Guest post by Joyce Backus and Kathel Dunn, both from NLM’s Division of Library Operations.
As shrinking budgets tighten belts at hospitals and academic institutions, medical libraries have come under scrutiny. In response, librarians have had to articulate the value they bring to the institution and to the customers—students, researchers, clinicians, or patients—they serve.
In 2011-2012, as such scrutiny swelled, Joanne Marshall and her team set out to study the very question these medical institutions faced: Do libraries add value? They collected 16,122 individual responses from health professionals at 118 hospitals served by 56 health libraries in the United States and Canada. The team sought to determine whether physicians, residents, and nurses perceived their libraries’ information resources as valuable and whether the information obtained impacted patient care.
We re-discovered (as has been written about before) the value of MEDLINE in changing patient care. We also found its preeminent role shines even more brightly in a dataset like this one that includes other sources. We saw the significance of MEDLINE as a single source of information but also as a source used in combination with full-text journals, books, drug databases, websites, and colleague consultations.
We were reminded, too, of the importance of the National Network of Libraries of Medicine (NNLM) to our work; the trust in the NNLM; each library’s connectedness to the other; and how the everyday web of relationships prompts cooperation and collaboration, including the successful implementation of the value of libraries study itself.
For us this re-discovery comes at a key time, when we’re examining NLM products and services as part of the strategic planning process. We are actively identifying methodologies and tools to elevate all our collections—from datasets to incunabula—and make them greater engines of discovery in service of health.
But what about your library’s resources?
The data mining challenge we gave ourselves is our guide for medical librarians everywhere: look at your data, what’s in front of you, and then others’ data. What can they tell you about what’s happening now, what will likely happen in the future, what’s being used, and how it’s being used?
Guest post by Lisa Lang, head of NLM’s National Information Center on Health Services Research and Health Care Technology
Singer-actress Selena Gomez shocked her fans this past September with the announcement that she had received a kidney transplant to combat organ damage caused by lupus.
Lupus, an autoimmune condition, strikes women much more than men, with minority women especially vulnerable. Not only is lupus two to three times more common in African American women than in Caucasian women, but recent studies funded by the CDC suggest that, like Ms. Gomez, Hispanic and non-Hispanic Asian women are more likely to have lupus-related kidney disease (lupus nephritis)—a potentially fatal complication.
Documenting such health disparities is crucial to understanding and addressing them. Significantly, the studies mentioned above are the first registries in the United States with sufficient Asians and Hispanics involved to measure the number of people diagnosed with lupus within these populations.
Investment in research examining potential solutions for health care disparities is essential.
In 2014, The Lancet featured a study that examined patterns, gaps, and directions of health disparity and equity research. Jointly conducted by the American Academy of Medical Colleges and AcademyHealth, a non-profit dedicated to enhancing and promoting health services research and a long-time NLM partner, the study examined changes in US investments in health equities and disparities research over time. Using abstracts in the NLM database HSRProj (Health Services Research Projects in Progress), the researchers found an overall shift in disparities-focused projects. From 2007 to 2011, health services research studies seeking to document specific disparities gave way to studies examining how best to alleviate such disparities. In fact, over half of the disparities-focused health services research funded in 2011 “aimed to reduce or eliminate a documented inequity.” The researchers also found significant differences in the attention given to particular conditions, groups, and outcomes. An update by AcademyHealth (publication forthcoming) found these differences continue in more recently funded HSR projects.
Lupus is one such condition. Research into this disease’s prevalence and impact among Hispanics is underway, but more attention may be warranted. There are almost 100 active clinical studies in the US targeting lupus currently listed in ClinicalTrials.gov and, of these, 15 address lupus nephritis. And while about 5% of ongoing or recently completed projects in the HSRProj database explicitly focus on Hispanic populations, only one, funded by the Patient-Centered Outcomes Research Institute, specifically addresses lupus. (You can see this study’s baseline measures and results on ClinicalTrials.gov.)
