Posted in Perspective

Why connectivity is crucial to the effectiveness of artificial intelligence in healthcare

Chris Nerney
Chris Nerney, Contributing Writer |
Why connectivity is crucial to the effectiveness of artificial intelligence in healthcare

Artificial intelligence has the potential to transform healthcare, but only if a number of “significant challenges” – including the collection of vast amounts of patient and population data from multiple sources – can be overcome.
That’s one conclusion from a report prepared at the request of the Office of the National Coordinator for Health Information Technology (ONC) and the Agency for Healthcare Research and Quality (AHRQ) by JASON, an independent group of scientists and academics.
“In the future, AI and smart devices will become increasingly interdependent, including in health-related fields,” according to the report’s authors. “On one hand, AI will be used to power many health-related mobile monitoring devices and apps. On the other hand, mobile devices will create massive datasets that, in theory, could open new possibilities in the development of AI-based health and health care tools.”
Turning that theory into reality will require cloud-based storage and analytics, as well as the ability to transmit data from devices and electronic health records (EHRs).
Unfortunately, EHR data isn’t always reliable. A 2016 study by The Journal of the American Medical Informatics Association found a 24.4 percent rate of inaccurate documentation in EHRs.
“Extreme care is needed in using EHRs as training sets for AI, where outputs may be useless or misleading if the training sets contain incorrect information or information with unexpected internal correlations,” the JASON report advises.
“What is clear from the report is that without access to high quality, reliable data, the promise of AI will not be realized,” ONC Chief Scientist Teresa Zayas Caban writes in a blog post. “The increased availability of digital health data could allow for the use of AI in clinical practice, though issues regarding the quality of existing data must be addressed.”
The JASON report offers several suggestions to providers and other healthcare stakeholders seeking to fully leverage AI for clinical decision-making, patient care, and population health:

  • Support development of AI applications that enhance the performance of new mobile monitoring devices and apps
  • Develop data infrastructure to capture and integrate data generated from smart devices to support AI applications
  • Support development of (and access to) research databases of labeled and unlabeled health data for AI health applications
  • Support research on how to incentivize sharing of health data, as well as new models for data ownership
  • Support research to determine the quantity and quality of data needed to support a given AI application
  • Identify and develop strategies to fill gaps in important health data

JASON has been advising the federal government since the 1960s. It is run through the MITRE Corporation, a non-profit organization with ties to the U.S. Defense Department. The Robert Wood Johnson Foundation provided support for the AI research report.