A multivariate cell-based liquid biopsy for lung nodule risk stratification: Analytical validation and early clinical...

Area of Science:

• Biotechnology
• Molecular Diagnostics
• Oncology

Background:

• The Indicator Cell Assay Platform (iCAP) utilizes living cells as biosensors for blood-based diagnostics.
• It integrates and amplifies weak disease signals from patient serum for analysis.
• Machine learning tools analyze transcriptomic responses to develop disease classifiers.

Purpose of the Study:

• To develop and evaluate a lung cancer-specific iCAP (LC-iCAP) as a rule-out test for indeterminate pulmonary nodules.
• To assess the assay's analytical reproducibility and biological relevance.
• To estimate the clinical performance of LC-iCAP in a prospective-specimen-collection, retrospective-blinded-evaluation (PRoBE) study.

Main Methods:

• Assay parameterization and analytical reproducibility testing were performed.
• A fixed 85-gene feature set was selected for future clinical validation.
• Classifier variants were trained and evaluated using nested cross-validation and temporal blind validation on 176 samples.

Main Results:

• The LC-iCAP assay demonstrated excellent reproducibility across conditions and cell lineages.
• Transcriptomic signals were enriched for hypoxia-responsive genes, aligning with lung cancer biology.
• Two models showed discriminative ability in blind validation (AUC=0.64); a combined model with CT imaging achieved 90% sensitivity and 95% NPV.

Conclusions:

• The study establishes the analytical reproducibility and biological relevance of LC-iCAP.
• Preliminary results support the assay's potential utility in lung nodule management.
• LC-iCAP represents a new paradigm for scalable, cost-effective cell-based biosensor assays for liquid biopsies and precision medicine.