CRF &SVM in Medication Extraction

Slides:



Advertisements
Similar presentations
Automatic Timeline Generation from News Articles Josh Taylor and Jessica Jenkins.
Advertisements

Document Summarization using Conditional Random Fields Dou Shen, Jian-Tao Sun, Hua Li, Qiang Yang, Zheng Chen IJCAI 2007 Hao-Chin Chang Department of Computer.
Progress update Lin Ziheng. System overview 2 Components – Connective classifier Features from Pitler and Nenkova (2009): – Connective: because – Self.
Supervised Learning Techniques over Twitter Data Kleisarchaki Sofia.
Problem Semi supervised sarcasm identification using SASI
Comparing Twitter Summarization Algorithms for Multiple Post Summaries David Inouye and Jugal K. Kalita SocialCom May 10 Hyewon Lim.
NYU ANLP-00 1 Automatic Discovery of Scenario-Level Patterns for Information Extraction Roman Yangarber Ralph Grishman Pasi Tapanainen Silja Huttunen.
Personal Name Classification in Web queries Dou Shen*, Toby Walker*, Zijian Zheng*, Qiang Yang**, Ying Li* *Microsoft Corporation ** Hong Kong University.
Annotation of 311 Admission Summaries of the ICU Corpus Yefeng Wang.
STRUCTURED PERCEPTRON Alice Lai and Shi Zhi. Presentation Outline Introduction to Structured Perceptron ILP-CRF Model Averaged Perceptron Latent Variable.
Extraction of Adverse Drug Effects from Clinical Records E. ARAMAKI* Ph.D., Y. MIURA **, M. TONOIKE ** Ph.D., T. OHKUMA ** Ph.D., H. MASHUICHI ** Ph.D.,K.WAKI.
Thien Anh Dinh1, Tomi Silander1, Bolan Su1, Tianxia Gong
2007. Software Engineering Laboratory, School of Computer Science S E Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying.
Illinois-Coref: The UI System in the CoNLL-2012 Shared Task Kai-Wei Chang, Rajhans Samdani, Alla Rozovskaya, Mark Sammons, and Dan Roth Supported by ARL,
A Simple Unsupervised Query Categorizer for Web Search Engines Prashant Ullegaddi and Vasudeva Varma Search and Information Extraction Lab Language Technologies.
Automatic Detection of Tags for Political Blogs Khairun-nisa Hassanali Vasileios Hatzivassiloglou The University.
Open Information Extraction using Wikipedia
Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop Nizar Habash and Owen Rambow Center for Computational Learning.
A Language Independent Method for Question Classification COLING 2004.
Recognizing Names in Biomedical Texts: a Machine Learning Approach GuoDong Zhou 1,*, Jie Zhang 1,2, Jian Su 1, Dan Shen 1,2 and ChewLim Tan 2 1 Institute.
Math Information Retrieval Zhao Jin. Zhao Jin. Math Information Retrieval Examples: –Looking for formulas –Collect teaching resources –Keeping updated.
05/03/03-06/03/03 7 th Meeting Edinburgh Naïve Bayes Fact Extractor (NBFE) v.1.
A Scalable Machine Learning Approach for Semi-Structured Named Entity Recognition Utku Irmak(Yahoo! Labs) Reiner Kraft(Yahoo! Inc.) WWW 2010(Information.
Date : 2013/03/18 Author : Jeffrey Pound, Alexander K. Hudek, Ihab F. Ilyas, Grant Weddell Source : CIKM’12 Speaker : Er-Gang Liu Advisor : Prof. Jia-Ling.
1 Italian FE Component CROSSMARC Eighth Meeting Crete 24 June 2003.
Recognizing Stances in Online Debates Unsupervised opinion analysis method for debate-side classification. Mine the web to learn associations that are.
