Adverse drug event detection using reason assignments in FDA drug labels.
Adverse drug event detection using reason assignments in FDA drug labels.
复制标题
DOI:
10.1016/j.jbi.2020.103552
复制
发表时间:
2020-10
影响因子:
4.5
通讯作者:
McInnes BT
中科院分区:
文献类型:
--
作者:
Sutphin C;Lee K;Yepes AJ;Uzuner Ö;McInnes BT
Adverse drug events (ADEs) are unintended incidents that involve the taking of a medication. ADEs pose significant health and financial problems worldwide. Information about ADEs can inform health care and improve patient safety. However, much of this information is buried in narrative texts and needs to be extracted with Natural Language Processing techniques, in order to be useful to computerized methods. In this paper, we present three methods consisting of a Conditional Random Field (CRF), a bi-directional Long Short Term Memory Unit with a CRF (bi-LSTM+CRF), and several ensembles of the two for extracting ADEs and their reason from FDA Drug Labels. We map extracted ADEs to the Medical Dictionary for Regulatory Activities (MedDRA) terminology for normalization. We show that each of the CRF and bi-LSTM+CRF perform well on our task, but their combination is even stronger, achieving 0.93 F1 in identification and 0.54 F1 in normalization.
登录
查看更多内容
影响因子:
4.2
作者:
Harpaz, Rave;Callahan, Alison;Tamang, Suzanne;Low, Yen;Odgers, David;Finlayson, Sam;Jung, Kenneth;LePendu, Paea;Shah, Nigam H.
通讯作者:
Shah, Nigam H.
影响因子:
4.5
作者:
Sarker, Abeed;Ginn, Rachel;Nikfarjam, Azadeh;O'Connor, Karen;Smith, Karen;Jayaraman, Swetha;Upadhaya, Tejaswi;Gonzalez, Graciela
通讯作者:
Gonzalez, Graciela
影响因子:
5.3
作者:
Hristovski, Dimitar;Kastrin, Andrej;Rindflesch, Thomas C.
通讯作者:
Rindflesch, Thomas C.
DOI:
10.1093/bioinformatics/btp049
发表时间:
2009-03-15
期刊:
Bioinformatics (Oxford, England)
影响因子:
--
作者:
Hur J;Schuyler AD;States DJ;Feldman EL
通讯作者:
Feldman EL
影响因子:
3.5
作者:
Li, Qi;Deleger, Louise;Solti, Imre
通讯作者:
Solti, Imre