Your Privacy is an NLM Priority

Patient privacy — you might be scratching your head right now. NLM is a research enterprise and a LIBRARY for heaven’s sake! What does a library have to do with patient privacy? NLM protects the privacy of all people who use our resources, which are free and accessible 24/7. NLM complies with requirements for privacy and security established by the Office of Management and Budget, Department of Health and Human Services, and NIH. I encourage you to visit our Privacy and Security Policy guidelines.

No personal identifying information is required to search and access our vast data repositories and library resources. Anyone, sick or well, who wants trusted information about a disease, illness, or health condition can search through our MedlinePlus online health information service. With data available in English and Spanish, MedlinePlus offers high quality, relevant health information for patients and their families on more than 1,000 topics such as children’s growth and development, gene therapies, and self-care after surgery.

We do not link search strategies to any specific patron without their permission. NLM only links information for those patrons who sign up for My NCBI, which is a service that allows patrons to save and return to previous search results. This information is held in a safe, secure part of our computer systems open only to the individual.

NLM also provides expert guidance to other federal agencies for the most effective approaches to preserving patient privacy. Clem Mc Donald, MD, our Chief Health Data Standards Officer, serves as a member of the Health Information Technology Advisory Committee, which is an advisory committee to the Office of the National Coordinator for Health Information Technology that oversees a range of issues from promoting health IT excellence in communities to collaborations among federal agencies. We recently participated in the federal response to Executive Order 13994, Ensuring a Data-Driven Response to COVID-19 and Future High-Consequence Public Health Threats, leveraging our expertise in protecting patient data and preventing inadvertent re-identification from genomic information.

Patient participation in clinical trials and other research efforts advances science and creates the pathways to discover new clinical therapies and interventions. Sometimes, data generated in one study becomes useful in future studies; for example, when trying to understand how different groups of patients respond to the same therapy. NLM provides technical assistance to the National Institutes of Health in creating ways to store participant-level study information safely and securely making information useable for other researchers while making sure that personally identifiable information is not disclosed. We also help NIH create safe, secure data repositories of research data and implement mechanisms and oversight measures to ensure that data is available to researchers and managed in a way consistent with the original agreements for use of the data. We helped establish NIH’s Researcher Auth Service Initiative, a single sign-on for researchers that allows access to specific data sets in a controlled manner.

Our researchers also develop computational methods to protect patient privacy. This includes research investigating how to remove traces of identifying data from clinical records, while making those records useful for researchers to better understand the course of disease and determine the effectiveness of treatments. NLM’s Dr. Mehmet Kayaalp develops ways to let approved researchers use clinical records for clinical studies in a way that protects patient privacy. He describes his work this way:

Narrative clinical reports contain a rich set of clinical knowledge that could be invaluable for clinical research. However, they usually also contain personal identifiers that are considered protected health information and are associated with use restrictions and risks to privacy. Computational de-identification seeks to remove all of the identifiers in such narrative text in order to produce de-identified documents that can be used in research while protecting patient privacy. Computational de-identification uses natural language processing tools and techniques to recognize patient-related individually identifiable information (e.g., names, addresses, and telephone and social security numbers) in the text and redacts them. In this way, patient privacy is protected, and clinical knowledge is preserved.

Dr. Mehmet Kayaalp

So – we’re more than a library. We are a partner in preserving patient privacy while making sure that researchers and clinicians can discover the best new ways for taking care of patients.

How do you think NLM can better serve scientists and society?

Ending the HIV Epidemic: Equitable Access, Everyone’s Voice

A guest post by Amanda J. Wilson, Chief, Office of Engagement and Training; Leigh Samsel, NLM Planning and Evaluation Officer, Office of Strategic Initiatives; and Elizabeth A. Mullen, Manager of Web Development and Social Media, History of Medicine Division, National Library of Medicine at the National Institutes of Health.

This year’s theme for World AIDS Day is Ending the HIV Epidemic: Equitable Access, Everyone’s Voice. As the world’s largest biomedical library, NLM has a long history of supporting NIH’s efforts to end the HIV epidemic by providing equitable access to trusted biomedical information, supporting biomedical research, and highlighting the historical, social, and cultural context of this research. Expedient, reliable, free public access to NLM’s trusted biomedical information resources and literature collections advances the knowledge and treatment of HIV/AIDS worldwide, helps progress research to end the HIV epidemic and improves the health of people living with HIV.

