ABSTRACT NUMBER: ESOC2026A2214 COMBINING A LARGE LANGUAGE MODEL WITH TRADITIONAL SOFTWARE ENGINEERING TOOLS FOR AUTOMATED RES-Q REGISTRY VARIABLE EXTRACTION
Gertrūda Kaubrytė, Agnė Ulytė, Rytis Klimovič, Andrius Maslovas, Robert Mikulík, Dalius Jatuzis, Rytis Masiliunas · 2026
Read ABSTRACT NUMBER: ESOC2026A2214 COMBINING A LARGE LANGUAGE MODEL WITH TRADITIONAL SOFTWARE ENGINEERING TOOLS FOR AUTOMATED RES-Q REGISTRY VARIABLE EXTRACTION by Gertrūda Kaubrytė, Agnė Ulytė, Rytis Klimovič, Andrius Maslovas, Robert Mikulík, Dalius Jatuzis, Rytis Masiliunas (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/pmc-13145630.txt.
Description
Gertrūda Kaubrytė and co-authors present a 2026 conference study on pulling stroke registry data from records with an AI language tool joined to plain software. Hand data entry for quality registries eats staff time. The team built a pilot system for the RES-Q registry and checked it against hand work.
The hand-made reference set covered one hundred stroke cases and near fourteen thousand data points, at about twenty minutes per patient. The pilot pulled most fields with plain code and the rest with the AI tool. Overall accuracy reached about eighty-nine percent. Sixty fields matched the hand work perfectly, including age, sex, and key procedure times. The system also caught fields the hand team had keyed in wrong.
Catalog record
| CREATOR | Gertrūda Kaubrytė, Agnė Ulytė, Rytis Klimovič, Andrius Maslovas, Robert Mikulík, Dalius Jatuzis, Rytis Masiliunas |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |