Medical Information Navigation Engine for Clinical Data Mining
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The medical field faces challenges with unreliable and inaccessible medical information management, leading to inefficiencies and poor quality of care, as existing systems fail to effectively consolidate and utilize patient data to calculate payoffs based on encounter outcomes.
Innovation Solution
A Medical Information Navigation Engine (MINE) that computes concept associations by aggregating patient data, filtering out random associations, and providing ranked results to users, ensuring secure and relevant information access for improved care efficiency and quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If medical information is consolidated and aggregated from multiple sources, then information reliability and accessibility are improved, but system complexity and data security risks increase
Solution Approach 1:
The patent introduces a Medical Information Navigation Engine (MINE) as an intermediary system that sits between multiple medical information sources and users. The MINE consolidates data from EHRs, billing systems, and other sources without requiring direct integration between them, thereby improving information reliability while managing system complexity through a centralized mediation layer.
Solution Approach 2:
The system creates aggregated copies of medical information from multiple sources and stores them in a standardized format within the MINE. This allows the system to work with consolidated data without permanently altering or centralizing sensitive original records, thus improving accessibility while maintaining security and managing complexity.
2Reliability
If payoff calculation is tied to encounter outcomes, then care quality is improved, but measurement complexity and data processing requirements increase
Solution Approach 1:
The patent implements a feedback mechanism where the MINE calculates payoffs based on actual encounter outcomes and feeds this information back to providers and administrators. This enables quality-based reimbursement by measuring actual care outcomes rather than just quantity of services, thereby improving care quality while using automated algorithms to manage measurement complexity.
Solution Approach 2:
The system changes the parameters used for payment calculation from service quantity metrics to outcome-based metrics. By transforming how payoffs are computed—using aggregated clinical data to measure actual patient outcomes rather than billing codes alone—the system improves care quality while managing complexity through standardized parameter transformations.
3Loss of information
If aggregated patient data is mined for concept associations, then information utility is improved, but risk of exposing protected health information increases
Solution Approach 1:
The MINE acts as an intermediary that processes and aggregates patient data to extract meaningful concept associations without directly exposing individual patient records. The system mines patterns from aggregated data while maintaining privacy through the intermediary layer, thus improving information utility while minimizing PHI exposure risk.
Solution Approach 2:
The system works with anonymized copies of patient data for mining concept associations. By creating and processing aggregated copies rather than accessing original PHI, the MINE extracts valuable clinical insights and concept relationships while eliminating the risk of exposing protected health information.
Data Source
AI summary
A medical processor computes concept associations by mining aggregated data from patient documents thereby reducing risk of PHI exposure. The processor identifies clinically relevant terms in patient documents, compute associations between pairs of clinically relevant terms using co-occurrences, and filter out random associations. A knowledge provider receives user query concepts, retrieves patient concepts, and extracts relevant apixions from an association matrix. The knowledge provider intersects relevant apixions with patient concepts, ranks and provides the results to the user.