Improving HIV/AIDS Health Information Access

NLM integrates multiple types of HIV literature, sequence, testing, and clinical trials data into a portfolio of resources that enables researchers to easily find related information and robustly supports global research to end the HIV epidemic. Free public access to citations to the scholarly literature is provided through NLM’s PubMed and Bookshelf, while free access to full-text is provided through PubMed Central and NLM Digital CollectionsGenBank and the Sequence Read Archive allow researchers to deposit and access publicly available DNA sequences, including HIV experimental and clinical genome sequences. NCBI Virus makes HIV and other virus sequences from RefSeq, GenBank, and other NLM repositories available. The HIV-1 Human Interaction Database includes information gleaned from literature about the interaction between human and HIV-1 genes and proteins.

NLM also provides a rich resource of easy-to-understand online health and wellness information available in English and Spanish via MedlinePlus. Among its wealth of content, MedlinePlus contains several HIV/AIDS topical pages. NLM supports an equitable distribution of information by providing resources and support to strengthen skills and literacies needed to access and use biomedical information for those affected by HIV/AIDS. The Network of the National Library of Medicine provides free health information training, from webinars to instructor-led classes to on-demand tutorials. Additional trainings on a variety of topics are added weekly.

A Long History of Support

NLM’s engagement and collections activities strive to capture the many voices in and around the HIV epidemic. A key historical partnership for engagement with the NIH Office of AIDS Research was the HIV/AIDS Community Information Outreach Program; beginning in 1994 as a resource for community-based organizations to improve the knowledge, skills, and technical means to access and provide the latest authoritative prevention, treatment, and research information electronically. The current iteration of the program concludes this month with 200 plus organizations conducting more than 350  projects in 38 states providing training, communications campaigns, and enhanced products and apps to raise awareness of HIV/AIDS information and discoveries over the 40-year history.

NLM has been collecting publications and archival materials related to HIV/AIDS since the first Morbidity and Mortality Weekly Report on the topic was issued in June 1981. The NLM HIV/AIDS Web Archive offers more than 150 websites documenting the biomedical, clinical, cultural, and social aspects of HIV/AIDS in the early 21st century. This month you can look for new additions and resources.

World AIDS Day 2021

Screen shot of NLM's History of Medicine Division's exhibit entitled "AIDS, Posters and Stories of Public Health"

This month, to help mark World AIDS Day, NLM will launch a new online exhibition—A People’s History of Pandemic: AIDS, Posters, and Stories of Public Health. The NLM exhibition will cover the archive of public health posters about AIDS rooted in the cultural output of artists, activists, and community workers. Their work, specifically the use of personal narrative as a visual-art strategy, along with language and the collective process of creating AIDS posters, continues to broadcast the message that, 40 years after the crisis began, attention to AIDS has not diminished. In mid-December, NLM’s Profiles in Science, will release a curated collection of digitized primary source materials related to the United States National Commission on AIDS, dating from the mid-1980s through the early 1990s. Learn more about the diversity of NLM’s historical collections related to HIV/AIDS on Circulating Now.

As we mark this year’s World AIDS Day, NLM is proud to continue its efforts to provide global access to trusted resources; share the voices of those affected by HIV; and provide the foundation for researchers, clinicians, patients, and families to engage and answer the call to end the HIV epidemic.

Photo of Amanda Wilson

Amanda J. Wilson is Chief of the NLM Office of Engagement and Training (OET), bringing together general engagement, training, and outreach staff from across NLM to focus on NLM’s presence across the U.S. and internationally. OET is also home to the Environmental Health Information Partnership for NLM and coordinates the Network of the National Library of Medicine.

Photo of Leigh Samsel

Leigh Samsel, MS, is responsible for formal reporting of NLM activities and for providing staff leadership to strategic planning activities. Leigh is currently serving as NLM’s AIDS Coordinator to the NIH Office of AIDS Research.

Photo of Elizabeth Mullen

Elizabeth A. Mullen, MS, is Manager of Web Development and Social Media for the History of Medicine Division (HMD) and Managing Editor of Circulating Now, a blog featuring new research, curatorial insights, and news about NLM’s historical collections.

Artificial Intelligence, Imaging, and the Promising Future of Image-Based Medicine

In mid-October I gave the NLM Research in Trustable, Transparent AI for Decision Support keynote speech to the 50th Institute of Electrical and Electronics Engineers (IEEE) Applied Imagery Pattern Recognition conference in Washington, D.C. (virtually, for me). The IEEE continues to advance new topics in applied image and visual understanding, and the focus this year was to explore artificial intelligence (AI) in medicine, health care, and neuroscience.

