What is Neic Payer ID Numbers

Electronic health records are very useful as repositories for valuable patient data. But you need help when it comes to that data that is at work for more innovative care delivery. The steadily growing scope and variety of clinical and socially determined factors require advanced technologies to be optimally used for precision medicine.

Enter AI and machine learning that "play a growing role in health care under two main categories - knowledge generation and data processing," said Auckland, New Zealand-based Kevin Ross, who will speak next month at HIMSS19 .

Ross is general manager at Precision Driven Health, launched as a partnership between Orion Health (where he is director of research) and government agencies and academic organizations in New Zealand to explore and promote precision medicine. He sees machine learning as a key technology in the years to come - as health systems look to unlock the data and in your EHR systems and put it to work for more individualized care.

"Patient records have been electronic - and therefore accessible for analysis - for a relatively short time, but we will now see large amounts of data generated from various sources," he explains. "We didn't have enough computing power to process the amount of data in a genome, let alone a microbiome, etc. until quite recently."

The advent of AI and machine learning opens new avenues for healthcare wisdom to be delineated. Medical research has traditionally been through “targeted studies on narrow subsets of the population,” he said, “now we can analyze over large populations in relative real time, since the data is collected digitally. New knowledge is gained through the application of machine learning to this increased amount of data in order to uncover patterns that can be found today without being noticed. "

In Orlando, Ross explain how he and other researchers are making most of some unique aspects of the New Zealand healthcare landscape - affiliated electronic health data through leading population research organizations - to enable the development of new technologies and data strategies for precision medicine.

"New Zealand has some unique advantages, including a long history of digital health records as well as managed health ID numbers, so it's much easier to link different sets of data together," he explains. In addition,

  • Linked data between social services (health, education, justice, welfare, taxation) available for scientific purposes;
  • A single-payer system, where the incentive of the patient, provider and system are usually well aligned (e.g. early intervention benefits everyone)
  • Ready collaboration between commercial and public providers, organizations as well as between clinical and data science scientists
  • A unique ethnic diversity (74% European, 15% Maori, 12 percent Asian, 7% Pacific Islander - also the identification of several)
  • Strong data science research
  • A population relatively comfortable with technology and broad access

All of that, plus the fact that New Zealand has a small population (less than 5 million people) means that “the research is more populist rather than highly specialized,” Ross said.

From this remote corner of the world to other global health systems, he sees a great future for AI-enabled EHRs - the rapid evolution for precision medicine.

"Machine learning can be used to help-intensive tasks such as processing large amounts of data for genomics, image processing or network analysis, as well as finding anomalies, e.g. for diagnosing or detecting fraud - and identifying cohorts", he said. "There are interesting applications in the maintenance of data sets such as suitable data from different systems, the derivation of missing data elements."

And as developments continue, what should healthcare systems that have already started AI implementations do to ensure that they are making the best use of machine learning in their workflows?

"Design systems with interoperability and data sharing in mind," said Ross. “Use of standards, build-tagging systems. And make it easy for patients to control how their data is used and shared, and see the benefits. "

He also advised health systems to get most of all the data they have on hand: "Even 'dirty' data can have incredible predictive value," he said. "Don't wait for perfect dates to use it."

Ross ‘illustration," Machine Learning About Our Growing Electronic Health Records "is planned for Wednesday, February 13, from 2:30 am to 3:30 pm in room W308A.

Twitter: @MikeMiliardHITN
Author's email: [email protected]

Healthcare-IT-News is a publication by HIMSS Medien.