Chronology-Aware Graph Visual Analytics for Healthcare Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing visual analytics tools for healthcare are limited in their ability to discover potential causal or risk factor correlations between clinical data points across large patient cohorts, particularly due to the large number of medical features and the complexity of electronic health records (EHR) data.

Innovation Solution

A scalable graph-based visual analytics pipeline that generates chronology-aware graph data structures from EHR data, allowing for efficient retrieval of patient care pathways and interactive pattern discovery, thereby presenting query results across time as graph visualization diagrams.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If traditional visual analytics tools are used for healthcare data, then basic data retrieval is possible, but the ability to discover causal correlations and patterns in large datasets is limited

Engineering Contradiction:

Improvepattern discovery capabilityVSAvoidanalysis efficiency

Core Design Contradiction:

Difficulty of detecting and measuringVSProductivity

Solution Approach 1:

The system segments the analysis process into distinct components: graph generation from EHR data, chronology-aware query processing, pattern discovery algorithms, and visualization. This segmentation allows each component to be optimized independently, enabling efficient pattern discovery in large healthcare datasets while maintaining high analysis productivity

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces chronology-aware graph data structures as an intermediary representation between raw EHR data and pattern discovery algorithms. This intermediary structure efficiently captures temporal relationships and enables rapid pattern detection, resolving the contradiction between difficult pattern detection and low analysis efficiency

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If the number of medical features is increased to capture more clinical information, then measurement precision improves, but the complexity of data processing increases

Engineering Contradiction:

Improveclinical data representation accuracyVSAvoiddata processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system transforms clinical data from traditional tabular formats into chronology-aware graph data structures, adding a temporal dimension to the data representation. This dimensional transformation allows precise capture of clinical features with their temporal relationships while simplifying the processing complexity through graph-based operations

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent changes the structural parameters of data representation from flat tables to hierarchical graphs with temporal awareness. This parameter change enables the system to handle increased numbers of medical features efficiently, maintaining measurement precision while reducing processing complexity through graph optimization techniques

Inventive Principle:

Principle #35Parameter changes

3Reliability

If comprehensive EHR data is analyzed to improve healthcare decision-making, then the quality of insights improves, but the time required for analysis increases

Engineering Contradiction:

Improvehealthcare decision qualityVSAvoidanalysis time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing EHR data into chronology-aware graph structures that capture temporal relationships. This preliminary organization of comprehensive data enables rapid pattern discovery and analysis, improving healthcare decision quality without incurring excessive analysis time delays

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical data processing approaches with graph-based computational methods. This substitution enables efficient traversal and analysis of comprehensive EHR data, maintaining high reliability of insights while significantly reducing the time required for analysis through optimized graph algorithms

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12314278B2Scalable visual analytics pipeline for large datasets

Publication Date: 2025.05.27 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Mechanisms are provided to implement a visual analytics pipeline. The mechanisms generate, from an input database of records, a chronology-aware graph data structure of a plurality of records based features specified in an ontology data structure. The chronology-aware graph data structure has vertices representing one or more of events or records based features corresponding to events, and edges representing chronological relationships between events. The mechanisms execute a chronology-aware graph query on the chronology-aware graph data structure to generate a filtered set of vertices and corresponding features corresponding to criteria of the chronology-aware graph query. The mechanisms execute a pattern discovery operation on the filtered set of vertices and corresponding features to identify a subset of vertices and corresponding features that correspond to a relatively higher frequency set of patterns of event paths, and generate a visual analytics graphical representation for the subset of vertices and corresponding features.