AI tool predicts cancer treatment outcomes with high accuracy
Harvard Gazette — September 4, 2024, 06:00 PM UTC
Summary: Researchers at Harvard Medical School have developed an AI model named CHIEF, achieving nearly 94% accuracy in cancer detection across 19 types. Trained on 15 million images, it predicts patient survival and tumor responses to treatments, outperforming existing AI systems by up to 36%. CHIEF's capabilities include identifying genetic mutations and tumor characteristics, enhancing cancer diagnosis and treatment personalization globally.
Article metrics
The article metrics are deprecated.
I'm replacing the original 8-factor scoring system with a new and improved one. It doesn't use the original factors and gives much better significance scores.