AI-assisted thematic synthesis of existing neurological core outcome sets: A descriptive reference framework (COS-Neuro)
Shyun Ping Tiong, Xiaoyu Yang, Alvaro Yanez Touzet, Christopher Paul Millward, Carl M Zipser, Lindsay Tetreault, Ali Gharooni, Benjamin M Davies · 2026
Read AI-assisted thematic synthesis of existing neurological core outcome sets: A descriptive reference framework (COS-Neuro) by Shyun Ping Tiong, Xiaoyu Yang, Alvaro Yanez Touzet, Christopher Paul Millward, Carl M Zipser, Lindsay Tetreault, Ali Gharooni, Benjamin M Davies (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/plos-pone-0333864.txt.
Description
Shyun Ping Tiong and colleagues used artificial intelligence to sift the outcome lists that neurology trials are told to measure, hunting for the structure beneath them. Core outcome sets exist to make trials comparable, but neurology, which touches three billion people, has built few of them. The team mined a global database of such sets, let the AI cluster their domains, and had experts review the groupings.
Common patterns emerged across very different brain disorders, enough to draft a reference framework, called COS-Neuro, describing the domain families future sets tend to need. Trial designers starting a set for an unlisted condition can begin from this skeleton instead of a blank page. The authors present it as a descriptive aid, not a mandate, and the expert pass over the machine's clusters is part of the method's honesty.
Catalog record
| CREATOR | Shyun Ping Tiong, Xiaoyu Yang, Alvaro Yanez Touzet, Christopher Paul Millward, Carl M Zipser, Lindsay Tetreault, Ali Gharooni, Benjamin M Davies |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45415 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |