AI Knowledge Graph for Medical Record Readability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic health records are often in non-standard, fragmented formats, making it difficult for healthcare professionals to review historical encounters, which is crucial for preliminary diagnoses.
Innovation Solution
A computer-implemented system that uses artificial intelligence to analyze medical data, perform temporal analysis, extract features, and create a visual output in an enhanced graphical format, including a health snapshot, interactive body map, and timeline health history, using a knowledge graph and trained AI models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If medical records are stored in nonstandard fragmented formats, then data can be collected from multiple sources, but readability and ease of review deteriorate
Solution Approach 1:
The system segments medical records into standardized components (demographics, vitals, medications, procedures, diagnoses, etc.) while maintaining the ability to collect from multiple fragmented sources. Each segment is processed and standardized independently, then reassembled into a coherent visual presentation that resolves the contradiction between collecting fragmented data and presenting readable information.
Solution Approach 2:
The patent introduces an intermediary processing layer that receives fragmented medical records from multiple sources, standardizes them using common data models, and transforms them into visual presentations. This intermediary layer acts as a mediator between the fragmented input formats and the readable output format, resolving the contradiction between data collection versatility and readability.
2Adaptability or versatility
If medical records are stored in nonstandard fragmented formats, then data can be collected from multiple sources, but diagnostic efficiency deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-processing and standardizing medical records before they reach the physician. Temporal analysis, feature extraction, and visual presentation generation are performed in advance, so when physicians review records, the diagnostic work is already partially completed, thereby improving diagnostic efficiency while maintaining the ability to collect from multiple fragmented sources.
Solution Approach 2:
The patent replaces the mechanical process of manual record review with automated computational processes. AI models perform temporal analysis, extract features, generate visual presentations, and identify patterns automatically, substituting the manual mechanical review process with automated systems that improve diagnostic efficiency while handling fragmented data from multiple sources.
3Device complexity
If traditional medical record formats are used, then data storage is simple, but additional predictive information is lost
Solution Approach 1:
The system introduces dynamic elements to the static medical record storage system. AI models continuously analyze the stored data to generate predictive information, risk assessments, and insights that evolve over time. This dynamic processing layer extracts additional value from the stored data without complicating the underlying storage structure, resolving the contradiction between storage simplicity and information richness.
Solution Approach 2:
The patent creates copies and transformations of the original medical data through visual presentations and AI-generated insights. Instead of storing multiple formats of the same data, the system maintains simple storage while generating enriched copies in the form of visual presentations, temporal analysis results, and predictive information, thereby preserving storage simplicity while preventing information loss.
4Device complexity
If manual review of medical records is used, then system complexity is low, but time consumption increases
Solution Approach 1:
The system implements self-service by enabling automated processing of medical records without requiring extensive manual intervention. AI models automatically perform temporal analysis, extract features, generate visual presentations, and identify patterns, allowing the system to serve itself in processing large volumes of data. This reduces both system complexity and review time by eliminating manual processing steps while maintaining intelligent analysis capabilities.
Data Source
AI summary
The computer-implemented system includes a computer having a processor and memory with executable instructions that run a platform for creating and displaying medical information. The system may receive medical data relating to a patient in FHIR/LPR format, including patient records and vital statistics. The system may perform temporal analysis and feature extraction on the medical data. Using an artificial intelligence model trained on historical patient data, the system may analyze the data to generate a knowledge graph by identifying nodes, determining relationships using semantic analysis and natural language processing, generating edges, and applying graph database algorithms. The system may create a visual output including a health snapshot with generated prose ranked using page rank algorithms, an interactive body map identifying health issues, and an enhanced timeline format health history with drill-down capabilities.