Click here to load reader
View
229
Download
0
Embed Size (px)
Citation preview
AMIA-2006 1
A Comparative Study of Supervised Learning
as Applied to Acronym Expansion in
Clinical Reports
Mahesh Joshi, Serguei Pakhomov, Ted Pedersen, Christopher G. Chute
University of Minnesota, DuluthMayo College of Medicine, Rochester
AMIA-2006 2
Overview
• Acronyms are ambiguous– in general, and in more specialized domains
• Acronyms can be disambiguated by expansion – expansions act as senses or definitions
• Acronym expansion can be viewed as word sense disambiguation– supervised learning from annotated examples
• Features trump learning algorithms– unigrams dominant
AMIA-2006 3
AMIA - Top Google Results
• American Medical Informatics Association
• Association of Moving Image Archivists
• Anglican Mission in America
• Associcion Mutual Israelita Argentina
AMIA-2006 4
RN in Wikipedia
• Registered Nurse
• Royal Navy
• Radio National
• Radio Nederland
• Richard Nixon
• Registered Identification Number
• Renovacion Nacional
AMIA-2006 5
Acronym Ambiguity not just a problem for General English…
• 33% of Acronyms in UMLS are ambiguous– Liu et. al. AMIA-2001
• 81% of Acronyms in MEDLINE abstracts are ambiguous, with an average of 16 expansions– Liu et. al. AMIA-2002
AMIA-2006 6
We view AE as WSD
• AE – sense 1: American Eagle– sense 2: Arab Emirates– sense 3: acronym expansion
• WSD– sense 1: Washington School for the Deaf– sense 2: web server director– sense 3: word sense disambiguation
AMIA-2006 7
Methodology
• Identify 16 ambiguous acronyms– 9 from Pakhomov, et. al. AMIA-2005– 7 newly annotated for this this study
• Manually annotate in clinical notes– 7,738 total instances from Mayo Clinic
database of clinical notes
• Use as training data for supervised learning
AMIA-2006 8
Acronyms (majority < 50%)
• AC – Acromioclavicular– Antitussive with Codeine– Acid Controller– 10 more
• APC – Argon Plasma Coagulation – Adenomatous Polyposis Coli– Atrial Premature Contraction– 10 more expansions
• LE– Limited Exam Lower
Extremity– Initials– 5 more expansions
• PE – Pulmonary Embolism– Pressure Equalizing– Patient Education– 12 more expansions
AMIA-2006 9
Acronyms (50% < majority < 80%)
• CP– Chest Pain– Cerebral Palsy– Cerebellopontine– 19 more expansions
• HD– Huntington's Disease – Hemodialysis– Hospital Day– 9 more expansions
• CF– Cystic Fibrosis – Cold Formula– Complement Fixation– 6 more expansions
• MCI– Mild Cognitive Impairment– Methylchloroisothiazolinone– Microwave Communications,
Inc.– 5 more expansions
• ID– Infectious Disease– Identification– Idaho Identified– 4 more expansions
• LA– Long Acting– Person– Left Atrium– 5 more expansions
AMIA-2006 10
Acronyms (majority > 80%)• MI
– Myocardial Infarction– Michigan– Unknown– 2 more expansions
• ACA– Adenocarcinoma– Anterior Cerebral Artery– Anterior Communication
Artery– 3 more expansions
• GE– Gastroesophageal– General Exam– Generose– General Electric
• HA– Headache– Hearing Aid– Hydroxyapatite– 2 more expansions
• FEN– Fluids, Electrolytes and
Nutrition– Drug Fen Phen– Unknown
• NSR– Normal Sinus Rhythm– Nasoseptal Reconstruction
AMIA-2006 11
Experimental Objectives
• Compare performance of ML methods– Naïve Bayesian classifier– J48/C4.5 decision tree learner – Support vector machine (SMO)
• Compare four different feature sets– POS tags from Brill-Hepple Tagger– Unigrams that occur 5 or more times
• Flexible window of size 5 around target
– Bigrams that occur 5 or more times• Flexible window of size 5 around target
– Unigrams + Bigrams + POS tags
AMIA-2006 12
Feature Extraction
• Horizon : up to 5 content words to left and right of target• Boundaries : cross sentences, but not clinical notes• Skip stop words• Bigrams are pairs of contiguous content words• Example (CF is target):
– Unigrams: “if she is found to be a carrier, then they will follow with CF carrier testing in her husband.”
– Bigrams: “if she is found to be a carrier, then they will follow with CF carrier testing in her husband.”
AMIA-2006 13
Results (majority < 50%)Feature Comparison (AC, APC, LE, PE)
30
40
50
60
70
80
90
100
Decision Trees Naïve Bayes SVM
Classifier
Accu
racy (
%)
POS bigrams unigrams ALL Majority
AMIA-2006 14
Results (50% < majority < 80%)Feature Comparison (CP, HD, CF, MCI, ID, LA)
30
40
50
60
70
80
90
100
Decision Trees Naïve Bayes SVM
Classifier
Accu
racy (
%)
POS bigrams unigrams ALL Majority
AMIA-2006 15
Results (majority > 80%)Feature Comparison (MI, ACA, GE, HA, FEN, NSR)
30
40
50
60
70
80
90
100
Decision Trees Naïve Bayes SVM
Classifier
Accu
racy (
%)
POS bigrams unigrams ALL Majority
AMIA-2006 16
Results (flexible window)Fixed vs. Flexible Window Performance
70
75
80
85
90
95
1 2 3 4 5 6 7 8 9 10Window Size
Accu
racy (
%)
fixed-bigrams fixed-unigrams fixed-unigrams+bigramsflexi-bigrams flexi-unigrams flexi-unigrams+bigrams
AMIA-2006 17
Conclusions
• Overall expansion accuracy at or above 90% regardless of distribution
• Differences in accuracy are largely due to features, not ML algorithms
• Addition of bigrams and POS tags helps performance, but unigrams dominant
• Flexible window improves upon fixed window feature selection
AMIA-2006 18
Future Work
• Expand all acronyms in a text, not just select few– expand based on prior expansions– utilize one sense per discourse constraint
• Integrate supervised methods with knowledge based approaches and clustering methods to reduce need for annotated examples
AMIA-2006 19
Acknowledgments
• We would like to thank our annotators Barbara Abbott, Debra Albrecht and Pauline Funk.
• This work was supported in part by the NLM Training Grant (T15 LM07041-19) and the NIH Roadmap Multidisciplinary Clinical Research Career Development Award (K12/NICHD)-HD49078.
• Dr. Pedersen has been partially supported by a National Science Foundation Faculty Early CAREER Development Award (#0092784).
AMIA-2006 20
Software Resources
• NSPGate (from Duluth/Mayo)– http://nspgate.sourceforge.net/
• Ngram Statistics Package (from Duluth)– http://ngram.sourceforge.net/
• WSDGate (from Duluth/Mayo)– http://wsdgate.sourceforge.net/
• WEKA (from Waikato) – http://www.cs.waikato.ac.nz/ml/weka/
• GATE (from Sheffield) – http://gate.ac.uk/