![]() | Only 14 pages are availabe for public view |
Abstract The Clinical E-Science Framework (CLEF) project is used to extract important information from medical texts by building a system for the purpose of clinical research, evidence-based healthcare and genotype-meets-phenotype informatics. The system is divided into two parts, one part concerns with the identification of relationships between clinically important entities in the text. The full parses and domain-specific grammars had been used to apply many approaches to extract the relationship. In the second part of the system, statistical machine learning (ML) approaches are applied to extract relationship. A corpus of oncology narratives that hand annotated with clinical relationships can be used to train and test a system that has been designed and implemented by supervised machine learning (ML) approaches. Many features can be extracted from these texts that are used to build a model by the classifier. Multiple supervised machine learning algorithms can be applied for relationship extraction. Effects of adding the features, changing the size of the corpus, and changing the type of the algorithm on relationship extraction are examined. System has been built and implemented using different supervised machine learning algorithms for relation extraction and trained and tested it on a corpus of oncology narratives hand annotated with clinically important relationships. Over five algorithms, the system achieved F1-score 76.3% for support vector machine algorithm. Adding different non syntactic feature sets leads to improve the performance but adding syntactic feature sets leads to DROP the performance of the system. from the results, it is possible to extract clinical relationships from patient files, using supervised statistical ML techniques. Support vector machine (SVM) is much suitable algorithm for large corpus. Using large corpus in the model leads to improve the accuracy. |