MITRE system for clinical assertion status classification
| Autor: | David Tresner-Kirsch, Alexander S. Yeh, Ben Wellner, Matthew Coarr, Lynette Hirschman, Cheryl Clark, John S. Aberdeen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2011 |
| Předmět: |
Conditional random field
Document Structure Description Computer science Health Informatics computer.software_genre Research and Applications Pattern Recognition Automated Leverage (statistics) Data Mining Electronic Health Records Humans Pattern matching Natural Language Processing business.industry Principle of maximum entropy Assertion Uncertainty Decision Support Systems Clinical Semantics Statistical classification Artificial intelligence Cues business computer Classifier (UML) Natural language processing |
| Popis: | Objective To describe a system for determining the assertion status of medical problems mentioned in clinical reports, which was entered in the 2010 i2b2/VA community evaluation ‘Challenges in natural language processing for clinical data’ for the task of classifying assertions associated with problem concepts extracted from patient records. Materials and methods A combination of machine learning (conditional random field and maximum entropy) and rule-based (pattern matching) techniques was used to detect negation, speculation, and hypothetical and conditional information, as well as information associated with persons other than the patient. Results The best submission obtained an overall micro-averaged F-score of 0.9343. Conclusions Using semantic attributes of concepts and information about document structure as features for statistical classification of assertions is a good way to leverage rule-based and statistical techniques. In this task, the choice of features may be more important than the choice of classifier algorithm. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|