Cognitive Agent for Medical Query Intent Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current population health management systems face challenges in efficiently aggregating and analyzing patient data across multiple health information technology resources, leading to suboptimal clinical and financial outcomes, as they struggle to provide actionable insights that improve health outcomes while reducing costs.
Innovation Solution
A cognitive intelligence platform that integrates data from various sources, performs conversational analysis to understand user intent, and generates actionable information by compiling language samples, extracting concepts, and inferring user intent to provide personalized health management recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If population health management systems aggregate and analyze patient data across multiple health information technology resources, then health outcomes improve and costs are reduced, but the system complexity and difficulty of data integration increase
Solution Approach 1:
The patent introduces a natural language processing intermediary that mediates between users and the complex population health management system. Users can query the system using natural language instead of navigating complex data structures, while the system processes the query through multiple stages (parsing, entity extraction, concept mapping, query generation) to retrieve and present relevant health data and insights
2Productivity
If the system provides comprehensive actionable insights through data analysis, then clinical and financial outcomes improve, but the processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-processing and structuring health data into standardized formats with defined entities, attributes, and relationships before queries are submitted. The system maintains pre-computed data models and concept mappings that enable rapid query processing and retrieval of actionable insights without requiring extensive computation at query time
3Quantity of substance
If the system interfaces with multiple health information technology resources, then data comprehensiveness improves, but the ease of operation and user accessibility decrease
Solution Approach 1:
The patent replaces the mechanical interaction model (where users must manually navigate complex system interfaces and data structures) with a natural language processing model. Users can access comprehensive health data by simply typing or speaking their questions in natural language, and the system automatically parses, processes, and retrieves relevant information from multiple integrated health information technology resources
Data Source
AI summary
A method for answering questions posed by a user, the method comprising: receiving from a medical conversational user interface a user-generated natural language medical information query at an artificial intelligence-based medical conversation cognitive agent; extracting a medical question; compiling a medical conversation language sample; extracting internal medical concepts and medical data from the sample; inferring a therapeutic intent of the user; generating a therapeutic paradigm logical framework, wherein logical framework comprises medical logical progression paths from the medical question to respective therapeutic answers, each of the logical progression paths includes medical logical linkages from the medical question to a therapeutic path-specific answer, and the medical logical linkages include the internal medical concepts and external therapeutic paradigm concepts derived from a store of medical subject matter ontology data; selecting a likely medical information path based upon the therapeutic intent of the user; and answering the medical question.