Lung Cancer test (RuO)
Qlucore Insights Lung Cancer test (model) uses molecular data to define subclasses as well as to pinpoint the tissue of origin for lung metastases. Built on AI-based machine learning and transcriptomics, the test opens new ways for fast, cost efficient and objective sample analysis utilizing both gene expression data and gene fusions. Built on standard lab workflows, the program supports analysis of lung lesions from fixed and embedded tissue specimens.
Contact us to find out more
Current Routine Diagnostics of Lung cancer
A typical patient presents symptoms like a persistent cough or chest pain, often with a history of smoking. Standard workflow begins with medical history, physical exam, and imaging tests like X-rays and CT scans. Common tests (not an exhaustive list) involve:
Imaging: CT, MRI, PET scans. Biopsies: Needle biopsy, bronchoscopy. Histopathology and molecular tests.
Stages: Ranges from stage 1 (localized) to stage 4 (spread to other parts).
Challenges:
• Histopathology requires highly skilled staff to analyze data
• There is a subjective component in image analysis
• Relying on small and fixed assays is not sustainable
• Identifying the origin of metastases to the lung
• High costs due to specialized personnel/several tests
RNA-seq - the emerging clinical diagnostic solution
RNA sequencing plays a crucial role in overcoming present challenges in lung cancer diagnostics by measuring two key parameters: chimeric gene fusions and gene expression levels. These measurements help in accurately classifying cancer subtypes and determining the cancer’s origin.
RNA sequencing is set to become widely used in clinical settings by:
• The ability to detect key genetic alterations
• By lowering sequencing costs
• By ease of automation
• Enabling same lab workflow across many different diseases
Performance (RoU)
The Qlucore Insights (RoU) classifier model for lung cancer allows gene expression-based subtype classification of the groups listed below. The cover is broad, with 19 subtypes included. In addition to this, its inbuilt gene fusion analysis supports the identification of druggable as well as novel gene fusions.
Performance is excellent and as an example the accuracy is described in this POSTER. Reach out for more information.
Example of a visualization of classification in a PCA plot, using Qlucore Insights.
Report - classification of Lung Cancer
View a draft example of how a report might look. Note that the example report is generated with Qlucore Insights (Research Use Only).
White Paper - Automated Molecular Subclassification of Lung Lesions
Including Cancer Type and Tissue of Origin for Metastases. READ WHITE PAPER
Poster - presented at ESMO Congress 2024
This study demonstrates that Qlucore Insights can analyze lung tumors and lung diseases with high accuracy.