De-identified Location Analytics for Hospital Floor Plans
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for tracking patient locations in hospitals are time-consuming, costly, and challenging due to the need for manual document matching and the complexity of handling protected health information, with existing systems being poorly equipped for graphical-based investigations and data re-identification.
Innovation Solution
A system and method for performing de-identified location analytics that removes identifiable data characteristics from hospital floor plans, using a look-up table to enable automatic and standardized location extraction, allowing for epidemiological analysis and easier mapping of locations to specific features, while maintaining patient privacy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual document matching is used to track patient locations, then location tracking can be performed, but the process becomes time-consuming and costly
Solution Approach 1:
The patent replaces manual mechanical document matching with automated image processing and machine learning systems. The system automatically processes electronic health record images, extracts patient location data, and matches it with floor plan images using computer vision algorithms, eliminating the need for manual review and significantly reducing processing time while maintaining accuracy
Solution Approach 2:
The system enables self-service location tracking by automatically extracting and processing patient location information from electronic health records without requiring manual intervention. The automated system performs document matching, location extraction, and data aggregation independently, allowing the system to serve itself rather than requiring continuous human oversight for routine tracking tasks
2Object-affected harmful factors
If patient location data is de-identified and encrypted for off-site analysis, then patient privacy is protected, but data re-identification becomes difficult
Solution Approach 1:
The patent introduces a de-identification layer as an intermediary between the raw patient location data and the analysis system. This layer removes personally identifiable information while preserving spatial and temporal patterns through aggregation and anonymization techniques, allowing analysis to proceed without exposing individual patient identities. The system acts as a mediator that protects privacy while maintaining analytical value
Solution Approach 2:
The system segments patient location data into aggregated statistical representations rather than processing individual records. By dividing the data into aggregated patterns, time-series distributions, and spatial heat maps, the system maintains privacy through aggregation while preserving the ability to re-identify patterns and trends in patient movement without exposing individual identifiable information
3Adaptability or versatility
If existing clinical interoperable systems are used for patient data transmission, then some data exchange is enabled, but they are not equipped for graphical-based investigations and room coordinate mapping
Solution Approach 1:
The patent creates a universal platform that handles multiple functions: it processes electronic health record data, extracts location information, maps coordinates to floor plans, performs de-identification, and enables graphical visualizations all within a single integrated system. This multi-functional approach replaces the need for separate specialized systems and makes the platform adaptable to various analytical and operational requirements
Solution Approach 2:
The system transforms one-dimensional data transmission capabilities into multi-dimensional analytical capabilities by adding spatial mapping, temporal aggregation, and graphical visualization dimensions. It maps patient location data onto two-dimensional floor plan representations and three-dimensional time-space matrices, enabling graphical-based investigations that were not possible with traditional linear data exchange protocols
4Measurement precision
If room coordinates are mapped using floor plans, then location visualization is improved, but the process becomes manual and time-consuming
Solution Approach 1:
The patent replaces manual coordinate mapping with automated computer vision and machine learning systems. The system automatically extracts room boundaries and coordinate information from floor plan images using image processing algorithms, then automatically associates these with patient location data, eliminating the need for manual measurement and mapping while maintaining high precision
Solution Approach 2:
The system performs preliminary extraction and processing of floor plan data before it is needed for analysis. By pre-processing floor plans to extract room definitions, coordinate systems, and spatial relationships in advance, the system eliminates the need for manual mapping during actual analysis, significantly reducing the time required for location visualization and patient tracking
Data Source
AI summary
A method for performing de-identified location analytics is provided. The method may include generating a de-identified image by removing the identifiable characteristics from a building arrangement image; generating a binary threshold image by processing the de-identified image using a threshold process; generating a segmentation image by removing any segmentation objects of the binary threshold image with an area less than a defined pixel area; extracting room definitions from the segmentation image, wherein each room definition comprises a series of pixels corresponding to an outline of one of the rooms of the building arrangement image; generating a pixilation table, the pixilation table comprising room definition entries corresponding to the room definitions of the segmentation image, wherein each pixel of the segmentation image is mapped to the room definition entry corresponding to the room definition of the outline surrounding the pixel; and assigning a label to each room definition entry.