Rapid and accurate assessment of EGFR mutations in lung adenocarcinoma is critical for the management of NSCLC patients.
PCR-based assays provide rapid results but with reduced accuracy compared with next-generation sequencing and can exhaust the increasingly valuable small amount of biopsy tissue available for predictive biomarkers. Computational biomarkers
Leveraging modern foundation models may offer alternative solutions. 

In this episode of Precision Pathology Podcast (P3), the host discusses with Dr. Chad Vanderbilt from the Department of Pathology and Laboratory Medicine at MSKCC in NY, his team’s recent study, published in Nature Medicine, using a large international clinical dataset of digital lung adenocarcinoma slides to develop a computational EGFR biomarker. The artificial-intelligence-assisted workflow has the potential to reduce the number of rapid molecular tests needed by up to 43%.