Hyejuj project abstract

What I plan to do

I propose a semantic tagger that provides high level concept information for phrases based on several kinds of low level information about words in clinical narrative texts.

Motivation

Clinical documents are invaluable information. Semantic tagging on clinical documents will help doctors with a support for medical decision making or for quality assurance of medical treatment.

Interesting point

The clinical documents are written in both Korean and English. Usually, English is used for the medical terminologies, and Korean is used for some general nouns and most verbs though there are many exceptions.

Target Semantic Tag

• Symptom
• Diagnosis
• Test
• Test Result
• Treatment Plan
• Treatment
• Treatment Stop
• Performance
• Patient Result

Dataset

I have 600 manually tagged clinical narrative documents. They have been tagged with Unifies Medical Language System (UMLS), Part-of-Speech (POS).

Evaluation

The performance of the system can be measured as the level of accuracy of annotation, and it can be calculated as the number of correct tags per the total number of tags.

Techniques that can be used to solve this problem

• use Conditional Random Field
• use UMLS, POS, abbreviation, clue words, and numerical information to produce higher level concept information.

What question to answer

Can we show good performance on high-level semantic tagging using CRF?

Related Experience

I have developed a semantic tagger using Hidden Markov Model (HMM) in 2006. At that time, the target semantic tags were "Symptom", "Therapy", and "Performance."

References

• Hyeju Jang, Yun Jin, Sung Hyon Myaeng, Integration of Low Level Linguistic Information for Clinical Document Semantic Tagging, IEEE Conf. on Information Reuse and Integration 2006.
• TBA