Medical Literature Recommender Using EHR Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Healthcare professionals face challenges in efficiently accessing and interpreting vast amounts of medical literature due to the complexity of search engines like PubMed, often retrieving too few or too many relevant publications, and require systems that can provide personalized and relevant medical information based on patient data.

Innovation Solution

A recommender system that uses AI techniques to analyze electronic health records (EHRs), formulate database queries, and present relevant medical literature to healthcare professionals, incorporating natural language processing, expert-system rules, and user feedback to prioritize and organize search results effectively.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a healthcare professional uses a search engine like PubMed to access medical literature, then they can retrieve publications, but they often retrieve too few or too many relevant publications and face difficulty in efficiently accessing and interpreting vast amounts of medical literature

Engineering Contradiction:

Improverelevance of retrieved publicationsVSAvoidtime spent searching and interpreting medical literature

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system introduces an intermediary component that automatically analyzes electronic health records and formulates search queries based on patient-specific data. This intermediary layer bridges the gap between the healthcare professional's needs and the medical literature database, filtering and retrieving only the most relevant publications without requiring the professional to manually search through vast amounts of literature.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables self-service by automatically generating search queries from patient EHR data without requiring the healthcare professional to manually construct search terms or navigate complex search interfaces. The system autonomously retrieves and ranks relevant medical literature based on the patient's specific condition, eliminating the time-consuming manual search process.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If a healthcare professional manually specifies search terms and interprets results, then they can access medical literature, but they face the onerous tasks of specifying search terms and interpreting presented results

Engineering Contradiction:

Improvepersonalization of medical literature recommendationsVSAvoidcomplexity of search process

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system performs self-service by automatically extracting relevant information from electronic health records and formulating appropriate search queries without human intervention. The system independently navigates the search process, retrieves results, and presents them in a user-friendly format, eliminating the need for healthcare professionals to learn or remember complex search syntax and database characteristics.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces the mechanical process of manual search term specification and result interpretation with an automated computational system. Instead of requiring healthcare professionals to manually construct queries and analyze results, the system uses computer algorithms to automatically generate search terms from patient data and intelligently rank and present relevant publications.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If a system provides automated search query formulation, then it reduces the burden of searching, but it requires AI techniques to analyze EHRs and formulate queries accurately

Engineering Contradiction:

Improveefficiency of accessing medical literatureVSAvoidcomplexity of AI processing system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system employs an intermediary layer that connects the simple input of patient EHR data with the complex requirements of medical literature search. This intermediary component automatically performs the complex tasks of analyzing unstructured EHR data, extracting relevant medical information, formulating appropriate search queries, and retrieving results, while presenting a simple interface to the healthcare professional.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20210391075A1Medical Literature Recommender Based on Patient Health Information and User Feedback

Publication Date: 2021.12.16 AMERICAN MEDICAL ASSOC

AI summary

A system recommends to a healthcare professional (HCP) (230) medical literature that is of relevance to the HCP's patients. The system communicates with the HCP (230) and accesses electronic health record (EHR) documents in a database (210) associated with the HCP's patients. The system analyzes the contents of the EHR documents to query a medical-literature database (212) for publications that are deemed relevant to the EHR documents. The extracted publications are then presented to the HCP.