1. Automated information extraction from free‐text medical documents for stroke key performance indicators: a pilot study.
- Author
-
Bacchi, Stephen, Gluck, Sam, Koblar, Simon, Jannes, Jim, and Kleinig, Timothy
- Subjects
- *
PILOT projects , *STROKE , *KEY performance indicators (Management) , *NATURAL language processing , *THROMBOLYTIC therapy , *ANTICOAGULANTS , *INFORMATION retrieval , *AUTOMATION , *MEDICAL records , *CLINICAL medicine , *STROKE patients , *ELECTRONIC health records , *RECEIVER operating characteristic curves , *SENSITIVITY & specificity (Statistics) , *DISCHARGE planning - Abstract
Automated information extraction might be able to assist with the collection of stroke key performance indicators (KPI). The feasibility of using natural language processing for classification‐based KPI and datetime field extraction was assessed. Using free‐text discharge summaries, random forest models achieved high levels of performance in classification tasks (area under the receiver operator curve 0.95–1.00). The datetime field extraction method was successful in 29 of 43 (67.4%) cases. Further studies are indicated. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF