individual variability in disease timelines.
Innovation Solution
The development of a method that creates unique disease timelines for each individual, incorporating events such as disease exposure, symptom onset, and end of contagious period, to model test sensitivity as a function of specific disease timelines, using cubic splines to generate a unique test performance trajectory and determine the probability of a positive test result at each time point.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a generic infectious disease test performance model is used for all individuals, then the modeling process is simple and quick, but the accuracy of test performance prediction deteriorates due to inability to account for individual variability in disease timelines
Solution Approach 1:
The patent applies dynamics by transitioning from a static, generic test performance model to a dynamic, individualized model that adapts to each person's unique disease timeline. The system calculates personalized test sensitivity curves based on an individual's specific progression through disease stages (exposure, symptom onset, severe symptom onset, end of contagious period), making the model responsive to individual variability rather than relying on population averages.
Solution Approach 2:
The patent changes key parameters from fixed population-level test performance values to variable, individual-specific parameters. By modeling test sensitivity as a function of time relative to individual disease events (exposure, symptom onset, etc.), the system adjusts test performance parameters dynamically based on each person's unique timeline, thereby improving prediction accuracy without using overly complex modeling approaches.
2Measurement precision
If individualized disease timelines are created for each person, then test performance modeling accuracy improves, but the computational time and resources required increase
Solution Approach 1:
The patent segments the disease progression into distinct, manageable stages (exposure, symptom onset, severe symptom onset, end of contagious period). By dividing the complex disease timeline into these discrete events, the system can model test sensitivity at each stage separately using standardized functions, reducing computational complexity while maintaining individualized accuracy. This segmentation allows efficient processing without requiring complex real-time simulations.
3Reliability
If conventional screening protocols are used without individualized modeling, then the screening process remains simple and fast, but the ability to minimize disease translocation risks deteriorates
Solution Approach 1:
The patent implements feedback mechanisms by continuously monitoring an individual's disease timeline progression and adjusting test sensitivity predictions accordingly. The system uses feedback from reported symptoms and disease stage transitions to update the personalized test performance model, enabling more reliable risk assessment. This feedback loop allows the screening protocol to adapt to individual conditions, improving disease translocation risk minimization while maintaining operational efficiency through automated updates.
Data Source
AI summary
Aspects of the disclosure provide solutions for modeling an efficacy of disease screening and testing strategies for an infectious disease. Examples include: identifying events for a disease timeline for the infectious disease, creating a model of test sensitivity as a function of the events, adaptively mapping the events to characteristics of the infectious disease unique to a simulated infected person, based at least on adaptively mapping, creating a unique disease timeline for the simulated infected person, and creating a numerical function specific to the unique disease timeline to model sensitivity as a function of the unique disease timeline.