Perhaps a celebrity like Ms. Gomez publicly discussing her experience with lupus will spark more attention from both researchers and the public seeking to contribute to knowledge and cures.
After all, we are all both fundamentally unique and alike. Reducing—or better yet, eliminating—health disparities benefits us all.
Guest blogger Lisa Lang is Assistant Director for Health Services Research Information and also Head of NLM’s National Information Center on Health Services Research and Health Care Technology (NICHSR).
Photo credit (The Scales of Justice, top): Darius Norvilas [Flickr (CC BY-NC 2.0)] | altered background
Guest post by Dina Demner-Fushman, MD, PhD, staff scientist at NLM.
“So, what do you do for a living?”
It’s a natural dinner party question, but my answer can prompt that glazed-over look we all dread.
I am a computational linguist, also known (arguably) as a specialist in natural language processing (NLP), and I work at the National Library of Medicine.
If I strike the right tone of excitement and intrigue, I might buy myself a few minutes to explain.
My work combines computer science and linguistics, and since I focus on biomedical and clinical texts, it also requires adding some biological, medical, and clinical know-how to the mix.
I work specifically in biomedical natural language processing (BioNLP). The definition of BioNLP has varied over the years, with the spotlight shifting from one task to another—from text mining to literature-based discovery to pharmacovigilance, for example—but the core purpose has remained essentially unchanged: training computers to automatically understand natural language to speed discovery, whether in service of research, patient care, or public health.
The field has been around for a while. In 1969 NIH researchers Pratt and Pacak described the early hope for what we now call BioNLP in the paper, “Automated processing of medical English,” which they presented at a computational linguistics conference:
The development of a methodology for machine encoding of diagnostic statements into a file, and the capability to retrieve information meaningfully from [a] data file with a high degree of accuracy and completeness, is the first phase towards the objective of processing general medical text.
NLM became involved in the field shortly thereafter, first with the Unified Medical Language System (UMLS) and later with tools to support text processing, such as MetaMap and TextTool, all of which we’ve improved and refined over the years. The more recent Indexing Initiative combines these tools with other machine learning methods to automatically apply MeSH terms to PubMed journal articles. (A human checks the computer’s work, revising as needed.)
These and NLM’s other NLP developments help improve the Library’s services, but they are also freely shared with the world, broadening our impact but more importantly, helping to handle the global proliferation of scientific and clinical text.
It’s that last piece that makes NLP so hot right now.
NLP, we’re finding, can take in large numbers of documents and locate relevant content, summarize text, apply appropriate descriptors, and even answer questions.
It’s every librarian’s—and every geek’s—dream.
But how can we use it?
Imagine, for example, the ever-expanding volume of health information around patients’ adverse reactions to medications. At least four different—and prolific—content streams feed into that pool of information:
the reactions reported in the literature, frequently in pre-market research (e.g., in the results of clinical trials);
the labeled reactions, i.e., the reactions described in the official drug labels provided by manufacturers;
the reactions noted in electronic health records and clinical progress notes; and
the reactions described by patients in social media.
NLM’s work in NLP—and its funding of extramural research in NLP—is helping develop approaches and resources for extracting and synthesizing adverse drug reactions from all four streams, giving a more complete picture of how people across the spectrum are responding to medications.
It’s a challenging task. Researchers must address different vocabularies and language structures to extract the information, but NLP, and my fellow computational linguists, will, I predict, prove up to it.
Now imagine parents seeking health information regarding their sick child.
NLP can answer their question, first by understanding key elements in the incoming question and then by providing a response, either by drawing upon a database of known answers (e.g., FAQs maintained by the NIH institutes) or by summarizing relevant PubMed or MedlinePlus articles. Such quick access to accurate and trustworthy health information has the potential to save time and to save lives.
We’re not fully there yet, but as our research continues, we get closer.
Maybe it’s time I reconsider how I answer that perennial dinner party question: “I’m a computational linguist, and I help improve health.”
