Related Experiment Videos
Creating and indexing teaching files from free-text patient reports
D B Johnson1, W W Chu, J D Dionisio
1Department of Computer Science, University of California, Los Angeles, USA.
Proceedings. AMIA Symposium
|November 24, 1999
Summary
This study introduces a new system using multi-word indexing for better retrieval of free-text patient reports. This approach improves information access for medical education and research.
Area of Science:
- Medical Informatics
- Information Retrieval
- Medical Education
Background:
- Real patient data teaching files enhance medical education.
- Keyword-based information retrieval struggles with content-heavy medical terms like anatomy descriptions.
- Existing systems lack nuanced understanding of medical report content.
Purpose of the Study:
- To describe a novel system for accessing free-text patient reports using multi-word indexing terms.
- To improve the performance of information retrieval systems for medical documents.
- To enhance the utility of patient data for educational purposes.
Main Methods:
- Developed a system employing multi-word indexing for free-text patient reports.
- Focused on selecting indexing terms that better represent report content.
- Evaluated the retrieval performance of the new system.
Main Results:
- Multi-word indexing allows for more accurate modeling of medical report content.
- The system demonstrated improved retrieval performance compared to traditional methods.
- The approach enhances the accessibility of complex medical information.
Conclusions:
- Multi-word indexing significantly enhances the retrieval of free-text medical reports.
- This system offers a more effective way to utilize patient data for medical education and research.
- The findings suggest a valuable advancement in medical information retrieval technology.