User Tools

Site Tools


projects:workgroups:nlp-wg

This is an old revision of the document!


OHDSI Natural Language Processing Working Group

Objective

The primary goal of the NLP working group is to promote the use of textual information from Electronic Health Records (EHRs) for observational studies under the OHDSI umbrella. To facilitate this objective, the group will develop methods and software that can be implemented to utilize clinical text for studies by the OHDSI community.

Project Lead

Project Coordinator

Vipina K Keloth

OHDSI NLP WG Monthly Meeting

When: Second Wednesday of every month at 1 PM - 2 PM CT

Where: Click here to join the meeting

Monthly Research Webinar: Upcoming - October 13, 2021 (as part of the WG meeting)

Title: Harnessing Big Data for Population Health: Advancing NLP Techniques to Extract Social-Behavioral Risk Factors from Free Text within Large Electronic Health Record Systems
Abstract: Social and Behavioral Determinants of Health (SBDH) are powerful drivers of future well-being of individuals, but the clinical community rarely has access to standardized tools to systematically incorporate SBDH into clinical research and decision-making. To address this, we have been creating fundamental resources to systematically identify SBDH from within health records. We incorporate a wide range data sources such as coded clinical data (ICD codes), encoded questionnaires, and annotated texts corpora, and we apply a variety of NLP and AI methods such as heuristic-based natural language inference, conventional machine learning, and contextual neural network models. At the same time, we also focus on the dissemination of our methods and collaborating with external partners to ensure the generalizability of our models across various health systems. Results for heuristic-based, deep learning and ensemble models are promising and we have successfully validated our models on external partners sites.

Presenter: Dr. Masoud Rouhizadeh
Masoud Rouhizadeh is an Assistant Professor in the University of Florida College of Pharmacy, Department of Pharmaceutical Outcomes, under the AI in the Health Sciences Initiative. The primary focus of Dr. Rouhizadeh’s research involves applying machine learning and natural language processing methods for identifying clinical concepts from unstructured text and converting them into structured data. Another major part of his research has been developing clinical ontologies and lexical resources, as well as computational models for identifying social and behavioral determinants of health. Before joining the UF, Dr. Rouhizadeh was a Faculty Instructor at Biomedical Informatics and Data Science and the Natural Language Processing lead at the Institute for Clinical and Translational Research at the Johns Hopkins University School of Medicine. Prior to JHU, he was a postdoctoral fellow at the University of Pennsylvania’s World Well-Being Project and then at the Penn Institute for Biomedical Informatics. He obtained his Master’s and Ph.D. in Computer Science and Engineering from Oregon Health and Science University and his Master’s in Human Language Technology from the University of Trento, Italy.

Ongoing Projects

  • Clinical Abbreviations
  • Post-acute sequelae of SARS-CoV-2 infection (PASC) study
  • Extraction, Transformation, and Load Process (ETL)
  • Note type normalization
  • Open source Python NLP package

Past Projects

  • Note_NLP table
  • COVID-19 testing normalization (TestNorm)
  • Note type
  • NLP tools: NLP Wrappers; THEIA; Ananke

Participants

Participants
Hua Xu Abraham Hartzema Feifan Liu
Anupama Gururaj David Sontag Paris Nicolas
Nigam Shah Arnab Bose Mark Dredze
Noemie Elhadad Lian Hu Masoud Rouhizadeh
Jon Duke Jan A Kors Malcolm McRoberts
Alexandre Yahi J van Der Lei Nishanth Parameshwar Pavinkurve
Thomas Ginter Peter R Rijnbeek Carol Friedman
Olga Patterson Vivienne Zhu Miao Chen
George Hripsack Bob Patterson Jianlin Shi
Vojtech Huser Michael Gurley Vassilis Koutkias
Mark Khayter Xiaoling Chen Dan Schlegel
Karthik Natarajan Hongfang Liu Mark V Mai
Min Jiang Hong Yu Todd Lingren
Scott DuVall Stephane Meystre Jose Posada
Xiao Dong Timothy Miller Andrew E Williams
Ning Shang Wendy Chapman Vignesh Srinivasan
Jessie Tenenbaum Elizabeth Marshall Yuan Luo
Kathleen Nogueira Noa Palmon Kelly Peterson
Chris Ryan Danielle Bitterman Jimyung Park
Kate Weber Alexander Sivura Patrick Alba
Tarun Xi Yang Meliha Yetisgen
T.M. Seinen Jiang Bian Xiyu Ding
Georgina Kennedy Yaoyun Zhang Rui Zhang
Paul Heider

Upcoming Meeting Dates (2021)

  • October 13
  • November 10
  • December 8

Repository

Past WG meetings (Agenda/Minutes/Recordings)

Microsoft Teams meeting

Join on your computer or mobile app

Click here to join the meeting

Learn More

projects/workgroups/nlp-wg.1633443554.txt.gz · Last modified: 2021/10/05 14:19 by vipina