An AI used medical notes to teach itself to spot disease on chest x-rays

The research found that the model was more effective at identifying lung issues than other models. It was just as accurate as a human radiologist.

The ability to predict multiple diseases from a given x-ray with a high degree of accuracy is the first time an artificial intelligence model has learned from unstructured text, and it has been demonstrated by this model.

He says that they are the first to do that and show it off.

The model's code has been made publicly available to other researchers in the hopes that it could be used to detect diseases in other parts of the body.

He hopes that people can apply this to other chest x-ray data sets and diseases that they care about.

Diagnostic artificial intelligence models requiring minimal supervision could help increase access to health care in countries and communities where specialists are rare.

“It makes a lot of sense to use the richer training signal from reports,” says Christian Leibig, director of machine learning at German startup Vara, which uses AI to detect breast cancer. “It’s quite an achievement to get to that level of performance.”