To prepare for my talk, I reviewed our extramural research portfolio so I could highlight current research on these topics. NLM’s brilliant investigators are using a range of machine learning and AI strategies to analyze diverse image types. Some of the work fosters biomedical discovery; other work is focused on creating novel decision support or quality improvement strategies for clinical care. As I did with the audience at IEEE, I’d like to introduce you to a few of these investigators and their projects.

Hagit Shatkay and her colleagues from the University of Delaware direct a project titled Incorporating Image-based Features into Biomedical Document Classification. This research aims to support and accelerate the search for biomedical literature by leveraging images within articles that are rich and essential indicators for relevance-based searches. This project will build robust tools for harvesting images from PDF articles and segment compound figures into individual image panels, identify and investigate features for biomedical image-representation and categorization of biomedical images, and create an effective representation of documents using text and images grounded in the integration of text-based and image-based classifiers.

Hailing from the University of Michigan, Jenna Wiens leads a project called Leveraging Clinical Time Series to Learn Optimal Treatment of Acute Dyspnea. Managing patients with acute dyspnea is a challenge, sometimes requiring minute-to-minute changes in care approaches. This team will develop a novel clinician-in-the-loop reinforcement learning (RL) framework that analyzes electronic health record (EHR) clinical time-series data to support physician decision-making. RL differs from the more traditional classification-based supervised learning approach to prediction; RL “learns” from evaluating multiple pathways to many different solution states. Wiens’ team will create a shareable, de-identified EHR time-series dataset of 35,000 patients with acute dyspnea and develop techniques for exploiting invariances (different approaches to the same outcome) in tasks involving clinical time-series data. Finally, the team will develop and evaluate an RL-based framework for learning optimal treatment policies and validating the learned treatment model prospectively.

Quynh Nguyen from the University of Maryland leads a project called Neighborhood Looking Glass: 360 Degree Automated Characterization of the Built Environment for Neighborhood Effects Research. Using geographic information systems and images to assemble a national collection of all road intersections and street segments in the United States, this team is developing informatics algorithms to capture neighborhood characteristics to assess the potential impact on health.

Corey Lester from the University of Michigan leads a multidisciplinary team using machine intelligence in a project titled Preventing Medication Dispensing Errors in Pharmacy Practice with Interpretable Machine Intelligence. Machine intelligence is a branch of AI distinguished by its reliance on deductive logic, and the ability to make continuous modifications based in part on its ability to detect patterns and trends in data. The team is designing interpretable machine intelligence to double-check dispensed medication images in real-time, evaluate changes in pharmacy staff trust, and determine the effect of interpretable machine intelligence on long-term pharmacy staff performance. More than 50,000 images are captured and put through an automated check process to predict the shape, color, and National Drug Code of the medication product. This use of interpretable machine intelligence methods in the context of medication dispensing is designed to provide pharmacists with confirmatory information about prescription accuracy in a way that reduces cognitive demand while promoting patient safety.

Alan McMillan from the University of Wisconsin-Madison and his team are examining how image interpretation can improve noisy data in a project called Can Machines be Trusted? Robustification of Deep Learning for Medical Imaging. Noisy data is information that cannot be understood and interpreted correctly by machines (such as unstructured text). While deep learning approaches (methods that automatically extract high-level features from input data to discern relationships) to image interpretation is gaining acceptance, these algorithms can fail when the images themselves include small errors arising from problems with the image capture or slight movements (e.g., chest excursion in the breathing of the patient). The project team will probe the limits of deep learning when presented with noisy data with the ultimate goal of making the deep learning algorithms more robust for clinical use.

In the work of Joshua Campbell’s team at Boston University, the images emerge at the end of the process to allow for visualization of large-scale datasets of single-cell data. The project, titled Integrative Clustering of Cells and Samples Using Multi-Modal Single-Cell Datauses a Bayesian hierarchical model developed by the team to perform bi-clustering of genes into modules and cells into subpopulations. The team is developing innovative models that cluster cells into subpopulations using multiple data types and cluster patients into subgroups using both single-cell data and patient-level characteristics. This approach offers improvements over discrete Bayesian hierarchical models for classification in that it will support multi-modal and multilevel clustering of data.

Several things struck me as I reviewed these research projects. The first was a sense of excitement over the engagement of so many smart young people at the intersection of analytics, biomedicine, and technology. The second was the variety of types of images considered within each project. While one study explores radiological images, another study examines how image data types vary from figures in journal papers to pictures of the built environment and images of workflows in a pharmacy. Two of these studies use AI techniques to analyze the impact of the physical environment to better understand its influence on patient health and safety, and one study uses images as a visualization tool to better support inference of large-scale biomedical research projects. Images appear at all points of the research process, and their effective use heralds an era of image-based medicine. Let’s see what lies ahead!

