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

The Next Normal: Supporting Biomedical Discovery, Clinical Practice, and Self-Care

As we start year three of the COVID-19 pandemic, it’s time for NLM to take stock of the parts of our past that will support the next normal and what we might need to change as we continue to fulfill our mission to acquire, collect, preserve, and disseminate biomedical literature to the world.

Today, I invite you to join me in considering the assumptions and presumptions we made about how scientists, clinicians, librarians and patients are using critical NLM resources and how we might need to update those assumptions to meet future needs. I will give you a hint… it’s not all bad—in fact, I find it quite exciting!

Let’s highlight some of our assumptions about how people are using our services, at least from my perspective. We anticipated the need for access to medical literature across the Network of the National Library of Medicine and created DOCLINE, an interlibrary loan request routing system that quickly and efficiently links participating libraries’ journal holdings. We also anticipated that we were preparing the literature and our genomic databases for humans to read and peruse. Now we’re finding that more than half of the accesses to NLM resources are generated and driven by computers through application programming interfaces. Even our MedlinePlus resource for patients now connects tailored electronic responses through MedlinePlus Connect to computer-generated queries originating in electronic health records.

Perhaps, and most importantly, we realize that while sometimes the information we present is actually read by a living person, other times the information we provide—for example, about clinical trials (ClinicalTrials.gov) or genotype and phenotype data (dbGaP)—is actually processed by computers! Increasingly, we provide direct access to the raw, machine-readable versions of our resources so those versions can be entered into specialized analysis programs, which allow natural-language processing programs to find studies with similar findings or machine-learning models to determine the similarities between two gene sequences. For example, NLM makes it possible for advocacy groups to download study information from all ClinicalTrials.gov records so anyone can use their own programs to point out trials that may be of interest to their constituents or to compare summaries of research results for related studies.

Machine learning and artificial intelligence have progressed to the point that they perform reasonably well in connecting similar articles—to this end, our LitCovid open-resource literature hub has served as an electronic companion to the human curation of coronavirus literature. NLM’s LitCovid is more efficient and has a sophisticated search function to create pathways that are more relevant and are more likely to curate articles that fulfill the needs of our users. Most importantly, innovations such as LitCovid help our users manage the vast and ever-growing collection of biomedical literature, now numbering more than 34 million citations in NLM’s PubMed, the most heavily used biomedical literature citation database.

Partnerships are a critical asset to bring biomedical knowledge into the hands (and eyes) of those who need it. Over the last decade, NLM moved toward a new model for managing citation data in PubMed. We released the PubMed Data Management system that allows publishers to quickly update or correct nearly all elements of their citations and that accelerates the delivery of correct and complete citation data to PubMed users.

As part of the MEDLINE 2022 Initiative, NLM transitioned to automated Medical Subject Headings (MeSH) indexing of MEDLINE citations in PubMed. Automated MeSH indexing significantly decreases the time for indexed citations to appear in PubMed without sacrificing the quality MEDLINE is known to provide. Our human indexers can focus their expertise on curation efforts to validate assigned MeSH terms, thereby continuously improving the automated indexing algorithm and enhancing discoverability of gene and chemical information in the future.

We’re already preparing for the next normal—what do you think it will be like?

I envision making our vast resources increasingly available to those who need them and forging stronger partnerships that improve users’ ability to acquire and understand knowledge. Imagine a service, designed and run by patients, that could pull and synthesize the latest information about a disease, recommendations for managing a clinical issue, or help a young investigator better pinpoint areas ripe for new interrogation! The next normal will make the best use of human judgment and creativity by selecting and organizing relevant data to create a story that forms the foundation of new inquiry or the basis of new clinical care. Come along and help us co-create the next normal!

%d bloggers like this: