Related Experiment Video
Updated: Oct 3, 2025
Computerized Adaptive Testing System of Functional Assessment of Stroke
Published on: January 7, 2019
Automated information extraction from free-text medical documents for stroke key performance indicators: a pilot
Stephen Bacchi1,2, Sam Gluck1,2, Simon Koblar1,2
1Royal Adelaide Hospital, Adelaide, South Australia, Australia.
Automated information extraction using natural language processing shows promise for collecting stroke key performance indicators (KPI). While classification tasks were highly accurate, datetime extraction needs further development.
Area of Science:
- Medical Informatics
- Natural Language Processing
- Healthcare Data Analytics
Background:
- Collecting stroke key performance indicators (KPI) is crucial for quality improvement.
- Manual data extraction from clinical notes is time-consuming and prone to errors.
Purpose of the Study:
- To assess the feasibility of automated information extraction for stroke KPIs.
- To evaluate natural language processing (NLP) for classification and datetime field extraction from discharge summaries.
Main Methods:
- Utilized random forest models for classification-based KPI extraction.
- Applied NLP techniques to extract datetime information from free-text discharge summaries.
Main Results:
- Random forest models achieved high performance in classification tasks (AUC 0.95-1.00).
- Datetime field extraction was successful in 67.4% of cases (29 out of 43).
Conclusions:
- Automated information extraction via NLP is a feasible approach for stroke KPI collection.
- Further research is needed to optimize datetime extraction accuracy.
More Related Videos
09:52Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
Published on: January 15, 2017
07:50A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