25×5: Decreasing Documentation Burden on U.S. Clinicians

Guest post by Sarah Rossetti, RN, PhD, FAAN, FACMI, FAMIA, and S. Trent Rosenbloom, MD, MPH, FACMI, FAMIA, Co-Chairs of the 25 By 5 Symposium

Health professionals are consistently being recognized for their heroic efforts to manage illness during the COVID-19 pandemic in the face of unprecedented challenges. As doctors, nurses, and all health care professionals faced their greatest challenges in more than a century, they did so while also dealing with the ongoing and increasing challenge of clinical documentation burden, which can be exacerbated by the widespread use of electronic health records systems.

The burden of clinical documentation on professionals has had a negative impact on health care since long before the first diagnosis of COVID-19. This burden can lead to a variety of negative outcomes including clinician burnout and decreased job satisfaction, medical errors, and hospital-acquired conditions. The pandemic increased recognition of the role of clinical documentation on workload. This recognition provided an opportunity to consider the contributions of inpatient and outpatient documentation on clinician well-being.

To establish strategies and approaches to reduce documentation burden on U.S. clinicians, we developed the 25 By 5 Symposium Series with the goal to reduce documentation burden to 25% of its current level by 2025. This symposium was sponsored by the American Medical Informatics Association, NLM, Columbia University Department of Medical Bioethics, and Vanderbilt Medical University Center.

The symposium, held virtually over six weeks in early 2021, addressed efforts to reduce clinical documentation burden, the associated challenges, and future innovations. More than 300 people representing clinical settings, academia, industry – electronic health record (EHR) vendors and start-up companies, government, payers, professional organizations, and patients participated in sessions featuring more than 30 presentations from stakeholders across health systems, academia, industry, government, payers, and professional societies.

Convening such a diverse group of key stakeholders and thought leaders resulted in the development of a national action plan focused on short, medium, and long-term approaches to reduce documentation burden to 25% by the year 2025.

To aid the work in addressing the complex issue of documentation burden, an organizing framework from the American Nursing Informatics Association 2020 Position Paper was used to outline the Six Domains of Burden.

These domains were used to organize breakout sessions and generate action items for reducing burden. An Executive Summary and Appendix of 82 Action Items from the Symposium are posted on the 25 By 5: Symposium website.

These action items are further categorized across four themes: 1) Accountability, 2) Evidence, 3) Education and Training, and 4) Innovation of Technology.

Action items—synthesized and prioritized in Calls to Action for key stakeholder groups — are highlighted below:

Call to Action for Providers and Health Systems

  • Establish guiding principles for adding documentation to EHRs and generating evidence for reduced documentation.
  • Develop a national roadshow and educate clinicians and clinicians in training on balancing brevity and completeness in documentation.
  • Increase support for functions like real-time information retrieval, documentation, and ordering in the EHR.
  • Implement interdisciplinary notes to decrease redundant documentation.

Call to Action for Health IT Vendors

  • Promote an ecosystem of interoperable systems to allow for complementary technology.
  • Develop measurement tools to categorize documentation practices.
  • Package best training practices into toolkits to promote best practice EHR use and plan recognition programs to publicize exemplars.
  • Create simplistic EHR views to see that new clinical data has been reviewed, then bookmark for the user and document as reviewed by that user in the EHR.
  • Implement user-personalized Clinical Decision Support to drive specific workflows.

Call to Action for Policy and Advocacy Groups

  • Urge agencies to fund innovative research that captures all billing code information without taking up clinicians’ time.
  • Select the best of breed approaches to documentation and implement throughout the health care system.
  • Develop technology to reliably and accurately create reimbursement/payment data for all care settings.

Now the hard work begins to turn these action items into change to benefit clinicians’ well-being and patient care.

This work will require the creation of a network of allies, convening sessions, and the creation of working groups from national health professional organizations in order to execute a national strategy for implementing and institutionalizing these changes.

Our clinicians are depending on concerted and coordinated engagement with key stakeholders from organizations within our health care community to mobilize strategies nationally.

On behalf of the 25 By 5 Symposium Steering Committee, we hope you will join us in this effort.

Funding sources: 
National Library of Medicine (1R13LM013581-01)
National Institute of Nursing Research (NINR): 1R01NR016941-01

Dr. Rossetti is an Assistant Professor of Biomedical Informatics and Nursing at Columbia University. Her research is focused on identifying and intervening on patient risk for harm by applying computational tools to mine and extract value from EHR data and leveraging user-centered design for patient-centered technologies.

