Meet the NLM Investigators: Dr. Demner-Fushman Knows the Answers to Your Questions!

Meet my close colleague, Dr. Dina Demner-Fushman! This brilliant researcher is the face behind what many of you have already accessed on NLM’s websites. Many of you will agree with me when I say that having one PhD is extremely impressive–but would you believe she has TWO?! In addition to her master’s degree, Dr. Demner-Fushman has PhDs in immunology and computer science.

Dr. Demner-Fushman and her team use advanced artificial intelligence (AI), natural language processing, and data mining techniques to answer consumers’ questions about a variety of health topics. Did you know that it was Dr. Demner-Fushman’s research that led to the developmental stages of the indexing initiative that produced the current iteration of the MEDLINE resource? This work helps all of us navigate a plethora of NLM resources.

Check out the infographic below to learn more about the innovative, important research happening in Dr. Demner-Fushman’s lab.

Infographic titled: Biomedical Question Answering. The title area features a picture of Dr. Demner-Fushman along with her title and accreditations (MD, Phd): Investigator, Computational Health. The first column of the graphic explores her short and long-term goals  for her projects. The center column describes the processes she uses to achieve these goals, and the last column depicts a simple graphic illustrating a Q and A service.

What makes your team unique? Tell us more about the people working in your lab.   

It is a diverse, multicultural team. Some were even born after I got my first IT job checking computers at Hunter College for Y2K compliance. The team is united by the task of enabling computers to understand health-related information needs and the socioeconomic and professional status of people who come to NLM seeking information. It is a group of exceptionally dedicated and talented people. Our diverse backgrounds make us see all possible aspects of addressing the informational and emotional needs of our users. 

What is your advice for young scientists or people interested in pursuing a career in research?  

  • Be proactive: Seek information and take advantage of training opportunities.  
  • Be brave: Admit you don’t know or don’t understand something. Most people will try to help.  
  • Be bold: Reach out to people who you would like to work with or to discuss your ideas.  
  • Be honest.  
  • Be patient: Research implies working hard, sometimes without immediate results. Even if research is your passion and fun, sometimes you have to do things that you might not enjoy or you might fear but still have to do, like giving talks or writing paper.

What do you enjoy about working at NLM?  

The community of dedicated people across all divisions, the mission, and the intellectual freedom.  

Where are you planning to travel to this year?  

I was just in Dublin, Ireland, in May for the 60th meeting of the Association for Computational Linguistics and co-chaired the BioNLP workshop for the 15th time. I loved Dublin when I visited shortly before the pandemic. I enjoyed revisiting a place I loved and discovering new things to love.

What are you reading right now?  

In the Garden of Beasts by Erik Larson. It provides an amazing view of pre-World War II Germany and political relations. I hope some lessons have been learned! 

You’ve read her words, now hear them for yourself. Follow our NLM YouTube page for more exciting content from the NLM staff that make it all possible. If you’d like to learn more about our Intramural Research Program (IRP), view job opportunities, and explore research highlights, I invite you to explore our recently redesigned NLM IRP webpage.

Transcript [Demner-Fushman]*: When people need information, what they really like is to ask a question and get a really good comprehensive answer, and to also know that the answer is true and correct.

When I started my independent clinician career, I had lots of questions, but I was sometimes not even sure if I was getting the right answer. “Question answering” is this system to understand the question, what the question is about, and why it is asked. When the answer is found, it’s usually not a single answer: It’s parts of the answer in different places. It’s multiple answers. So, all of that then needs to be condensed into one comprehensive answer with evidence of where the answer came from. So that’s the focus of my research.

On the surface, very similar questions asked by clinicians and by the public should be answered very differently. Different deep-learning systems are needed to find the answers to the same question asked by two different people.

The long-term goal is one entry point to all the NLM resources. It doesn’t matter who the person is and how they ask their question or look for information. We should be able to recognize what the person needs and provide it. There is no one—other than NLM—who is specifically dedicated to biomedical information retrieval and biomedical question answering. Although it seems industry is doing that kind of research as well, it is not their main focus, whereas we keep people focused on what really matters for health and advancing medicine.

*Transcript edited for clarity

%d bloggers like this: