Early detection of colorectal cancer by leveraging Dutch primary care consultation notes with free text embeddings
Abstract We aimed to assess the added predictive performance that free-text Dutch consultation notes provide in detecting colorectal cancer in primary care, in comparison to currently used models. We developed, evaluated and compared three prediction models for colorectal cancer (CRC) in a large primary care database with 60,641 patients. The prediction model with both known predictive features and free-text data (with TabTxt AUROC: 0.823) performs statistically significantly better (p < 0.05) than the other two models with only tabular (as used nowadays) and text data, respectively (AUROC... Mehr ...
Verfasser: | |
---|---|
Dokumenttyp: | Artikel |
Erscheinungsdatum: | 2023 |
Reihe/Periodikum: | Scientific Reports, Vol 13, Iss 1, Pp 1-10 (2023) |
Verlag/Hrsg.: |
Nature Portfolio
|
Schlagwörter: | Medicine / R / Science / Q |
Sprache: | Englisch |
Permalink: | https://search.fid-benelux.de/Record/base-28579448 |
Datenquelle: | BASE; Originalkatalog |
Powered By: | BASE |
Link(s) : | https://doi.org/10.1038/s41598-023-37397-2 |