Dr. Rosenbloom is the Vice Chair for Faculty Affairs and a Professor of Biomedical Informatics at Vanderbilt University. His research has focused on studying how health care providers, patients, and caregivers interact with health information technologies when documenting medical and health-related activities, and when making clinical decisions.

40 Years of Progress: It’s Time to End the HIV Epidemic

Guest post by Maureen M. Goodenow, PhD, Associate Director for AIDS Research and Director, Office of AIDS Research, National Institutes of Health

On June 5th, the National Institutes of Health (NIH) Office of AIDS Research (OAR) joined colleagues worldwide to commemorate the 40th anniversary of the landmark 1981 Centers for Disease Control and Prevention (CDC) Morbidity and Mortality Weekly Report (MMWR) that first recognized the syndrome of diseases later named AIDS. June 5th also marks HIV Long-Term Survivors Awareness Day. 

Forty years ago, the CDC’s MMWR described five people who were diagnosed with Pneumocystis carinii pneumonia—catalyzing a global effort that led to the identification of AIDS, and later, the virus that causes AIDS.

Over the years, much of the progress to guide the response to HIV has emerged from research funded by the NIH, and helped turn a once fatal disease into a now manageable chronic illness. This progress is attributable in large part to the nation’s longstanding HIV leadership and contributions at home and abroad.

NIH is taking action to recognize the milestones achieved through science, pay tribute to more than 32 million people who have died from AIDS-related illness globally (including 700,000 Americans), and support the goal of Ending the HIV Epidemic in the U.S. (EHE) and worldwide. OAR is coordinating with NIH Institutes, Centers, and Offices (ICOs) to share messaging that will continue through NIH’s World AIDS Day commemoration on December 1, 2021.

The NIH remains committed to supporting basic, clinical, and translational research to develop cutting-edge solutions for the ongoing challenges of the HIV epidemic. The scientific community has achieved groundbreaking advances in the understanding of basic virology, human immunology, and HIV pathogenesis and has led the development of safe, effective antiretroviral medications and effective interventions to prevent HIV acquisition and transmission.

Nevertheless, HIV remains a serious public health issue.

NIH established the OAR in 1988 to ensure that NIH HIV/AIDS research funding is directed at the highest priority research areas, and to facilitate maximum return on the investment. OAR’s mission is accomplished in partnership within the NIH through the ICs that plan and implement specific HIV programs or projects, coordinated by the NIH HIV/AIDS Executive Committee. As I reflect on our progress against HIV/AIDS, I would like to note the collaboration, cooperation, innovation, and other activities across the NIH ICOs in accelerating HIV/AIDS research.

Key scientific advances using novel methods and technologies have emerged in the priority areas of the NIH HIV research portfolio. Many of these advances stem from NIH-funded efforts, and all point to important directions for the NIH HIV research agenda in the coming years, particularly in the areas of new formulations of current drugs, new delivery systems, dual use of drugs for treatment and prevention, and new classes of drugs with novel strategies to treat viruses with resistance to current drug regimens.

Further development of long-lasting HIV prevention measures and treatments remains at the forefront of the NIH research portfolio on HIV/AIDS research.

NIH-funded investigators continue to uncover new details about the virus life cycle, which is crucial for the development of next generation HIV treatment approaches. Additionally, the NIH is focused on developing novel diagnostics to detect the virus as early as possible after infection.

Results in the next two years from ongoing NIH-supported HIV clinical trials will have vital implications for HIV prevention, treatment, and cure strategies going forward. For example, two NIH-funded clinical trials for HIV vaccines, Imbokodo and Mosaico, are evaluating an experimental HIV vaccine regimen designed to protect against a wide variety of global HIV strains. These studies comprise a crucial component of the NIH’s efforts to end the HIV/AIDS epidemic.

As we close on four decades of research, I look forward to the new advances aimed at prevention and treatment in the years to come.

You can play a role in efforts to help raise awareness and get involved with efforts to end the HIV epidemic. Visit OAR’s 40 Years of Progress: It’s Time to End the HIV Epidemic webpage, and use the toolkit of ready-to-go resources.

Dr. Goodenow leads the OAR in coordinating the NIH HIV/AIDS research agenda to end the HIV pandemic and improve the health of people with HIV. In addition, she is Chief of the Molecular HIV Host Interactions Laboratory at the NIH.

%d bloggers like this: