GenAI Query Generation for Surgical Data Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical devices, particularly sensor-equipped surgical instruments, generate vast amounts of data, but accessing timely and relevant information about patients, caregivers, or medical device usage is limited.
Innovation Solution
A system utilizing a generative artificial intelligence (GenAI) model to process natural language requests and generate database queries for a graph database, enabling rapid access to contextual data associated with network-connected medical devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If sensor-equipped surgical instruments generate vast amounts of data, then the quantity of information increases, but the ability to access timely and relevant information is limited
Solution Approach 1:
The system extracts and stores surgical event information in a structured graph database format, separating relevant data from the vast amount of raw sensor data. This extraction enables efficient querying and timely access to specific surgical events without processing the entire data set.
Solution Approach 2:
The system transforms raw sensor data into structured surgical event records with specific parameters (event type, timestamp, device ID, etc.). This parameterization allows for efficient indexing and retrieval, converting unstructured data into queryable information that can be accessed rapidly.
2Speed
If a graph database is queried using generated database queries, then data access speed improves, but computing resource consumption increases
Solution Approach 1:
The system pre-structures surgical event data into a graph database with defined relationships and indices before querying is needed. This preliminary organization allows for fast query execution without requiring complex real-time data processing, reducing computing resource consumption during actual surgical operations.
3Ease of operation
If natural language requests are processed through GenAI models, then ease of use improves, but system complexity increases
Solution Approach 1:
The system introduces a GenAI model as an intermediary that translates natural language requests into structured database queries. This intermediary layer allows users to access surgical data using simple language while the complex query translation and execution is handled automatically by the AI model and database system.
Data Source
AI summary
A natural language request is received for surgical event information associated with one or more network-connected medical devices. Based on the natural language request, a generative artificial intelligence model is prompted to generate a database query. This database query is used to query a graph database which returns, data responsive to the database query. Such responsive information can be conveyed to a user initiating the request in a user interface (e.g., GUI, audio, etc.). In some variations, the results from the graph database are used to poll one or more other models to obtain further contextual information or to provide curation of the results in a more user-friendly and intuitive manner.