Clinical Knowledge Discovery System for Patient Query Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Patients and non-clinical experts face difficulties in retrieving and understanding medical information from technical records due to limitations in formulating effective queries and assimilating complex search results, leading to inadequate health-related decision-making.
Innovation Solution
A clinical knowledge discovery system combining natural language processing and deep learning algorithms to process user queries, generate professional medical terms, retrieve relevant information, and summarize findings for non-expert users through an inferencing engine and summary engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional computer search techniques are used to search for medical terms, then the search can be performed quickly, but the results are spotty and provide less-than-satisfying explanations because they are based on the patient's non-expert presentation of terms
Solution Approach 1:
The patent introduces an intermediary system comprising natural language processing components and medical knowledge bases that mediate between the patient's non-expert query and the medical literature database. The system translates patient language into professional medical terminology through intermediate processing layers, enabling accurate retrieval without requiring patients to formulate expert-level queries.
Solution Approach 2:
The search process is segmented into multiple independent stages: natural language processing to extract intent, medical terminology translation, query expansion using medical knowledge graphs, and result retrieval. This segmentation allows each component to specialize in its function, improving overall search accuracy while maintaining ease of use.
2Loss of information
If the system retrieves comprehensive medical reference material to answer patient queries, then the information completeness improves, but the volume of located reference material becomes overwhelming for the patient to assimilate
Solution Approach 1:
The system extracts only the most relevant information from comprehensive medical references based on the patient's specific query intent. Rather than presenting all available reference material, the system selectively extracts and presents only the pertinent findings, explanations, and recommendations that directly address the patient's concern.
Solution Approach 2:
The information presentation is dynamically adapted to the patient's query and needs. The system adjusts the level of detail, complexity, and format of the presented information based on the specific medical topic and inferred patient understanding, transforming static comprehensive references into dynamic, personalized explanations.
3Reliability
If the system provides detailed medical explanations in professional language, then the medical accuracy is maintained, but the patient comprehension decreases because the language is unintelligible to non-experts
Solution Approach 1:
The system applies different language qualities to different parts of the response. Medical terminology and precise clinical language are used where accuracy is critical (e.g., diagnostic terms, treatment names), while explanatory passages use simplified, patient-friendly language. This local differentiation maintains medical accuracy while improving comprehensibility.
Solution Approach 2:
A language translation intermediary layer converts between professional medical language and patient-friendly explanations. This intermediary maintains the precise meaning and medical accuracy of the source material while rendering it accessible to non-expert patients through analogies, simplified terminology, and contextual explanations.
Data Source
AI summary
A medical information retrieval system comprises a natural language processing system that processes a vocal user query to identify key words and phrases. These key words and phrases are provided to an inferencing engine that provides a set of knowledge-based inferences from medical knowledge sources, based on these key words and phrases. Thereafter, these knowledge-based inferences are provided to an information retrieval engine that retrieves a corresponding plurality of medical articles based on these knowledge-based inferences, and ranks each with respect to the knowledge-based inferences. A summary engine receives the ranked articles and creates a model based on the topical keywords and candidate sentences found in the highly ranked articles. A paraphrase engine processes the candidate sentences to provide a summary response based on a knowledge-based paraphrase model. An audio output device renders the summary report as the response to the user's original vocal query.