Computational Evidence Graph for Next-Best Clinical Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical evidence is predominantly narrative and document-based, leading to inefficiencies such as delayed diffusion, ineffective scaling, alert fatigue, and minimal feedback, and is unable to support individualized assessments needed for precision medicine.
Innovation Solution
A computational evidence platform that converts medical evidence into structured, computational elements, enabling applications to query and utilize this evidence for real-time, individualized patient assessments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If medical evidence is represented as narrative documents and guidelines, then human interpretability is maintained, but diffusion speed and scalability are severely limited
Solution Approach 1:
The patent transforms medical evidence from narrative text format to structured computational data format (graphs with nodes and edges representing conditions, factors, and investigations). This parameter change enables rapid diffusion and scaling while maintaining interpretability through standardized ontologies like SNOMED CT and LOINC.
Solution Approach 2:
The patent segments medical evidence into discrete computational elements (conditions, diagnostic factors, risk factors, investigations) that can be independently processed, queried, and combined. This segmentation enables efficient diffusion across the system while reducing the complexity of handling comprehensive evidence sets.
2Loss of time
If manual search and interpretation of medical evidence is performed, then accuracy of evidence application is maintained, but time consumption increases significantly
Solution Approach 1:
The patent replaces manual mechanical search and interpretation processes with automated computational systems. The graph database structure enables computers to efficiently query, filter, and synthesize evidence based on patient characteristics, eliminating time-consuming manual searches while maintaining precision through structured data relationships.
Solution Approach 2:
The system enables self-service evidence retrieval where the computational graph automatically queries relevant evidence based on patient data without requiring manual intervention. The structured format allows the system to self-organize and retrieve appropriate evidence instantaneously, reducing time loss while maintaining application accuracy.
3Adaptability or versatility
If standardized ontologies are mapped to documents, then interoperability is improved, but controllable use by AI systems remains limited
Solution Approach 1:
The patent creates a universal computational graph format that serves multiple functions: it represents medical evidence, enables AI querying, supports clinical decision-making, and facilitates data interoperability through standardized ontologies. This multi-functionality achieves both high interoperability and AI controllability simultaneously.
Solution Approach 2:
The computational graph structure acts as an intermediary layer between standardized ontologies and AI systems. It translates ontology mappings into actionable computational representations that AI can process controllably, bridging the gap between interoperability standards and AI processing requirements.
4Adaptability or versatility
If narrative evidence is converted to computational elements, then scalability for precision medicine is enabled, but system complexity increases
Solution Approach 1:
The patent segments the complex task of precision medicine support into discrete computational operations on segmented data elements. The graph structure breaks down complex patient assessments into queries about individual conditions, factors, and investigations, enabling scalability while managing complexity through modular data organization.
Solution Approach 2:
The transformation from narrative to computational format changes the fundamental parameters of evidence representation, enabling precise filtering and matching for individualized patient care. This parameter change provides the scalability needed for precision medicine through efficient data querying and synthesis capabilities.
Data Source
AI summary
A computational evidence platform extracts clinical concepts from medical evidence sources and creates a database of elemental diagnostic factors and elemental investigations links to medical conditions. Input from a person groups factors and investigations makes corrections and adds a ranking. Elemental factors and investigations do not include information specific to their associated conditions but include synonyms and a link to a medical ontology. A patient state is determined by extracting patient known diagnostic factors and investigation results from the patient chart. These known factors and results are matched to the database and a ranking of likely conditions are output. Next-best actions per condition are output by determining factors not yet known and investigations not yet performed. Next-best actions across conditions are determined by performing a recursive tree search of the database and assuming that unknown factors are now known to generate a score for each assumption.