Pancreatic cancer, which is notoriously difficult to catch early, can now be detected early with a simple blood test, but powered by artificial intelligence (AI). The AI-based test analyzes metabolic fingerprints in a blood sample and spots pancreatic cancer at its earliest stages with up to 94 percent accuracy. The study published in the journal Nature Communications showed that the diagnostic tool called PanMETAI can be a non-invasive and cost-effective screening tool to save lives lost due to pancreatic cancer -- one of the deadliest forms of cancer worldwide, with only a 13 percent five-year survival rate. The tool combines with nuclear magnetic resonance (NMR) metabolomics to identify pancreatic cancer with remarkable accuracy. NMR is a method that captures the unique chemical fingerprint of hundreds of metabolites in a patient's blood. "By combining the power of AI with the rich metabolic information captured by NMR spectroscopy, we have created a tool that can detect pancreatic cancer at its earliest and most treatable stages. Our goal is to bring this technology to clinical practice so that more patients can benefit from timely diagnosis and treatment," said Yu-Ting Chang, Professor of internal medicine (gastroenterology and hepatology) at National Taiwan University, Taiwan. The researchers noted that the PanMETAI platform enables high-precision pancreatic cancer prediction, facilitating early detection, which will enhance treatment outcomes. Pancreatic Cancer: How PanMETAI makes early-stage detection Pancreatic cancer is hard to treat as the symptoms are rarely seen in the initial stages, and most patients receive their diagnosis at an advanced stage, when treatment options are limited. The PanMETAI platform tapped the current screening methods -- blood marker CA19-9 -- for early detection. Using 500 microliters of blood serum, the platform was able to extract over 260,000 metabolic signals in the study. It then analyzed the datasets using an AI model. By integrating these metabolic profiles with age, the cancer marker CA19-9, and a protein biomarker called Activin A, PanMETAI correctly distinguished cancer patients from high-risk controls in nearly every case, said the team. The researchers then validated the model in an independent Lithuanian cohort of 322 participants. The results proved that the tool works reliably across diverse populations. Further, the team found that NMR metabolomic data were essential to boost early-stage detection sensitivity. These capture subtle metabolic shifts -- such as decreased HDL cholesterol (bad cholesterol) and glutamine (an essential protein), and elevated lactic acid, glucose, and glutamic acid -- that occur before the cancer becomes clinically apparent. Pancreatic Cancer: A Global Health Burden Pancreatic cancer is the 12th most common cancer worldwide. Data from the Globocan reveal there were 510,992 new cases of pancreatic cancer in 2022, with China, the US, and Japan reporting the highest number of cases. The pancreas is a 15cm long gland found behind the stomach and in front of the spine. The organ is key to digesting food and curbing blood sugar levels in the body. Cancer develops in the pancreas when a change in the cells of the organ causes them to grow uncontrollably. Most pancreatic cancers start in exocrine cells, which produce digestive enzymes to help digest food and are secreted into the small intestine. While there are hardly any early symptoms, the ones appear can include: eyes or skin turning yellow (jaundice)itchy skin darker pee and paler poo than usual loss of appetite or losing weight without trying to fatigue a high temperature, or feeling hot or shivery