Deep Learning Improves Pancreatic Cancer Diagnosis Using RNA-Based Variants

Simple Summary Blood samples from patients with pancreatic diseases have been analysed to identify predictive RNA-based variants. These variants are not subject to changes in the environment, as is the case for gene expression or metabolic. The variants served together with CA19-9 as input to deep learning for a cohort of 268 patients with pancreatic diseases. Of these patients, 183 patients had pancreatic cancer and 85 from chronic pancreatitis. Among others, we were able to define a set of variants, which were able to differentiate resected pancreatic cancer from chronic pancreatitis with an area under the curve of (AUC) of 96%. Due to the ease of our approach and the wide availability of the used method, it will have a broad impact on the clinical routine. Suspicious patients are only subjected to a blood draw of 2.5 mL blood, and the specimen can then be sent at room temperature to a specialised laboratory. For optimal pancreatic cancer treatment, early and accurate diagnosis is vital. Blood-derived biomarkers and genetic predispositions can contribute to early diagnosis, but they often have limited accuracy or applicability. Here, we seek to exploit the synergy between them by combining the biomarker CA19-9 with RNA-based variants. We use deep sequencing and deep learning to improve differentiating pancreatic cancer and chronic pancreatitis. We obtained samples of nucleated cells found in peripheral blood from 268 patients suffering from resectable, non-resectable pancreatic cancer, and chronic pancreatitis. We sequenced RNA with high coverage and obtained millions of variants. The high-quality variants served as input together with CA19-9 values to deep learning models. Our model achieved an area under the curve (AUC) of 96% in differentiating resectable cancer from pancreatitis using a test cohort. Moreover, we identified variants to estimate survival in resectable cancer. We show that the blood transcriptome harbours variants, which can substantially improve noninvasive clinical diagnosis.