CHIEF, the new AI model that can detect different types of cancer
Scientists have created a new artificial intelligence (AI) model similar to ChatGPT that may be able to diagnose and evaluate multiple types of cancer.
The new model, called the Clinical Histopathology Image Evaluation Foundation (CHIEF), was up to 36 percent more effective at detecting cancer, determining the origin of a tumor, and predicting patient outcomes than other deep learning models. , the researchers said.
The team led by Harvard Medical School researchers wanted the model to be more applicable to different diagnostic tasks since many current deep learning models for cancer are trained to perform specific functions.
"Unlike existing methods, our AI tool provides clinicians with accurate and real-time second opinions on cancer diagnoses considering a wide spectrum of cancer types and variations," said Kun-Hsing Yu, assistant professor of in biomedical informatics at Harvard Medical School.
How does CHIEF work?
The model was trained on more than 15 million different pathology images, "which increases its reliability in diagnosing cancers with atypical characteristics," Yu added.
They then used more than 60,000 high-resolution images of tissue slides "to further develop the AI model and fine-tune it for specific genetic and clinical prediction tasks."
The researchers tested their model on more than 19,400 images from 24 hospitals and patient groups around the world and published the findings in the journal Nature on Wednesday.
The team said the model works by reading digital slides of tumor tissues and can predict their molecular profile based on features in the image. It can also identify features of a tumor that correlate with how a patient might respond to treatment.
It achieved nearly 94 percent accuracy in detecting cancer cells in 11 types of cancer based on a model performance metric.