Waiting for MRI results can feel endless, especially when every minute matters. Now, researchers say that the wait could shrink to just seconds. Scientists at the University of Michigan have developed a powerful new AI system called Prima that can read and diagnose brain MRI scans almost instantly, with accuracy reaching 97.5%. The findings have been published in the journal Nature Biomedical Engineering, and experts believe this technology could significantly transform emergency brain care. What is Prima, and how does it work? Prima is an artificial intelligence model trained to interpret brain MRI scans the way a radiologist would. But instead of taking hours, or sometimes days, it can deliver results in seconds. The AI was trained using over 220,000 real MRI studies, along with patient medical histories and doctors’ notes. Researchers also tested it over one year across nearly 30,000 MRI scans in a real hospital setting.
Unlike older AI tools designed to detect only one specific condition, Prima can identify more than 50 neurological disorders, including: By combining imaging data with clinical information, the system creates a fuller picture, similar to how doctors review scans alongside patient history. 97.5% accuracy, and faster than humans According to the study, Prima achieved an accuracy rate of up to 97.5%, outperforming several other advanced AI systems. Todd Hollon, a neurosurgeon at U-M Health and the lead author of the study, described the model as: “ChatGPT for medical imaging” He explained that the tool could significantly ease hospital workloads, especially in areas where neurological specialists are not immediately available. As the global demand for MRI rises and places a significant strain on our physicians and health systems, our AI model has the potential to reduce burden by improving diagnosis and treatment with fast, accurate information,” Hollon said. Researchers added: “We believe that Prima exemplifies the transformative potential of integrating health systems and AI-driven models to improve healthcare through innovation.” Also read: Global tech leaders to gather for India–AI Impact Summit 2026; here’s the list of tech giants coming to India
Why speed is so important In brain emergencies, time can mean the difference between recovery and permanent damage. Conditions like stroke or internal bleeding require immediate medical attention. Prima not only detects these problems quickly but can also flag urgent cases automatically, helping doctors prioritise critical patients faster. Hospitals worldwide are facing a shortage of radiologists, and MRI demand continues to grow. In many places, patients wait days for scan reviews. Tools like Prima could help reduce these delays without replacing doctors, acting more like a digital assistant. Samir Harake, a co-first author of the study and data scientist, explained that Prima works by analysing both scan images and patient information together, much like a trained radiologist would do. AI in medical diagnosis AI tools are increasingly being used to assist in medical diagnoses. Recently, a video of Elon Musk discussing AI in healthcare went viral. Musk said: I think AI will be very helpful with the medical stuff. Right now, you can upload your X-rays or MRI images to Grok, and it will give you a medical diagnosis. I have seen cases where it’s actually better than what doctors tell you.
He shared the example of a 49-year-old man in Norway who initially received a diagnosis of acid reflux during an emergency visit. Still in pain, the man reportedly consulted an AI tool, which suggested a more serious condition and advised further scanning. Tests later confirmed a severely inflamed appendix that required emergency surgery. While such cases highlight AI’s potential, experts stress that AI tools should support doctors, not replace them. Also read: Made-in-India ‘Sarvam AI’ beats ChatGPT and Gemini
Future of Prima Researchers believe future versions of Prima could: The goal is not to remove doctors from the process, but to give them faster and more reliable insights, especially in high-pressure emergencies. A glimpse into the future of healthcare Prima represents a major step forward in combining artificial intelligence with real-world hospital systems. As MRI demand increases and healthcare systems struggle with staffing shortages, tools like this could help deliver quicker diagnoses and potentially save lives. It may sound futuristic, but this AI model is already being tested in real hospitals. If widely adopted, reading brain scans in seconds could soon become the new normal, and that could change emergency care forever.
