Anonymous Medical Rule Aggregation System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing evidence-based approach to determining medical knowledge is slow, making it difficult to adapt to time-varying phenomena and leading to delayed identification and correction of errors, which can adversely impact patient health and trust.
Innovation Solution
A computer system dynamically generates population-based medical rules by iteratively applying and aggregating local medical rules across anonymous sub-populations without sharing Protected Health Information (PHI), using quality metrics to modify and provide the rules to users, enabling continuous adaptation and improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If clinical trials and peer-reviewed publication are used to determine medical knowledge, then reliability of medical knowledge is improved, but time required to generate and update medical knowledge increases
Solution Approach 1:
The patent segments the population-based medical rule validation process into multiple independent sub-populations. Each sub-population can be analyzed separately using the same local medical rule, allowing parallel processing and faster aggregation of results across diverse populations without requiring sequential clinical trials
Solution Approach 2:
The patent applies preliminary action by using retrospective analysis on existing medical records before prospective application. Local medical rules are first validated against historical data from multiple sub-populations to assess performance metrics, and only after successful validation are the rules prospectively applied to guide clinical decisions, reducing the time needed for full clinical trial validation
2Measurement precision
If local medical rules are applied across multiple sub-populations to generate population-based medical rules, then accuracy of medical knowledge is improved, but complexity of the system increases
Solution Approach 1:
The patent implements universality by designing a multi-functional computer system that can perform multiple operations: retrieving medical records, applying local medical rules, calculating performance metrics, aggregating results across sub-populations, and generating population-based medical rules. This single system handles the entire workflow, reducing overall system complexity compared to separate systems for each function
Solution Approach 2:
The patent uses an intermediary approach by introducing a computer system that acts as a mediator between local medical rules and population-based medical rule generation. The computer system aggregates results from multiple sub-populations and applies quality metrics to determine when population-based rules should be generated, simplifying the complex process of cross-population validation
3Adaptability or versatility
If medical rules are updated rapidly to adapt to time-varying phenomena, then adaptability of medical knowledge is improved, but risk of errors increases
Solution Approach 1:
The patent implements feedback mechanisms by continuously monitoring the performance of local medical rules across multiple sub-populations using quality metrics. The system aggregates results and uses this feedback to determine when population-based medical rules should be generated, ensuring that rapid updates are based on validated performance data rather than unverified changes
Solution Approach 2:
The patent applies dynamics by making the medical rule validation and update process dynamic rather than static. The system can adaptively determine when to generate population-based medical rules based on aggregated performance metrics from sub-populations, allowing medical knowledge to evolve rapidly in response to changing conditions while maintaining reliability through continuous validation
Data Source
AI summary
A computer system may iteratively modify a local medical rule that is based on an initial sub-population. In particular, after information specifying the local medical rule and sharing instructions are received from a user of the computer system, the computer system may iteratively apply the local medical rule to one or more additional sub-populations that are associated with other users of the computer system based on the sharing instructions without sharing PHI associated with the initial sub-population. Then, the computer system may aggregate results for the one or more additional sub-populations, and may generate the population-based medical rule by modifying the local medical rule based on the aggregated results and one or more quality metrics. Moreover, the computer system may selectively provide the population-based medical rule to the user without sharing PHI associated with the one or more additional sub-populations.