Abstract
Medical discharge summaries or patient prescriptions contain variety of medical terms. The semantic relation extraction between medical terms is essential for discovery of significant medical knowledge. The relation classification is one of the imperative tasks of biomedical information extraction. The automatic identification of relations between medical diseases, tests and treatments can improve the quality of patient care. This paper presents the deep learning based proposed system for relation extraction between medical entities. In this paper, convolution neural network is used for relation classification. The system is divided into four modules: word embedding, feature extraction, convolution and softmax classifier. The output contains classified relations between medical entities. In this work, data set provided by I2b2 2010 challenge is used for relation detection which consisted of total 9070 relations in test data and 5262 total relations in train data. The performance evaluation of relation extraction task is done using precision and recall. The system achieved average 75% precision and 72% recall. The performance of the system is compared with awarded i2b2 participated systems. Keywords: Convolution Neural Network;Feature Extraction;Relation Classification;Word Embedding.
Highlights
Relation extraction is an essential task of biomedical text mining
How any medical difficulty is related to symptoms, syndrome, and treatment, which tests will be required for disease diagnosis? These types of information are required in health care and clinical procedures
The system is proposed for medical relation extraction which is based on the concept of deep learning
Summary
Relation extraction is an essential task of biomedical text mining. How any medical difficulty is related to symptoms, syndrome, and treatment, which tests will be required for disease diagnosis? These types of information are required in health care and clinical procedures. Relation extraction is the task of classification in which a pair of relations between medical entities can be identified It is the core clinical information identification problem that identifies semantic relations between medical concepts problem, test, and treatment in discharge summaries [13]. It is one of the challenging tasks of i2b2 2010 NLP challenges. Relation extraction is divided into various types according to their usage such asTrIPindicates treatment improvement with problem, TrWP (treatment worsen the medical problem), TrCP (treatment causes the medical problem), TrAP (treatment is administered for the medical problem) and TrNAP(treatment is not administered because of the medical problem), other for test with problem TeRP (test shows the medical problem), TeCP (test conducted to investigate medical problem) and the problem with other problem indicates PIP (problem indicates problem) [1]. Relation between Medical problem and Medical problem does not exist other than PIP
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