Dina Demner-Fushman, MD, PhD is a staff scientist in NLM’s Lister Hill National Center for Biomedical Communications. She leads research in information retrieval and natural language processing focused on clinical decision-making, answering clinical and consumer health questions, and extracting information from clinical text.
Guest post by Lincoln Weed, son of the late Dr. Lawrence L. Weed and co-author with him of the book Medicine in Denial and other publications. Dr. Weed, who died June 3, 2017, was the originator of “knowledge coupling” tools for clinical decision support and the problem-oriented medical record, including its problem list and SOAP note components.
“Patients are sitting on a treasure trove of data about their own medical conditions.”
My late father, Dr. Lawrence L. Weed (LLW), made this point the day before he died. He was talking about the lost wealth of neglected patient data—readily available, richly detailed data that too often go unidentified and unexamined. Why does that happen, and what can be done about it?
The risk of missed information
From the very outset of medical problem-solving, LLW argued, patients and practitioners face greater risk of loss and harm than they may realize. The risk arises as soon as a patient starts an internet search about a medical problem, or as soon as a practitioner starts questioning the patient about the problem (whether diagnostic or therapeutic).
This gap creates high risk that information crucial to solving the patient’s problem will be missed.
Ideally, these initial inquiries would somehow take into account the entire universe of collectible patient data and vast medical knowledge about what the data mean. But such thoroughness is more than the human mind can deliver.
This gap creates high risk that information crucial to solving the patient’s problem will be missed. And whatever information the mind does deliver is not recorded and harvested in a manner that permits organized feedback and continuous improvement.
Guidance tools set standard of care
The only secure way to proceed, LLW concluded, is to begin investigation of medical problems (the “initial workup”) using guidance tools external to the mind. These tools must couple patient-specific data with general knowledge as follows:
Link the initial data point (i.e., the patient’s presenting problem) with (1) medical knowledge about potentially relevant options and (2) readily available data for identifying those options (see the outer circle in the diagram below);
Link the data in (2), once collected, with the knowledge in (1) to show how well the data match up with the combinations of data points defining each relevant option—this matching indicates which options are worth considering for the individual (see the middle circle in the diagram below); and
Organize this information (data coupled with knowledge) into options and evidence—that is, diagnostic possibilities or therapeutic alternatives, the combined findings (positive, negative, or uncertain) on each alternative, and additional knowledge useful for assessing the best option to pursue (see the inner circle in the diagram below).
Tools to carry out these steps would define best practices and make them enforceable as high standards of care for the initial workup (i.e., patient history, physical exam, and basic lab tests). That threshold task is pivotal. It lays the informational foundation for follow-up thought and action by the patient and practitioner. That foundation is also needed for feedback activities to and from third parties. (See the diagram on p. 13 of Medicine in Denial.)
In carrying out the initial workup, the patient’s role is always central. The tools should enable patients to enter history data, which is often the most detailed component of the initial workup. Moreover, the patient necessarily participates in the physical exam conducted by the practitioner, and reviews history, physical, and lab findings with the practitioner.
Tools for the initial workup must thus be used by patients and practitioners jointly. But patients must be able to initiate use of the tools unilaterally. They can’t rely on practitioners to recognize when serious medical investigation is needed. Patients are the ones who experience symptoms—who notice changes from what feels normal. To investigate whether these symptoms might be medically significant, patients need web-based tools for problem-specific inquiries. So do healthy persons who may simply require periodic screening checkups for unidentified problems (plus initial workup of any problems discovered).
Overcoming the medical Tower of Babel
Whether it is patients or practitioners seeking guidance for the initial workup, traditional medical practice leaves them both in a vacuum. Once that vacuum was filled solely by practitioners’ idiosyncratic judgments. Now the vacuum is also being filled with a plethora of practice guidelines and clinical decision support tools, not to mention internet search engine tools.
But the very multiplicity of all these resources defeats the purpose of defining generally accepted, enforceable best practices for initial workups. And the multiplicity is increasing with new patient-generated health data from sensors, wearables, and smartphone-connected devices for physical exam data. Moreover, the universe for needed guidance is expanding with vast new genomic/molecular data and knowledge.
