The New Health Information Exchange from Cloudticity: NLP, Catalogs, and Standards

Rapid exchange of patient data is crucial not only for coordinating care, but for research and public health. Data sharing is even more fundamental to accountable care organizations (ACOs), but it has become more and more complex as the health care field embraces new forms of data, such as genomics and messages from fitness devices. I recently talked with Gerry Miller, Founder and CEO of Cloudticity, to learn how they see health information exchange today.

It’s a very different matter from the unlamented Health Information Exchanges of the late twentieth century. These HIEs rarely had a viable business model–nor should they have. They were slow-moving, bureaucratic, expensive, and geographically limited (heaven forbid you should experience a medical event out of state). Let’s take a look at what the HIE of the twenty-first century is like.

Cloudticity helps health care organizations use cloud technologies, but their services go far beyond that. They harmonize, structure, and catalog the data to create a supple repository known in computing circles as a data lake, suitable for machine learning.

In this way, Cloudticity provides data in ways that make it searchable and useful to all the potential users: hospital administrators, clinicians, public health agencies, and researchers.

On top of the data, Cloudticity builds services such as machine learning and compliance checks (see figure). Miller said that since the reforms in the Affordable Care Act, payers are more interested in using machine learning for key cost-saving tasks, such as identifying super-utilizers among their patients.

Compliance Dashboard
Compliance Dashboard

Natural language processing (NLP), another application of AI, can look through doctors notes to find procedures they performed but forgot to bill for. Healthcare ontologies such as the ICD standards are built on top of the NLP to assign meaning to data. Old HL7 documents are converted to the widespread JSON standards, with human-readable field names added.

Miller says that traditional databases require complicated and resource-intensive Extract Transform and Load (ETL) to produce tables or spreadsheets of use to professionals. The data lake offers a similar “structure on extraction,” but its preprocessing and organization allow the extraction to be much lighter-weight than classic ETL.

The examples I’ve offered so far for Cloudticity deployment suggest its value is for cost control, a 24/7 obsession of health care administrators. But bringing data together this way also help patients:

  • New York State got on top of its COVID-19 crisis in a lightning-speed project involving 118 stakeholders, which let the state quickly collect and analyze data on both patient loads and medical resources. Cloudticity won an award from its partner, AWS, for this initiative.
  • Caredove uses Cloudticity to build its network of home care and community services.
  • The Michigan Health Information Network Shared Services developed a program to improve patient transitions and follow-ups on top of Cloudticity.

Modern businesses can’t afford to ignore any information technology that can help them respond to clients fast and improve visibility into what they’re doing. Health care is under just as much pressure as everyone else. If data crunching can save someone from an infection during a transfer to rehabilitative care, or replace repetitive hospital visits with a coordinated approach to chronic conditions, everybody will be better off. That’s what I want to see in health information exchange.

About the author

Andy Oram

Andy is a writer and editor in the computer field. His editorial projects have ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. A correspondent for Healthcare IT Today, Andy also writes often on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM (Brussels), DebConf, and LibrePlanet. Andy participates in the Association for Computing Machinery's policy organization, named USTPC, and is on the editorial board of the Linux Professional Institute.

   

Categories