Adaptive Bayesian Biomarker Reference Ranges for Plasma Volume Variation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biomarker detection methods struggle with between-subject variations, leading to inaccurate diagnoses and treatments, as they rely on general population reference ranges that do not account for individual genetic and physiological differences.
Innovation Solution
A method using adaptive Bayesian models to derive individual reference ranges from biomarker data, allowing for personalized biomarker signal enhancement by measuring biomarker values, applying Bayesian inference to adapt to new information, and comparing measured values to individual Z scores and ranges, which indicates biological or physiological conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If general population reference ranges are used for biomarker detection, then the method is simple and broadly applicable, but between-subject variations lead to reduced diagnostic accuracy and increased false positives
Solution Approach 1:
The patent segments the general population into distinct subgroups based on genetic characteristics (e.g., ABO blood groups, HLA types). By dividing the population into genetically-defined segments, reference ranges can be tailored to each segment, reducing between-subject variations within each group and improving diagnostic accuracy without requiring fully individualized approaches.
Solution Approach 2:
The patent performs preliminary genetic characterization of the population to establish genotype-specific reference ranges before actual biomarker detection. By pre-defining reference ranges for different genetic subgroups based on prior knowledge of genetic-fenotypic relationships, the system eliminates the need for complex real-time individualization during diagnostic testing.
2Measurement precision
If individualized reference ranges are derived for each subject, then diagnostic accuracy improves, but the complexity of data collection and analysis increases significantly
Solution Approach 1:
The patent uses readily available, inexpensive genetic markers (such as ABO blood groups and common HLA types) that can be determined from routine blood samples. These genetic characteristics serve as proxies for complex individual physiological variations, providing sufficient individualization at minimal cost and complexity while avoiding the need for comprehensive genomic sequencing or extensive phenotypic characterization for each subject.
3Measurement precision
If genetic information is used to stratify biomarker reference ranges, then between-subject variations are reduced, but additional genetic testing and data processing are required
Solution Approach 1:
The patent uses genetic information for multiple purposes: establishing reference ranges, explaining phenotypic variations, and guiding clinical decision-making. By integrating genetic data into a unified framework that serves multiple diagnostic functions, the system maximizes the utility of genetic information while minimizing redundant testing and analysis.
Solution Approach 2:
The patent changes the parameter basis for reference ranges from general population statistics to genotype-specific parameters. By shifting from universal reference intervals to genetically-stratified reference ranges, the system captures biological variations that would otherwise appear as noise, thereby improving reference range specificity without requiring complex individualized modeling for each subject.
Data Source
AI summary
The present invention relates to a method of enhancing the detection of a signal from biomarker data in a subject or group of subjects.