The outcome of this multiplicity is not useful diversity but a Tower of Babel.
What we need instead are information tools with a unified design and trustworthy medical content, tools that guide users through the basic steps for inquiry into all medical problems, tools that take into account relevant information from all specialties without intellectual or financial biases. Users should not have to switch back and forth among different tools and interfaces for different medical problems, different specialties, different practice settings, different data types, different vendors, and different classes of users. The medical content captured in the tools must be problem-specific, but the tools’ basic design (see the three bullets above) should generalize to all problems in all contexts, as much as possible. This generality enables intuitive ease-of-use at the user level and powerful synergies at the software development level.
NLM’s role for the 21st century
LLW saw NLM as key to developing tools of this kind.
Drawing on its uniquely comprehensive electronic repository of medical content, NLM could create a new repository of distilled, structured knowledge. Drawing on its connections with the NIH research institutes and federal health agencies such as the CDC and FDA, NLM could rapidly incorporate new knowledge into that specialized repository. Outside parties and NLM itself could use that repository to build user-level tools with a unified design for conducting initial workups on specific medical problems.
Drawing on its uniquely comprehensive electronic repository of medical content, NLM could create a new repository of distilled, structured knowledge.
By enabling creation of such a knowledge infrastructure for the public, NLM would seize an “opportunity to modernize the conceptualization of a ‘library.’” Beyond its current electronic repository, NLM could be “demonstrating how information and knowledge can best be developed, assimilated, organized, applied, and disseminated in the 21st century.” [NIH Advisory Committee to the Director, NLM Working Group, Final Report, p. 12 (June 11, 2015).]
This new infrastructure will encounter a barrier to its use—the medical practice status quo. Not all practitioners (or their overseers) will accept the data collection demands defined by the tool.
Patients at the center
Here we return to the central role of patients.
Patients who unilaterally use NLM tools to complete the history portion of the initial workup can then seek out practitioners who are willing (and permitted) to use the same tools for the physical exam and basic lab test portions. By creating demand for those innovative practitioners and using the tools jointly with them, patients can drive medical practice toward a foundational reform.
* * *
Readers who have questions about the above are referred to the fuller discussion of these ideas in the book Medicine in Denial (PDF | published work), especially parts IV.E, F, and G, pages 192-194, and the diagram on page 13. The author also invites comments below.
Lincoln Weed, JD, Dr. Lawrence Weed’s son, practiced employee benefits law in Washington, DC for 26 years. He then joined a consulting firm where he specialized in health information privacy. He is now retired.
Guest post by the 2016-2017 NLM Associate Fellows.
NLM Associate Fellowship Coordinator Kathel Dunn introduced our program in her post “NLM Associate Fellows Spark Library Alchemy,” speaking to the process of transformation this program can facilitate. As we, the 2016-2017 NLM Associate Fellows, prepare to bid NLM a fond farewell, we would like to share some reflections from our year and how we have been changed by our time here.
From our arrival on September 1, 2016, we knew this year would be different, as we began our fellowship only a few weeks after the arrival of Dr. Patricia Flatley Brennan, NLM’s then recently appointed director. One of our first activities as a cohort was to attend Dr. Brennan’s swearing-in ceremony, and the issues that shaped her first year–strategic planning and envisioning NLM’s future –became threads woven throughout our formative curriculum sessions and have been intertwined with our experiences throughout the program.
The heart of this program resides in the people of NLM and their willingness to share their time and knowledge with us. Throughout the curriculum, and later during the project phase of our year, NLM staff from all levels of the organization made themselves available for conversation, connection, and collaboration. As a result, we were able to build relationships across the Library and see connections and interdependencies across departments.
