Mayo Clinic researchers have developed Redmod, an AI system that detects pancreatic cancer on routine CT scans an average of 15 months before clinical diagnosis. The breakthrough could dramatically improve survival rates for one of cancer's deadliest forms.
Pancreatic cancer typically has poor outcomes due to late detection, with most patients diagnosed at advanced stages. Redmod analyzes standard imaging scans to identify tumors years earlier than conventional methods, potentially allowing intervention during more treatable phases.
The system represents a significant advance in using machine learning for early cancer detection. By processing routine CT scans already being performed for other reasons, Redmod provides an opportunity to catch pancreatic cancer incidentally—without additional imaging procedures or screening protocols.
Researchers at Mayo Clinic have not yet released detailed findings on accuracy rates or the size of the study population. The work builds on broader efforts to deploy AI in radiology for improved diagnostic capabilities.
Early detection of pancreatic cancer remains a critical challenge, as the disease is often asymptomatic in early stages. If validated in larger studies, Redmod could become a standard tool in clinical settings, potentially improving prognosis for thousands of patients annually.
Uber's weekly AI agent requests have grown nearly tenfold since February, yet the company has held spending flat since April after exhausting its entire 2026 AI budget in Q1.
A recent paper shows artificial intelligence often diagnoses and treats patients better than human physicians. The findings are prompting difficult conversations within the medical community about the profession's evolving role.
The Relay Q, launching next year, represents the latest push to establish voice as the primary interface for human-computer interaction, challenging the keyboard's decades-long dominance.
An Anthropic researcher demonstrated automated systems that can identify and correct misaligned behaviors without compromising overall performance. The systems improved on all 10 tested benchmarks measuring specific problematic outputs.