Anirban Maitra, Eric J Topol
Lancet . 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1.
Pancreatic cancer is on the rise globally, and usually presents at advanced metastatic stages, inoperable, with little responsiveness to chemotherapy. Early diagnosis has been associated with better outcomes, but only a minority of pancreatic cancer cases are diagnosed at a stage when the tumour is surgically operable. Current guidance for pancreatic cancer surveillance is restricted to high-risk individuals (HRIs) who have germline mutations that predispose to a lifetime increased risk of pancreatic cancer or a strong family history of pancreatic cancer. When a pancreatic cyst is detected incidentally by abdominal imaging, such patients are often put in the HRI category for surveillance. Cumulatively, HRIs account for only about 20–25% of cases. What about the majority of patients with no risk factors who present at an advanced stage? This is where advances in artificial intelligence (AI) based on mining of electronic health records (EHRs) have started to show some promise.