Automated derivation of diagnostic criteria for lung cancer using natural language processing on electronic health records: a pilot study
Andrew Houston, Sophie Williams, William Ricketts, Charles Gutteridge, Chris Tackaberry, John Conibear · 2024
Read Automated derivation of diagnostic criteria for lung cancer using natural language processing on electronic health records: a pilot study by Andrew Houston, Sophie Williams, William Ricketts, Charles Gutteridge, Chris Tackaberry, John Conibear (2024) 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-11616170.txt.
Description
Andrew Houston and five co-authors pilot a way to pull diagnosis rules for lung cancer from hospital records with language software. Digital records hold vast free text, and coded fields can miss symptoms that matter. The study came out in twenty twenty-four.
The team took adults who had a chest X-ray across a span of years. Their records from the year before the scan were mined for named symptoms, which were mapped to a standard health code list. Codes were rolled up to broader groups to fight sparsity, and a chance score ranked candidate traits. A genetic search then picked the trait set that split cancer from non cancer best, to form the rules.
Catalog record
| CREATOR | Andrew Houston, Sophie Williams, William Ricketts, Charles Gutteridge, Chris Tackaberry, John Conibear |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |