Non-Invasive Liver Diagnostic Index Reliability Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current non-invasive diagnostic tests for liver diseases, such as those using Fibroscan, suffer from inaccuracies leading to patient misclassifications due to abnormal, inconsistent, or non-homogeneous data, which affects the reliability and accuracy of fibrosis staging.
Innovation Solution
A method that collects an Initial Index from non-invasive tests like FibroMeter, analyzes its reliability by identifying abnormal or inconsistent data, and generates Event Alerts to replace or adjust the data, resulting in a Final Index that improves diagnostic accuracy by suppressing or substituting problematic data with mean values to enhance the Dispersion Index, thereby improving test reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If non-invasive diagnostic tests are used to assess liver fibrosis, then patient comfort and cost are improved, but diagnostic accuracy and reliability deteriorate due to false-positive or false-negative results
Solution Approach 1:
The patent implements a feedback mechanism where the initial diagnostic index is evaluated for reliability, and if unreliable, the system automatically requests additional measurements or alternative tests. This closed-loop feedback system continuously improves diagnostic accuracy by learning from initial results and adjusting the diagnostic pathway accordingly, resolving the contradiction between ease of operation and reliability.
Solution Approach 2:
The patent performs preliminary reliability assessment of the initial index before final diagnosis is made. By evaluating data quality, consistency, and homogeneity in advance, the system can identify potentially unreliable results early and trigger appropriate corrective actions, preventing false diagnoses while maintaining the non-invasive approach.
2Device complexity
If non-invasive diagnostic tests are used to assess liver fibrosis, then invasiveness and cost are reduced, but measurement accuracy deteriorates due to errors from markers, practitioners, or patients
Solution Approach 1:
The patent monitors and evaluates multiple parameters including the dispersion index, reliability predictors, and data consistency metrics. By changing and comparing these parameters, the system can detect measurement errors and distinguish between true diagnostic results and artifacts caused by measurement variability, thereby improving measurement precision without increasing invasiveness.
Solution Approach 2:
The patent introduces an intermediary reliability evaluation layer between the initial measurement and the final diagnosis. This intermediary system assesses data quality using multiple criteria (dispersion index, consistency, homogeneity) and acts as a mediator to filter out erroneous measurements before they affect the final diagnostic conclusion, thus improving measurement precision while maintaining device simplicity.
3Reliability
If reliability analysis is performed on initial index data, then diagnostic accuracy is improved, but computational complexity and time increase
Solution Approach 1:
The patent segments the reliability analysis into distinct, modular components: dispersion index calculation, consistency evaluation, homogeneity assessment, and reliability predictor analysis. Each component is independently calculated and evaluated, allowing the system to process reliability information in manageable steps without overwhelming computational complexity, thus improving diagnostic accuracy while controlling system complexity.
4Reliability
If multiple reliability criteria are evaluated (dispersion index, consistency, homogeneity), then test reliability is improved, but processing time and complexity increase
Solution Approach 1:
The patent performs preliminary calculations of reliability metrics (dispersion index, consistency, homogeneity) during the initial data collection phase rather than as separate post-processing steps. By preparing these reliability indicators in advance alongside the primary measurements, the system minimizes additional processing time while maintaining comprehensive reliability evaluation.
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
Computerised system, especially in the form of an expert system, for evaluating combined diagnostic scores for liver disease and increasing accuracy of diagnosis using non-parametric sensitivity analysis based on analysis of variance and ROC curves to eliminate unreliable parameters from the model.