Over the last 20 years, molecular analysis of cancers has offered clinicians a growing toolbox for understanding and treating cancer. Next-generation sequencing (NGS) of tumors identifies alterations that can predict sensitivity and resistance to targeted therapies as well as ascribe prognostic and diagnostic significance. As sequencing power and research into cancer-causing mutations have grown, the number of genes on panels has increased.
In 2022, typical panels can detect hundreds of thousands of mutations across several hundred cancer-related genes. In some cases, laboratories perform exome analysis to detect mutations across all ~22,000 genes in the genome. As a result, the burden of variant interpretation has also expanded exponentially.
Numerous clinical decision support (CDS) software and knowledgebases have been developed to assist variant scientists and laboratory directors with the task of variant classification. These private and commercially available systems utilize varying degrees of software automation and manually curated literature to provide variant assessment and therapy matching for clinicians. The body of literature that must be accessed to deliver accurate variant interpretation is vast. As a result, there is debate in the field as to the most accurate and efficient approach.
CDS software leveraging artificial intelligence or natural language processing can index enormous volumes of literature but lack precision in correctly representing complex genomic interactions in association with clinical outcomes. In this context, human curation remains the gold standard. A community crowdsourcing approach allows contribution from many different experts and can help to build a larger pool of knowledge in the context of limited resources.
However, significant standardization efforts are required to ensure a consistent level of accuracy and reliability. In contrast to machine curation, human professional expert curation is resource intensive but can provide consistent and accurate interpretation.
QIAGEN Clinical Insight (QCI) Interpret for Oncology is CDS software that enables pathologists to identify biologically and clinically relevant oncology-related variants. The software draws on a large knowledgebase of curated information, coupled with an expert interpretation service. The content core of QCI Interpret, the QIAGEN Knowledge Base is populated through a combined approach utilizing human and machine curation. Known as augmented molecular intelligence (AMI), this approach combines artificial intelligence and human expertise to advance and accelerate confident clinical decision-making.
A key differentiator of QCI Interpret, the application of AMI leverages artificial intelligence and machine
learning to efficiently identify, extract, and align evidence from scientific literature, guidelines, clinical trials, and drug labels in over 40 public and proprietary databases in the QIAGEN Knowledge Base. This evidence is then reviewed by over 200 PhD- and MDlevel scientists to ensure accuracy, consistency, and
relevance. The evidence is then stored in computable units according to well-defined protocols.
QCI Interpret utilizes the structured content of the QIAGEN Knowledge Base to match appropriate variant- and disease-specific content and executes rules to classify variant pathogenicity and actionability based on the ACMG (1) and AMP (2) guidelines. The computed classification and supporting data are available for review in a user interface. And the user has the ability to review all the data and approve or revise the classification.
QCI Interpret also incorporates an additional level of human expert interpretation. Users can submit variants to the expert interpretation service and oncologists review the clinical content.
The expert interpretation available in QCI Interpret utilizes a contrasting analysis approach; the scientists execute a topic-based analysis, searching for and extracting information on each variant and formulating an assessment based on the synthesis of the evidence. Then, the usesr receives report-ready text with references to incorporate into the final report. Users can easily view the expert classification and interpretation alongside the computed classification, and the user can approve or revise the classification for reporting.
Multiple studies compare variant classification across institutions (3-5). However, these studies lack a “gold standard” set of variant interpretations that could stand as a benchmark for evaluation.
In order to assess the utility and accuracy of QCI Interpret, QIAGEN engaged GenQA, an external quality assessment organization. GenQA designed and executed a study published in the Journal of Molecular Pathology that compared the use of QCI Interpret to internal laboratory methods. The study recruited eight independent laboratories to utilize QCI Interpret for variant interpretation. Variant classification results were compared and an expert panel resolved all conflicts. The results suggest QCI Interpret is a reliable CDS tool that can help laboratories streamline and improve interpretation practices.
Learn more about the study, including how QCI Interpret performed against the 8 laboratories, sources of discrepancies, and methods of variant analysis.
November 1-5, 2022 in Phoenix, Arizona
This year at the Association for Molecular Pathology (AMP) 2022 Annual Meeting, QIAGEN will be showcasing our integrated cancer NGS workflow powered by augmented molecular intelligence (AMI) at Booth #906. The combination of artificial intelligence and human expertise, AMI is an approach unique to QIAGEN. AMI uses machines to rapidly index millions of articles. Then, human curators review and certify the accuracy, relevancy, and consistency of the information pulled.
Learn more and schedule a 1:1 demo here.
