The Intelligence Layer
of Surgery

OpenAI’s startup fund and Founders Fund back Coherence Neuro, whose brain implant is built to detect brain tumor signals and treat them in real time.

A Bern University Hospital AI model uses vital signs recorded during surgery to predict infection risk at skin closure, reaching an AUROC of 0.88.

A peer-reviewed paper argues thoracic surgery, not general surgery, is where autonomous robots operate next. Here is the clinical case.

Pancreatic cancer is usually diagnosed too late for curative surgery. More than 85% of patients present with advanced disease, when resection is no longer possible. Researchers at Mayo Clinic have developed an AI model that detects imaging changes months before pancreatic cancer becomes visible on routine CT scans. Looking beyond the tumor The model, called REDMOD, analyzes radiomic features throughout the pancreas instead of searching for a visible mass. In a validation stud

Artificial intelligence is starting to change breast cancer care before treatment even begins. Researchers at UCSF and UC Berkeley used an AI model called Mirai to identify women at high risk immediately after screening mammography and move them into expedited diagnostic evaluation. The workflow reduced diagnostic assessment from weeks to about one hour. Among women diagnosed with breast cancer, the median time to biopsy fell from more than two months to fewer than ten days.

Researchers at the University of Bern have developed an artificial intelligence model that predicts a patient's risk of postoperative infection immediately after surgery, using physiologic data collected during the operation rather than relying only on preoperative risk factors. Why it matters Postoperative infections remain one of the leading causes of surgical complications, contributing to longer hospital stays, higher healthcare costs, and increased mortality. Traditional