The American Medical Informatics Association is calling on the National Library of Medicine to lead data science research efforts in health and biomedicine across the National Institutes of Health.

NLM issued a request for information in September, seeking input from stakeholders on promising directions for new data science research to make science more open and reproducible, as well as developing new partnerships to boost data science.

In response to the information request, AMIA suggests that NLM focus research on the basic science of data standards, improve open science and reproducibility, and build on its leadership in informatics education and training.

“The future of health and medicine is data,” says Doug Fridsma, M.D., president and CEO at AMIA. “As the science of collecting, analyzing and applying data to health challenges, informatics can be a powerful complement to data science tools and methodology. AMIA views the NLM as a natural home to ensure that both fields evolve towards mutual goals.”

Doug Fridsma, MD
Doug Fridsma, MD

With the industry undergoing rapid digitalization, now is the time to make progress on the systematic and strategic use of data and NLM should focus on the basic science of data standards and development of granular data specifications to create a “periodic table of elements” approach to biomedicine data standards, AMIA recommends. “Such an approach would enable the combination and substitution of discrete data elements for specific use cases, such as quality measures, and facilitate data re-use more readily than is the case today.”

Also See: How precision medicine will leverage data analytics and AI

Focus areas could include improved methods to support data capture from patients across care settings, better data storage and formats, methods to document how data have been processed, measuring data accuracy and auditing metadata and terminology qualities.

AMIA further suggests that NLM focus on further development of standards for data elements in specific disease areas and in nursing and other clinical settings, find ways to determine when coding variation is appropriate and inappropriate, and develop standard imaging recognition algorithms for radiology, pathology and other imaging-based disciplines.

This research could then support finding ways to use data from sources that could include wearable devices, mHealth apps, online journaling and other social media tools, geospatial sensors, genomics and Internet of Things sensors, according to AMIA, which also encouraged NLM to better embrace open source concepts, such as the value of using well-defined standard open source licenses.

“To make the kinds of progress envisioned by the 21st Century Cures Act and to deliver on the vision articulated by Triple Aim, we must be able to better process and apply data,” says Thomas Payne, M.D., chair of AMIA and medical director of IT services at UW Medicine in Seattle. “This starts by ensuring we understand the fundamentals behind data science and can apply that knowledge to health and biomedicine and evolve the field in an evidence-based manner.” The full comments from AMIA are available here.

Register or login for access to this item and much more

All Health Data Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access