From Words to Senses: A Case Study of Subjectivity Recognition Author: Fangzhong Su & Katja Markert (University of Leeds, UK) Source: COLING 2008 Reporter:
Event-Based Extractive Summarization E. Filatova and V. Hatzivassiloglou Department of Computer Science Columbia University (ACL 2004)
Object Recognition as Ranking Holistic Figure-Ground Hypotheses Fuxin Li and Joao Carreira and Cristian Sminchisescu 1.
Virtual Examples for Text Classification with Support Vector Machines Manabu Sassano Proceedings of the 2003 Conference on Emprical Methods in Natural.
The P YTHY Summarization System: Microsoft Research at DUC 2007 Kristina Toutanova, Chris Brockett, Michael Gamon, Jagadeesh Jagarlamudi, Hisami Suzuki,
Semi-Supervised Recognition of Sarcastic Sentences in Twitter and Amazon -Smit Shilu.
1 Predicting Answer Location Using Shallow Semantic Analogical Reasoning in a Factoid Question Answering System Hapnes Toba, Mirna Adriani, and Ruli Manurung.
Multi-Class Sentiment Analysis with Clustering and Score Representation Yan Zhu.
City Forensics: Using Visual Elements to Predict Non-Visual City Attributes Sean M. Arietta, Alexei A. Efros, Ravi Ramamoorthi, Maneesh Agrawala Presented.
Natural Language Processing Information Extraction Jim Martin (slightly modified by Jason Baldridge)
Best-of-Breed Hybrid Methods for Text De-identification Yang H, Garibaldi JM. Automatic detection of protected health information from clinical narratives.
Medical Semantic Similarity with a Neural Language Model Dongfang Xu School of Information Using Skip-gram Model for word embedding.
Extracting CHF information from clinical text using CLAMP Hua Xu, PhD pSCANNER
Language Identification and Part-of-Speech Tagging
Functional EHR Systems
Constructing a Predictor to Identify Drug and Adverse Event Pairs
Acknowledgement: Khem Gyawali
Showcasing work by Jonnageddala, Liaw, Ray, Kumar, Chang, and Dai on
Investigating Pitch Accent Recognition in Non-native Speech
The Relationship between Deep Learning and Brain Function
Medication Information Extraction
Deep Learning Amin Sobhani.
Architecture Concept Documents
8. Causality assessment:
Named Entity Tagging with Conditional Random Fields
Bidirectional CRF for NER
Natural Language Processing of Knee MRI Reports
IX- PREPARING THE BUDGET
Social Knowledge Mining
MS Access: Using Advanced Query Features
Functional EHR Systems
Discriminative Frequent Pattern Analysis for Effective Classification
Automatic Detection of Causal Relations for Question Answering
SNOMED-CT representation Radiologic report Admission Letter
Explaining the Methodology : steps to take and content to include
Family History Technology Workshop
Leveraging Textual Specifications for Grammar-based Fuzzing of Network Protocols Samuel Jero, Maria Leonor Pacheco, Dan Goldwasser, Cristina Nita-Rotaru.
Model Enhanced Classification of Serious Adverse Events
Clinically Significant Information Extraction from Radiology Reports
A Novel Smoke Detection Method Using Support Vector Machine
CRISP Process Stephen Wyrick.
Extracting Why Text Segment from Web Based on Grammar-gram
Computed Tomography (C.T)
Stance Classification of Ideological Debates
Presentation transcript:

