MKEM: a Multi-level Knowledge Emergence Model for mining undiscovered public knowledge
2010
MKEM: A Model for Discovering Hidden Knowledge in Biomedical Literature
Sample size: 5000
publication
Evidence: moderate
Author Information
Author(s): Ijaz Ali Z, Min Song, Doheon Lee
Primary Institution: KAIST, South Korea
Hypothesis
Can a Multi-level Knowledge Emergence Model (MKEM) effectively uncover undiscovered public knowledge in biomedical literature?
Conclusion
The MKEM model is effective in discovering hidden relationships in biomedical texts.
Supporting Evidence
- The system extracted 410 relationships from 5000 abstracts.
- Precision of the system was 75%, indicating a good level of accuracy.
- 24 new hypotheses were generated from the extracted data.
Takeaway
This study created a computer program that helps find new connections in medical research by looking at lots of articles at once.
Methodology
The study used Natural Language Processing techniques and a model called SEPDB to extract relationships from 5000 biomedical abstracts.
Limitations
The performance evaluation lacked a gold standard for comparison.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website