Star InactiveStar InactiveStar InactiveStar InactiveStar Inactive

Abstract: An adverse event is an injury to a patient and an adverse drug event is an injury to a patient resulting from a medical intervention related to pharmacotherapy. Adverse drug events complicate two million hospital stays annually, are associated with a prolonged hospital stay, account for upwards of two thirds of post-discharge complications, and are a significant contributor to escalating health care costs. The Office of Disease Prevention and Health Promotion has identified adverse drug event prevention as a patient safety priority. Electronic health records (EHRs) contain important adverse drug event-related information and manual chart review is prohibitively expensive. In contrast, biomedical natural language processing (NLP) provides automated tools that facilitate chart review and can improve patient drug safety surveillance and post-marketing pharmacovigilance through enhanced cost efficiencies and provision of real-time information. In this talk, I will first introduce an expert-annotated EHR corpus we developed. I will then describe several new deep neural network models (e.g., LSTM-CRF and memory-augmented NNs) we developed to build the state-of-the-art NLP systems for automated medication and adverse drug event detection from EHR narratives. I will also describe Item Response Theory (IRT) as a new evaluation metrics for NLP systems. Unlike the traditional evaluation metrics of recall/precision/F-score, IRT models characteristics of individual data points (called “items”) such as difficulty and discriminatory ability to estimate ability as a function of the characteristics of correctly answered items. Based on our IRT analysis, we found that deep neural network models exhibit human-like learning process and intelligence capabilities. Our work is an important step towards ADE surveillance and pharmacovigilance.


Bio: Professor Yu is an elected fellow of the American College of Medical Informatics and a tenured full professor in the Department of Computer Science, University of Massachusetts, Lowell. She is also an adjunct professor in the Department of Medicine at the University of Massachusetts Medical School, and in the College of Information and Computer Science at the University of Massachusetts, Amherst. She is a Research Health Scientist at the Bedford VA Medical Center.

Star InactiveStar InactiveStar InactiveStar InactiveStar Inactive

NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE1.0)

 hosted by University of Massachusetts Lowell, Worcester, Amherst

User Rating: 5 / 5

Star ActiveStar ActiveStar ActiveStar ActiveStar Active




Job Title: Computational Linguistics Post-Doctoral Fellowship

Location:Worcester, Massachusetts, USA

Description: We are recruiting for multiple positions to participate research development in biomedical natural language processing (NLP) and biomedical informatics. The group’s research ( involves developing NLP and text mining approaches for gathering, analyzing and interpreting heterogeneous data from multiple text sources, including social media, literature, textbooks, and electronic health records. Recruits will develop deep learning, reinforcement learning and other machine learning approaches for big data analysis.

Requirements:PhD in Computer Science, Computational Linguistics or Biomedical Informatics with expertise in natural language processing, machine learning or information retrieval with excellent writing and communication skills and ability to work with the research team.

Application: If you are highly motivated and passionate about research in big data research, please contact Elaine Freund ( with your resume or CV and a cover letter.






Job Title: Research Assistant/Internship in Biomedical Informatics

Summer Internship (with possibility of extension)

Unpaid, Academic Credit is Required

Hours per week: 10 - 40

On/Off Campus: Off Campus – Worcester, MA – must be able to be onsite 1 to 2 days/week

The BioNLP group at UMass Medical School is seeking a research assistant (full-time or part-time; starting from May or June; 2~3 months with possibility to extend) to join our cutting-edge application-oriented research in biomedical natural language processing (NLP) and biomedical informatics. Ideal candidates for this position can carry out at least one of the essential duties and other occasional duties. Exceptional candidates will have opportunities to participate in publishable work.

Essential Duties:

  • Train/test/develop/apply machine learning and natural language processing tools for biomedical text mining
  • Build software (web service and standalone tools) to work with biomedical researchers and healthcare providers and systems
  • Collect and develop tools for text data pre-processing (e.g. parsing XML files, converting format between text data files)
  • Collect and integrate biomedical knowledge bases (using mysql)

Other Duties (occasional):

  • Assist literature review on biomedical informatics
  • Assist preparing research report and presentations (e.g., creating figures, tables, reference lists etc.)


  • College students or higher degrees in computer science or related field
  • Solid programming skills in Java, Python, Perl or C++
  • Proficient in Unix/Linux environment, data structures, distributed computing , data storage
  • Experience in machine learning and natural language processing is a plus
  • Experience with MySQL programming is a plus
  • Experience with MATLAB is a plus
  • Ability to work independently with minimum supervision
  • Results oriented and able to meet deadlines and targets
  • Capable to establish and foster healthy working relationships with people across all levels
  • Excellent communication skills

Application: Applicants please email <> with a 1~2 page resume including a list of relevant projects, coursework and grades (official transcript not required). Applicants are encouraged to include a 1-page cover letter to briefly state your background, knowledge and skills that are directly related to the job duties.

Star InactiveStar InactiveStar InactiveStar InactiveStar Inactive

Abstract: Data scientific approaches can be used to develop novel ways to measure and improve patient safety, health care quality and patient experience. Dr. Salmasian will briefly explain some examples of such projects which can highlight the importance of data science in helping formulate better questions about patient safety and patient experience before attempting to answer them.

Bio: Dr. Salmasian is Program Director for Data Science and Evaluation at Brigham and Women's Hospital. Trained both as a physician and as an informatician, he is passionate about using technology to assess and improve quality and safety of health care delivery. He also has a strong background in epidemiology, research methodology and biostatistics. Dr. Salmasian has published more than 35 peer-reviewed papers in top scientific journals, include Journal of American Medical Informatics Association (JAMA), JAMA Internal Medicine, and Cell. He has also served as a reviewer for the top health care informatics journals and conferences.

Star InactiveStar InactiveStar InactiveStar InactiveStar Inactive


Mailing Address:

55 Lake Avenue North (AC7-059), Worcester, MA 01655


(508) 856-3474


Directions to UMass Worcester, as well as a map of the UMass Medical School campus and its parking lots, are available in this PDF. Our group is located in the Albert Sherman Center, which is highlighted on the campus map.