EchoGraph system for automated quality assessment of echocardiography reports
Chieh-Ju Chao, Jean-Benoit Delbrouck, Mohammad Asadi, Imon Banerjee, Juan M. Farina, Francesca Galasso, Ahmed K. Mahmoud, Mohammed Tiseer Abbas, Yu-Chiang Wang, Reza Arsanjani, Garvan C. Kane, Jae K. Oh, Bradley J. Erickson, Li Fei-Fei, Ehsan Adeli, Curtis Langlotz · 2025
Read EchoGraph system for automated quality assessment of echocardiography reports by Chieh-Ju Chao, Jean-Benoit Delbrouck, Mohammad Asadi, Imon Banerjee, Juan M. Farina, Francesca Galasso, Ahmed K. Mahmoud, Mohammed Tiseer Abbas, Yu-Chiang Wang, Reza Arsanjani, Garvan C. Kane, Jae K. Oh, Bradley J. Erickson, Li Fei-Fei, Ehsan Adeli, Curtis Langlotz (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12789664.txt.
Description
Chieh-Ju Chao and co-authors build EchoGraph, a tool that grades AI written echocardiography reports the way a careful reader would. Published in 2025, the model answers a gap: generative AI writes clinical text, but no automatic accuracy metric existed for heart ultrasound reports. EchoGraph was trained on 600 Mayo Clinic reports, densely annotated with over 48,000 entities and nearly 30,000 relations.
The model predicted entities and relations with strong scores, and held up on an outside hospital's reports. Against an existing radiology metric, its score proved far more sensitive to planted errors and explained more of their variance. The authors offer it as a check for language model tools in cardiology, toward safer AI drafted reports.
Catalog record
| CREATOR | Chieh-Ju Chao, Jean-Benoit Delbrouck, Mohammad Asadi, Imon Banerjee, Juan M. Farina, Francesca Galasso, Ahmed K. Mahmoud, Mohammed Tiseer Abbas, Yu-Chiang Wang, Reza Arsanjani, Garvan C. Kane, Jae K. Oh, Bradley J. Erickson, Li Fei-Fei, Ehsan Adeli, Curtis Langlotz |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |