Deep Learning Improves Pancreatic Cancer Diagnosis Using RNA-Based Variants

For optimal pancreatic cancer treatment, early and accurate diagnosis is vital. Blood-derived biomarkers genetic predispositions can contribute to diagnosis, but they often have limited accuracy or applicability. Here, we seek exploit the synergy between them by combining biomarker CA19-9 with RNA-based variants. We use deep sequencing learning improve differentiating chronic pancreatitis. obtained samples of nucleated cells found in peripheral blood from 268 patients suffering resectable, non-resectable cancer, sequenced RNA high coverage millions The high-quality variants served as input together values models. Our model achieved an area under curve (AUC) 96% resectable pancreatitis using a test cohort. Moreover, identified estimate survival cancer. show that transcriptome harbours variants, which substantially noninvasive clinical diagnosis.