SODA — Extracting information from clinical narratives for Clinical Outcomes Research

Project Summary

Main architecture of the LSTM with a CRFs layer model.

Paper: Identifying relations of medications with adverse drug events using recurrent convolutional neural networks and gradient boosting

Workflow of the NER module.

Paper: MADEx: A System for Detecting Medications, Adverse Drug Events, and Their Relations from Clinical Notes

J. J. Deferio, S. Breitinger, D. Khullar, A. Sheth, and J. Pathak, “Social determinants of health in mental health care and research: a case for greater inclusion,” J Am Med Inform Assoc, vol. 26, no. 8–9, pp. 895–899, Aug. 2019. [PubMed]
X. Yang, J. Bian, R. Fang, R. I. Bjarnadottir, W. R. Hogan, and Y. Wu, “Identifying relations of medications with adverse drug events using recurrent convolutional neural networks and gradient boosting,” J Am Med Inform Assoc. [PubMed]
X. Yang, J. Bian, Y. Gong, W. R. Hogan, and Y. Wu, “MADEx: A System for Detecting Medications, Adverse Drug Events, and Their Relations from Clinical Notes,” Drug Saf, vol. 42, no. 1, pp. 123–133, Jan. 2019. [PubMed]
Y. Wu, X. Yang, J. Bian, Y. Guo, H. Xu, and W. Hogan, “Combine Factual Medical Knowledge and Distributed Word Representation to Improve Clinical Named Entity Recognition,” AMIA Annu Symp Proc, vol. 2018, pp. 1110–1117, Dec. 2018. [PubMed]