EMR Free Text Search via Crawler and De-identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems lack effective free text searching capabilities within electronic medical records, and existing search engines are not customized for medical data, posing challenges in data retrieval and analysis while also needing to comply with HIPAA regulations for patient privacy.

Innovation Solution

A system and method for free text searching of electronic medical records, including an interface for search criteria input, a search engine that communicates with a crawler to search medical data, and a formatter to de-identify patient data, ensuring HIPAA compliance and enabling re-identification at the local user level.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If free text searching is implemented in electronic medical records, then data retrieval capability is improved, but system complexity increases

Engineering Contradiction:
Improvedata retrieval capabilityVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a search crawler as an intermediary component that operates between the search engine and the electronic medical record databases. The crawler pre-processes and indexes medical record data, transforming unstructured clinical text into searchable formats. This intermediary layer handles the complexity of data retrieval, allowing users to perform simple free text searches without directly interacting with the underlying system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If patient data is de-identified for privacy compliance, then patient privacy is protected, but data utility for analysis is reduced

Engineering Contradiction:
Improvepatient privacy protectionVSAvoiddata utility
Core Design Contradiction:
Object-affected harmful factorsVSLoss of information

Solution Approach 1:

The patent implements local quality by applying different levels of data masking to different portions of the medical record. Sensitive personally identifiable information (PII) such as names and social security numbers are completely redacted, while clinically relevant data such as diagnoses, treatments, and outcomes are preserved in full detail. This selective approach maintains patient privacy while preserving the analytical utility of clinical data for research and cohort analysis.

Inventive Principle:
Principle #3Local quality

3Loss of information

If comprehensive search of medical records is performed, then information completeness is improved, but search time increases

Engineering Contradiction:
Improveinformation completenessVSAvoidsearch time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent implements preliminary action through the search crawler that continuously pre-processes and indexes medical record data in the background before search queries are executed. Clinical documents are parsed, structured, and stored in optimized search indexes ahead of time. When a user performs a search, the system queries these pre-indexed structures rather than scanning raw medical records, dramatically reducing search time while maintaining comprehensive information retrieval capability.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS8037052B2Systems and methods for free text searching of electronic medical record data
Publication Date: 2011.10.11 GE PRECISION HEALTHCARE LLC
  • US8037052B2 patent drawing
  • US8037052B2 patent drawing
  • US8037052B2 patent drawing

AI summary

Certain embodiments of the present invention provide systems and methods for free text searching of electronic medical records. Certain embodiments provide a system including an interface configured to accept search criteria and display search results and a search engine accepting a free text search query from the interface. The free text search query is based on search criteria entered via the interface. The search engine communicates with a search crawler, which searches electronic medical record data based on the free text search query and provides search results. In certain embodiments, the system may de-identify patient/physician data from the search results. Certain embodiments provide a system for retrieving EMR search results. The system includes an interface configured to accept search criteria and display search results, a database interface adapter for interfacing with an electronic medical record database to transmit and receive data and a formatter for formatting search results.