Sample excerpt of a narrative of a CT scan of the heart. (VIDEO)

Harvard Medical School

Caption

Reliable scoring systems that accurately gauge the performance of AI-generated narrative reports of radiology images are critical for ensuring that AI continues to improve and that clinicians can trust medical AI models. Harvard Medical School researchers have designed two AI-scoring systems that outperform current ones.

Credit

Paul DiMattia, Harvard Medical School

Usage Restrictions

for non-commercial news media use

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.