This is a DEMO of adverse drug reaction search engine (ADRSE) which takes a drug name as input and listed related ADRs and their references. The Demo is implemented with Deep Learning and Natural Language Processing techniques. Specifically, over 26,000 Pubmed abstracts (1975-2020) are retrieved and then, drug mentions are recognized by utilizing BiLSTM-CRF network and ADR mentions are recognized by using BiLSTM-GAT-CRF network. The relations between drugs and ADRs are extracted using both sentence- and document-level relation extraction methods (See the references for the specific methods). Finally, all the relations are integrated.

http://www.medicalqa.xyz:29290/solr/adr/home

DALIAN UNIVERSITY OF TECHNOLOGY (大连理工大学)

Zhihao Yang(杨志豪)

yangzh@dlut.edu.cn

Exploiting Adversarial Transfer Learning for Adverse Drug Reaction Detection from Texts. Journal of Biomedical Informatics, 2020: 103431

[{"id":"2016YFC0901902","name":"2016YFC0901902"}]