Medical Configuration Anomaly Detection Using Frequent Pattern Mining

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Medical imaging devices often experience malfunctions due to complex configuration issues, making it difficult for remote service engineers to identify the root cause of problems, leading to significant time and cost expenditures in diagnosing and resolving issues.

Innovation Solution

A method involving a non-transitory computer-readable medium that stores instructions for extracting a fleet configuration transactions database from device log data, constructing a configuration outlier detector, and generating alarms or reports for suspect configuration transactions, thereby reducing the time and uncertainty in identifying root causes of device malfunctions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual investigation of device configuration data is performed to identify root cause of malfunction, then diagnostic accuracy is improved, but time consumption and cost increase significantly

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

An automated anomaly detection system acts as an intermediary between the complex configuration data and the service engineer. The system processes configuration transactions, identifies anomalies using pattern matching and statistical analysis, and presents filtered results to engineers, eliminating manual investigation of hundreds of parameter combinations while maintaining diagnostic accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The manual mechanical process of investigating configuration parameters is replaced by an automated computational system. The system uses algorithms to automatically analyze configuration transactions, detect anomalies, and generate diagnostic reports, substituting human manual analysis with automated information processing while reducing time consumption

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If comprehensive configuration analysis is performed on all parameter combinations, then root cause identification accuracy is improved, but system complexity and computational resources increase

Engineering Contradiction:

Improveroot cause identification accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system extracts only the relevant and anomalous configuration parameters from the complete configuration space. By identifying and isolating anomalies in configuration transactions rather than analyzing all possible parameter combinations, the system reduces computational complexity while maintaining root cause identification accuracy

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The configuration analysis is segmented into manageable components: configuration transaction extraction, anomaly detection, pattern recognition, and report generation. This segmentation allows the system to handle complex configuration data in discrete steps, reducing overall system complexity while maintaining comprehensive analysis capability

Inventive Principle:

Principle #1Segmentation

3Reliability

If device configuration changes are tracked and monitored, then device reliability is improved, but data processing requirements and storage needs increase

Engineering Contradiction:

Improvedevice reliabilityVSAvoiddata volume

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

Configuration transactions are extracted and stored in a structured database format in advance, before anomaly detection is performed. This preliminary organization of data into standardized fields (parameter identifiers, values, timestamps) enables efficient querying and analysis while reducing the need for repeated data processing and storage of redundant information

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12176098B2Configuration anomaly detection in medical system configurations using frequent pattern mining

Publication Date: 2024.12.24 KONINKLIJKE PHILIPS NV

AI summary

A non-transitory computer readable medium (107, 127) stores instructions readable and executable by at least one electronic processor (101, 113) to perform a suspect device configuration detection method (200). The method includes: extracting a fleet configuration transactions database (130) of device configuration transactions (132) from device log data (108) and/or system configuration files (112) of a fleet of devices (120) wherein each configuration transaction includes one or more support data fields (134), a parameter identifier (136), and its value (138); constructing a configuration outlier detector (140) to identify outlier configuration transactions in the fleet configuration transactions database; detecting one or more suspect configuration transactions (150) by applying the configuration outlier detector to configuration transactions extracted from one or more devices of interest; and generating at least one of an alarm (160) and a report (170) when the one or more suspect configuration transactions are detected.