AI for Healthcare

AI is an increasingly critical component of our healthcare ecosystem, and its potential applications are vast. Right now, AI is already being used to detect diseases earlier and more accurately. AI is also streamlining drug research and discovery processes in ways that could significantly reduce drug costs and the time it takes to bring new drugs to market. AI can help track the outbreak and spread of diseases more efficiently and effectively, allowing public health experts to engage in real-time modeling for managing and stopping epidemics and pandemics.

Detecting Cancer Earlier

Mayo Clinic

Mayo Clinic researchers developed an AI model helping specialists identify early signs of pancreatic cancer on routine abdominal CT scans up to three years before clinical diagnosis. In a landmark validation study, the model analyzed nearly 2,000 CT scans, including scans that had originally been interpreted as normal, and identified 73% of prediagnostic cancers 16 months before diagnosis. The tool is supporting clinicians by flagging subtle changes that may indicate elevated risk, helping doctors find disease earlier when curative treatment may still be possible.

 

Improving Care for Veterans

VHA’s AI-Driven eFax Fix

When veterans receive care from providers in their communities, important medical documents must be added to their VA health records quickly. The Veterans Health Administration’s (VHA) AI-Driven eFax Fix (AIEFF) is making that process faster and more accurate for veterans who seek care at VHA facilities. The automated system uses AI to save staff time, reduce stress, and ensure veterans’ records are updated quickly and accurately. By automating a time-consuming administrative process, the new AI-enabled technology allows VA staff to spend less time sorting documents and more time supporting veteran care.

 

AI Model Predicts Disease Risk While You Sleep

Sleep FM

An artificial intelligence model developed by Stanford Medicine researchers and their colleagues can use physiological recordings from one night’s sleep to predict a person’s risk of developing more than 100 health conditions. Known as SleepFM, the model was trained on nearly 600,000 hours of sleep data collected from 65,000 participants. The sleep data comes from polysomnography, the gold standard in sleep studies, and only a fraction of that data is used in current sleep research and sleep medicine. With these advances in AI, it’s now possible for scientists to make sense of much more of the sleep data available to them.