End to end AI system for surgical gesture sequence recognition and clinical outcome prediction
Xi Li, Nicholas Matsumoto, Ujjwal Pasupulety, Atharva Deo, Cherine Yang, Jay Moran, Miguel E. Hernandez, Peter Wager, Jasmine Lin, Jeanine Kim, Alvin C. Goh, Christian Wagner, Geoffrey A. Sonn, Andrew J. Hung · 2026
Read End to end AI system for surgical gesture sequence recognition and clinical outcome prediction by Xi Li, Nicholas Matsumoto, Ujjwal Pasupulety, Atharva Deo, Cherine Yang, Jay Moran, Miguel E. Hernandez, Peter Wager, Jasmine Lin, Jeanine Kim, Alvin C. Goh, Christian Wagner, Geoffrey A. Sonn, Andrew J. Hung (2026) 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/PMC13319110.txt.
Description
Xi Li leads a large team presenting, in 2026, an end-to-end AI system that reads surgical video and links movement patterns to patient outcomes. The system, called Frame-to-Outcome, turns dissection footage into gesture sequences. Testing used the nerve-sparing step of robot prostate surgery. Transformer models classified actions frame by frame.
The system detected short gestures of about two seconds reliably. Accuracy reached an AUC of 0.80 at frame level and 0.81 at video level in their tests. Features like gesture frequency, duration, and transitions predicted outcomes about as well as human labels. Effect directions matched across 25 shared features, with a strong correlation of 0.96 between the two. Longer tissue peeling and lower energy use tied to better erectile recovery. The authors see a base for data-driven surgical feedback.
Catalog record
| CREATOR | Xi Li, Nicholas Matsumoto, Ujjwal Pasupulety, Atharva Deo, Cherine Yang, Jay Moran, Miguel E. Hernandez, Peter Wager, Jasmine Lin, Jeanine Kim, Alvin C. Goh, Christian Wagner, Geoffrey A. Sonn, Andrew J. Hung |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71146 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |