Abnormality Score Vector for Unknown Drug Side Effect Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for detecting drug side effects struggle to identify latent abnormalities not defined by pre-determined rules and fail to detect unknown side effects in a timely manner, leading to delayed detection in drug safety management.

Innovation Solution

A device and method that calculate abnormality scores from medical data, integrate them into vectors, and use predetermined rules to detect side effects, allowing for the identification of unknown side effects by determining the likelihood of side effects based on these vectors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If pre-determined rules are used to detect side effects, then detection speed is improved, but unknown side effects cannot be detected

Engineering Contradiction:

Improvedetection speedVSAvoidability to detect unknown side effects

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary analysis by calculating abnormality scores for multiple medical data items before final side effect detection. This preliminary scoring integrates diverse data characteristics and prepares the system to detect both known and unknown side effects by establishing baseline abnormality levels across different data types.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the detection parameter from fixed rule-based thresholds to dynamic abnormality scores that adapt to different data characteristics. By calculating scores based on specificity of medical data and integrating them into vectors, the system can detect side effects regardless of whether they match pre-determined patterns.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If comprehensive medical data analysis is performed to detect unknown side effects, then detection accuracy is improved, but processing time increases

Engineering Contradiction:

Improveside effect detection accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system segments the comprehensive analysis into distinct processing stages: calculating abnormality scores for individual medical data items, integrating these scores into vectors, and then detecting side effects based on the integrated vectors. This segmentation allows parallel processing of multiple data items while maintaining comprehensive analysis accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system replaces traditional mechanical rule-based detection with an information-processing approach using abnormality scores and vectors. This substitution enables efficient computation of comprehensive data characteristics without the time-consuming nature of exhaustive rule checking.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If multiple abnormality scores are integrated into vectors, then side effect detection capability is improved, but system complexity increases

Engineering Contradiction:

Improveside effect detection capabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The abnormality score vector serves as a universal data structure that can represent multiple medical data characteristics simultaneously. This multi-functional vector approach consolidates diverse abnormality scores into a single integrated representation, simplifying the detection process while maintaining comprehensive analysis capability.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system creates composite information structures by integrating multiple abnormality scores into unified vectors. This composite approach combines diverse data characteristics (specificity, frequency, severity) into a single integrated representation that enhances detection reliability without requiring separate processing systems for each data type.

Inventive Principle:

Principle #40Composite materials

Data Source

PatentUS9269118B2Device, method, and program for extracting abnormal event from medical information

Publication Date: 2016.02.23 NEC CORP

AI summary

An abnormality score calculating means calculates abnormality scores which are information indicating abnormality of medical data, based on specificity of the medical data. An abnormality score vector generating means creates at least one or more abnormality score vectors which are information obtained by integrating the abnormality scores. Further, a side effect detecting means which decides a likelihood of a side effect indicated by the abnormality score vector, based on a predetermined rule, and detects an abnormality score vector the likelihood of which is set in advance and which satisfies conditions as information indicating the side effect.