The capacity for professional relationship building also extends beyond the walls of NLM. Each member of this year’s cohort led a spring project that relied on collaboration with an external partner. Megan Fratta conducted focus groups with cancer researchers across NIH and NCI to assess their PubMed-related training needs. Kendra Godwin interviewed open science policy makers, advocates, and innovators from across the global research community in her efforts to define open science at NLM. Tyler Moses conducted an information needs assessment for the residents of the Children’s Inn, the hospitality house for children and their families who participate in research trials at NIH. And, as part of an interagency collaboration between NLM and the FDA, Candace Norton investigated enhancements to search filters to support pharmacovigilance.
Among the other connections fostered through this program are those between the members of the cohort and NLM’s senior leadership. As a group, we met with each senior leader to discuss what makes NLM unique, what makes an exemplary leader, and how best to prepare for a career in a rapidly evolving profession. Their collective wisdom and insight are invaluable at this stage in our careers.
Perhaps the most important connections are those we’ve formed with each other, thanks to the program’s cohort learning model. We’ve been a fellowship of four, learning more because of each other and the collective insights of our shared experience, and from the conversations this year has inspired. The program under its current name has existed since 1966, and we’ve been impressed with the level of support from the Associate Fellows who preceded us, and the significant contributions they’ve made to the program, to NLM, and to the profession.
As we conclude our fellowship year at NLM and make space for the incoming 2017-2018 cohort’s arrival on September 1, we leave you with our respect and gratitude for making this opportunity possible. Thank you for a fascinating and life-changing year at NLM!
Guest bloggers (from left) Candace Norton, Megan Fratta, Kendra Godwin, and Tyler Moses served as 2016-2017 NLM Associate Fellows.
Guest post by James G. Smirniotopoulos, MD, chief editor for MedPix®.
Arizona Senator and former Vietnam POW John McCain was recently diagnosed with the most aggressive form of brain cancer: glioblastoma. This is the same type of tumor that killed Vice President Joe Biden’s son Beau and Senator Ted Kennedy.
Glioblastoma originates in the brain. It arises from astrocytes, one of the supporting cells of the brain, and grows by sending tendrils into the surrounding tissue.
Because of its diffuse nature, glioblastoma is not curable. However, surgery to remove as much of the tumor as possible, followed by both radiation and chemotherapy, has improved the prognosis. Median survival rates—which means half the patients live longer and half die sooner—now run 15-18 months, whereas 5-10% of patients live five years following diagnosis. Novel treatments, including immunotherapy, have been effective in some patients.
The symptoms of glioblastoma can vary, depending on the part of the brain in which it occurs. Different parts of the brain perform different functions, so some tumors cause seizures, while others may cause numbness or speech problems. Some of the most common symptoms are:
Nausea and vomiting
Changes in your ability to talk, hear, or see
Problems with balance or walking
Problems with thinking or memory
Feeling weak or sleepy
Changes in your mood or behavior
Doctors diagnose glioblastomas and other brain tumors by doing a neurologic exam and tests including an MRI, CT scan, and biopsy.
MedPix®, NLM’s open-access medical image database, includes about 500 images of glioblastomas, largely MR and CT scans, gross photographs, and pathology slides of tumor histology.
For example, the following images show two different glioblastomas. The image on the left is from an MRI (axial, T2-weighted) of Patient A and that on the right is an axial gross cut-section from Patient B. The tumors, outlined in red, show a general similarity in shape and size, and both tumors have distorted the brain and compressed normal structures, like the cerebral ventricles (blue outline) that contain cerebrospinal fluid.
Launched in 1999, MedPix now holds over 54,000 images from more than 12,000 patients, including unique whole brain sections from the era preceding non-invasive diagnosis using MRI and CT imaging. Designed as a teaching file, the database includes clinical information about each patient, along with their diseases and diagnoses. The medical cases in MedPix have been peer-reviewed and pathologically proven, making them an excellent resource for teaching and learning about disease.
Guest blogger James G. Smirniotopoulos, MD, serves as chief editor for MedPix. Now retired and a special volunteer at NLM, Smirniotopoulos formerly served as a professor and chair of radiology at the Uniformed Services University of the Health Sciences.