LLM-Mediated Patient Information Retrieval for Complete Data Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for retrieving patient information from databases require computer language queries, leading to incomplete data retrieval and potential oversight of relevant entries.
Innovation Solution
A system utilizing a large language model to process natural language queries, convert them into computer language queries, map these queries to database entries, and generate a graphical user interface displaying the results, enabling comprehensive data retrieval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If natural language queries are used instead of computer language queries, then ease of operation is improved, but data retrieval completeness deteriorates
Solution Approach 1:
The patent introduces a large language model as an intermediary component that translates natural language queries into computer language queries. This mediator enables users to interact with the database using natural language while ensuring accurate and complete data retrieval through properly structured computer language queries generated by the LLM.
Solution Approach 2:
The system segments the query processing into distinct stages: natural language input, LLM-based translation to computer language, atomic element extraction, node mapping to database entries, and final query generation. This segmentation allows each component to specialize in its function, maintaining both ease of use and retrieval completeness.
2Reliability
If natural language queries are converted into computer language queries with atomic elements and nodes, then data retrieval completeness is improved, but device complexity increases
Solution Approach 1:
The large language model performs self-service by automatically generating the complex computer language query structure, including atomic elements and node mappings, from the natural language input. This eliminates the need for manual query construction and reduces the perceived complexity for users while maintaining complete data retrieval.
Solution Approach 2:
The system performs preliminary actions by pre-defining the relationship between atomic elements, nodes, and database entries. The LLM is pre-trained to understand this mapping structure, allowing it to automatically generate appropriate queries without requiring the user to understand the underlying complexity of atomic elements and node mappings.
3Measurement precision
If atomic elements and nodes are mapped to database entries, then measurement precision is improved, but difficulty of detecting and measuring increases
Solution Approach 1:
The system implements feedback mechanisms where the LLM generates atomic elements and nodes, which are then mapped to database entries. The mapping results feed back into the query generation process, allowing the system to refine and adjust the query structure based on the actual database schema and available entries, thereby improving precision while managing complexity.
Data Source
AI summary
A system for retrieving patient information using large language models including a computing device configured to receive a natural language query as a function of a user input, input the natural language query into a large language model communicatively connected to the least a processor, receive a computer language query comprising a plurality of nodes from the large language model, map the plurality of nodes to one or more entries in a patient database, receive a database response from the patient database as a function of the mapping, generate a final database query as a function of the database response. query the patient database using the final database query, receive a user response as a function of the final database query, and transmit the user response to a graphical user interface as a function of the final database query.