CRF &SVM in Medication Extraction -------A Cascade Approach to Extracting Medication Events Dongfang Xu School of Information

Outline Methodology Results & Discussion Conclusion Extraction Definition Data Preparation System Architecture Results & Discussion NER(CRF) Experiment Relationship Classification (SVM) CONTEXT Engine Evaluation Conclusion

Extraction Definition Extract the following information(called field) on Medication experienced by the patient from discharge summary: Medications (m): names, brand names, generics, and collective names of prescription substances, over the counter medications, and other biological substances Dosages (do): indicating the amount of a medication Modes (mo): indicating the route for administering the medication Frequencies (f): indicating how often each dose of the medication should be taken. Durations (du): indicating how long the medication is to be administered. Reasons (r): stating the medical reason for which the medication is given. List/narrative (ln): indicating whether the medication information appears in a list structure or in narrative running text in the discharge summary.

Data Preparation 160 Discharge Summaries Training Data Testing Data Annotated by Physician, revised by the researcher 130 30 The annotation process took approximately 1.5 hours per record due to the length of clinical records.

Outline Methodology Results & Discussion Conclusion Extraction Definition Data Preparation System Architecture Results & Discussion NER(CRF) Experiment Relationship Classification (SVM) CONTEXT Engine Evaluation Conclusion

System Architecture Basic strategy for medication event extraction Use CRF to identify the entities, including medication, dosage, frequency, mode, etc. Build pairs for each medication relationship (only consider drug and its related entity). Classify the binary relationship by SVM Generate medication entries based on the results from the CRF and SVM.

System Architecture Basic strategy for medication event extraction

System Architecture CRF feature builder 7 feature sets were built for CRF, including drug, dosage, mode, frequency, duration, reason, morphology. Many other features were also used: the medical category for each word, whether the word is capitalized , etc. Use backward elimination to get the best useful feature sets. The context window for the CRF was set to be five words.

System Architecture Basic strategy for medication event extraction

System Architecture SVM Convertor converts CRF results into SVM input: Unigram Sentences Each pair of medication elements at the unigram sentence level is used to build an SVM training record. Sentence Pairs MEDICATION and its REASON could be across two sentences. Like the mechanism to generate the unigram sentence input, medication pairs are also built at the sentence pair level.

System Architecture SVM Features built based on the input data: 1. Three words before and after the first entity. 2. Three words before and after the second entity 3. Words between the two entities. 4. Words inside of each entity. 5. The types of the two entities determined by the CRF classifier. 6. The entities types between the two entities.

System Architecture Basic strategy for medication event extraction

System Architecture Context Engine Medication Entry Generation The CONTEXT engine identifies the medication en-try under the special section headings, such as “MEDICATIONS ON ADMISSION:”, “DISCHARGE MEDICATIONS:” etc., or in the narrative part of the clinical record. Medication Entry Generation The results from the previous steps are used here, namely CRF, SVM and CONTEXT Engine.

Outline Methodology Results & Discussion Extraction Definition Data Preparation System Architecture Results & Discussion NER(CRF) Experiment Relationship Classification (SVM) CONTEXT Engine Evaluation Final output evaluation

NER (CRF) results The comparison of the performance for exact match by using the 7 feature sets and bag of words feature sets (baseline, in bracket).

NER (CRF) results The F scores for Duration and Reason by using the 7 features sets are approximately 10% higher than baseline, because: The frequencies for the REASON and DURATION are much smaller than the other four entity types. For the DURATION entities, the rule based regular expression can match other non-medication terms (low precision). Some DURATION terms that can’t be discovered by our rules (low recall). REASON extraction depends highly on the Finding category in SNOMED CT and the performance of TTSCT (Patrick et al. 2007).

NER (CRF) results The F scores for Mode, Dosage and Frequency were improved by 2%. These errors come from: 1. Misspelling of drug names, such as “nitrog-lycerin” . 2. Drug names used in other contexts, such as the “coumadin” in the “Coumadin Clinic” phrase. 3. The drug allergies detector cannot cover all situations.

Relation Classification The comparison of the performance for relation classification by using the all feature sets and subset feature sets (1,2,4; baseline, in bracket) in SVM. The baseline F-score for the HAS RELATIONSHIP set of the unigram sentence level is 70.38% and 95.20% in the NO RELATIONSHIP set. The difference can be attributed to the fact that the total number of the NO RELATIONSHIP set is 7 times larger than the HAS RELATIONSHIP set. high performance is achieved in which the F-score for the “has relation” set of the unigram sen-tence level is 98.39%, while 96.47% is achieved in the bigram sentence level indicating little if any systematic errors.

CONTEXT Engine Evaluation The CONTEXT engine was adopted to discover the span of the medication list (the span between the medication heading and the next following heading).

Final Output Evaluation Due to the errors in the NER, Relationship Classification and Medication Entry Generator, the final F-scores for each entity type are lower than in the NER processing. The final scores for the medication event are between 86.23%. The identification of medication is low, which cause the lower relationship identification among other medication events. The frequency of appearance of multiple REASONs is relatively high, and the multiple REASONs should be used to construct multiple medication entries in the gold standard. In this way, the loss in REASON recognition would lead to the decrease in recall of all other entity types and the medication event.

Thank you!