Genomic Variant Classification System for Clinical Trial Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current clinical sequencing workflows face challenges in efficiently interpreting DNA variants due to the complexity of increasing test volumes, large datasets, and the need for timely integration of updated knowledge on genomic variants, which can lead to delayed patient treatment and inefficiencies in clinical trial patient enrollment.
Innovation Solution
A knowledge-based system that curates genomic variants using expert-reviewed literature and ontological organization, enabling automated classification and scalable decision support for clinical geneticists, while also facilitating patient enrollment in clinical trials by stratifying patients based on genetic criteria.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual literature review and variant interpretation is performed by geneticists, then accuracy of variant classification is improved, but time delay increases and productivity decreases
Solution Approach 1:
The patent introduces an automated informatics system as an intermediary between sequence data generation and geneticist review. This system performs initial variant filtering, classification, and literature curation, presenting only relevant variants to geneticists for final interpretation. This mediator handles the time-consuming manual tasks while preserving expert oversight for accuracy-critical decisions.
Solution Approach 2:
The system performs preliminary actions by automatically curating literature, classifying variants, and preparing interpretation reports before geneticist review. This advance processing reduces the time geneticists need to spend on each case while maintaining classification accuracy through their final expert validation.
2Adaptability or versatility
If test complexity and number of genes assayed increase, then diagnostic capability is improved, but data interpretation difficulty and time required increase
Solution Approach 1:
The patent segments the complex interpretation task into distinct components: automated literature curation, variant filtering by relevance criteria, classification by pathogenicity, and prioritization by clinical significance. This segmentation allows the system to handle large-scale genomic data from hundreds or thousands of genes while presenting organized, manageable results to geneticists.
Solution Approach 2:
The system replaces manual mechanical review of all variants with automated computational analysis. Algorithms automatically curate literature, filter variants based on multiple criteria, and classify pathogenicity, substituting human effort for computational processes that can efficiently handle the complexity of large-scale genomic testing.
3Productivity
If automated informatics systems are used to interpret variants, then productivity increases and time delay reduces, but accuracy and reliability may decrease
Solution Approach 1:
The automated system serves as an intermediary that prepares and filters variant information, but geneticists remain the final decision-makers for clinical interpretation. This hybrid approach maintains human expertise and judgment in the reliability-critical final step while using automation for productivity-enhancing preliminary tasks.
Solution Approach 2:
The system incorporates feedback mechanisms where geneticist interpretations and corrections are used to refine and improve the automated classification algorithms over time. This feedback loop allows the system to learn from expert judgments, progressively improving both accuracy and reliability while maintaining high productivity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed herein are system, method, and computer program product embodiments for aiding in the interpretation of variants observed in clinical sequencing data. An embodiment operates by receiving clinical trial enrollment criteria from a user, including but not limited to genetic targeting criteria; searching a knowledge base of patient test information received from a plurality of independent entities for patients that match the clinical trial enrollment criteria; and providing to the user search results for consented patients that match the clinical trial enrollment criteria.