Disease Progression Reference Model Using Temporal Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing disease progression models rely on proprietary data and do not account for treatment improvements and newer medical advances, leading to outdated predictions across populations.
Innovation Solution
The Reference Model uses publically available data and the MIST Python-based framework for Monte Carlo simulations, incorporating a temporal correction term for treatment improvement and biomarker changes, enabling systematic comparison and updating of models across multiple populations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing disease progression models use proprietary data, then model predictions are based on comprehensive data, but the models become outdated and do not account for treatment improvements and newer medical advances
Solution Approach 1:
The model transitions from a static structure using fixed proprietary data to a dynamic structure that continuously incorporates new medical advances and treatment improvements. The system dynamically updates predictions by integrating temporal correction terms and new biomarker data, allowing the model to adapt over time while maintaining reliability.
Solution Approach 2:
The model changes its parameters from fixed proprietary values to dynamic parameters that can be updated with new medical knowledge. Temporal correction terms are introduced to adjust predictions based on treatment improvements over time, and biomarker thresholds are made adjustable to reflect newer medical standards and advances.
2Measurement precision
If models are updated to account for treatment improvements, then prediction accuracy improves, but proprietary data access requirements increase
Solution Approach 1:
The system introduces temporal correction terms as intermediaries between existing model structures and new medical knowledge. These correction terms allow the model to account for treatment improvements without requiring direct access to proprietary clinical trial data, simplifying the data access requirement while maintaining prediction accuracy.
Solution Approach 2:
Instead of requiring access to proprietary original data, the system uses publicly available data combined with temporal correction terms that copy or replicate the effect of proprietary data. This approach maintains measurement precision while reducing device complexity by eliminating the need for proprietary data access infrastructure.
3Ease of operation
If publically available data is used instead of proprietary data, then data accessibility improves, but model accuracy may be reduced
Solution Approach 1:
The model changes from using fixed proprietary parameters to using publicly available parameters enhanced with temporal correction terms. This allows the model to maintain reliability by accounting for treatment improvements over time while using easily accessible public data, thus improving ease of operation without sacrificing prediction reliability.
Solution Approach 2:
The system incorporates feedback mechanisms through temporal correction terms that adjust predictions based on known treatment improvements and medical advances. This feedback loop allows the model to compensate for the lower quality of public data by continuously refining predictions with updated medical knowledge, maintaining reliability while improving data accessibility.
Data Source
AI summary
A method wherein reference disease models predict progression of disease within given populations, utilizing publically available clinical data and risk equations, to give a birds-eye view of clinical trials by allowing multiple trials to be systematically compared simultaneously via parallel processing/High Performance Computing which allows competition among alternative equations/hypothesis combinations; cross validation; and, then ranks results according to fitness via a fitness engine.