Relational Biomarkers for Disease Classification and Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional biomarkers face challenges due to variability and lack of specificity, making it difficult to establish clear cutoff values, affecting sensitivity and specificity in disease detection and prediction, especially when influenced by factors like age, gender, and genetic background.
Innovation Solution
The use of relational biomarkers, which are mathematical functions representing the covarying behavior of two or more conventional biomarkers, to distinguish health conditions by modeling relationships among patterns of biological materials such as DNA methylation, RNA transcription, and protein abundance, allowing for more accurate classification and prediction of diseases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional biomarkers are used for disease detection, then the detection process is simple and cost-effective, but the sensitivity and specificity are reduced due to variability and lack of specificity
Solution Approach 1:
The patent combines multiple conventional biomarkers into a single composite biomarker that integrates information from several individual markers. This merging approach improves disease detection accuracy by capturing more comprehensive disease-related information while reducing the complexity of analyzing multiple separate markers independently.
Solution Approach 2:
The invention creates a composite biomarker that functions similarly to composite materials - combining multiple individual biomarker components into a unified structure with enhanced performance characteristics. This composite biomarker exhibits improved sensitivity and specificity that exceed the capabilities of individual constituent markers.
2Measurement precision
If multiple conventional biomarkers are analyzed to improve diagnostic accuracy, then the classification precision improves, but the testing complexity and cost increase
Solution Approach 1:
The patent merges multiple biomarker measurements into a single composite indicator that maintains the diagnostic information of all constituent markers. This approach achieves high classification accuracy equivalent to analyzing multiple markers separately, while simplifying the testing process into a single integrated assay.
Data Source
AI summary
Methods for modeling system behavior and discovering relational biomarkers that distinguish a disease/disorder sample from a control sample. The methods generally include modeling a mathematical relationship between a pattern of a first biological material and the pattern(s) on one or more other biological samples for samples from each of a plurality of subjects having the disease/disorder to determine a case relational biomarker, and for samples from each of a plurality of subjects absent the disease/disorder to determine a control or noncase relational biomarker. These case noncase biomarkers, or discriminators, may be used to classify an unknown sample. Ensembles of discriminators may be generated by modeling the relationships among different combinations of biological materials. Moreover, ensembles of discriminators for various diseases or disorders, i.e., multiclass classifiers, may be generated by modeling the relationships among material from subjects who have or will develop additional diseases or disorders.