Medical Software

Public Health Informatics Predictions for 2018

Published by in Medical Software

When it comes to public health, surprises are almost never good. Wouldn’t it be nice if we had a crystal ball to show the future so we were never surprised?

We’re not there yet, but we’re getting closer by the day.

Public health informatics (PHI) is the closest thing we have to a fortune teller in healthcare. It’s a fast-growing, ever-more-important field for healthcare providers to know and participate in.

Below, I’ll give you a short overview of PHI and the benefits of combining EHR data, show you what it looks like in practice and what’s in store for PHI in 2018, and round things out with some tips on how healthcare providers can prepare.

header image of a hand holding a crystal ball; inside the ball there is a chart showing growth

What is PHI?

Public health IT systems record data on healthcare incidents and events on a population basis, including:

  • Births and deaths
  • Reportable conditions
  • Immunizations
  • Cancer
  • Congenital diseases

When public health IT systems combine their historical population health data with current population health data from other sources, researchers can accurately predict future events. This process is known as population health informatics.

Population health informatics is what you get when you combine PHI data with data from sources such as EHRs, claims data, Google, and even Twitter.

PHI venn diagram


Here’s a detailed breakdown of how the roles and responsibilities for data collection are shared between population health informatics, public health informatics, and clinical informatics:

PHI data collection breakdown table

Data collection breakdown (Source)

The power of combining EHR data with other data sources

When you accurately predict the future, you enter that future better prepared. PHI can help health systems optimize the following activities:

  • Prioritization of care
  • Surveillance
  • Education
  • GIS (geographic-level interventions)
  • Pay for performance
  • “Learning community health system”

Let’s look at some ways PHI is improving public health.

Predicting and preparing for the flu

Influenza is a leading cause of death in the U.S. According to Nature, influenza-like illnesses kill as many as 50,000 Americans every year. Predictive analytics tools are now good enough to accurately predict when and where the next influenza outbreak will occur, as well as how many people will be affected. This means public health officials and hospitals can know when to have face masks and flu shots ready, along with when and how much to staff up.

The Centers for Disease Control and Prevention has historical information on previous flu epidemics. Today, autoregressive models for influenza forecasts “have shown satisfactory performances when applied on large populations,” according to the Journal of Medical Internet Research. These systems “have the potential to accurately and reliably provide near real-time regional estimates of flu outbreaks in the United States,” write researchers in Nature.

According to JMIR researchers, the area “where the knowledge need presently is most immediate is the detection and prediction of influenza activity at local levels. Such granular views, in turn, can provide input into large-scale models and accurate prediction of influenza spread in wide geographical areas.” In 2016 Nature researchers were able to accurately predict flu activity using EHR data from athenahealth.

Predicting obesity among veterans

Veterans’ Affairs collects vitals (including BMI), plus clinical risk factors such as geography and socioeconomic status, for the 30 million patients in its EHR system. With this data, researchers were able to map the geographic distribution of obesity among Veterans Health Administration patients.

Map depicting the geographic distribution of obesity among VHA population

Geographic distribution of obesity among VHA population (Source)

The administration then used predictive models to project when and where obesity would rise among this population group.

Other examples of population health informatics in practice

  1. In another study, researchers combined data from eClinicalWorks with public health data to accurately predict smoking and obesity rates among low-income New Yorkers.
  2. The Johns Hopkins CPHIT works with the Baltimore City Health Department to combine social, medical, and public health data to accurately identify seniors at high risk for falls and intervene before injury occurs in order to reduce ER visits and improve public health.

What using EHR data for PHI looks like in practice

One example of combining EHR data with public health data can be found at the Johns Hopkins Center for Population Health Information Technology. It houses the JHU ACG Predictive Modeling software system, which is currently in use in more than 30 nations for over 160 million patients.

Here’s how the data-sharing breaks down at CHHIT:

CPHIT data sharing partnerships infographic.

CPHIT data sharing partnerships infographic (Source).

What’s next for EHR data for public health informatics

Mergers and partnerships

The need for individual medical care systems and public health IT systems to integrate is only increasing. There still aren’t enough community hospitals sharing their EHR data with public health databases to realize the full potential of population health informatics, according to Columbia University.

In 2018, expect to see more cloud-based electronic health records integrate their databases with public health IT systems. In addition, expect more mergers and partnerships between EHR vendors and other data sources, including payers.

The $77 billion merger between CVS and Aetna may help usher in “a new era in analytics, interoperability and population health.” CVS has the most locations and highest revenue of all U.S. pharmacy chains. It also partners with Epic, the world’s largest EHR company. Epic and CVS are currently working to combine CVS’ prescription data with Epic’s Healthy Planet population health analytics platform to boost medication adherence and keep costs down.

To people like Alan Hutchison, Epic’s vice president of population health, the potential for PHI advances is huge now that they’re sharing data with Aetna. “CVS Health is one of the leaders in using data to dissolve domain silos, while offering new sources of intelligence and expertise that can better inform care delivery, reduce administrative overhead, and lower costs for patients,” Hutchison said.

Hutchison is hardly alone. Duke University Margolis Center research associate David Anderson recently wrote:

“I can think of using the CVS retail data as a population health monitoring service, I can think of using the over the counter sales data tied to individuals to fuel predictive models for future opioid issues, or arthritis flares, or pulmonary hospital admissions or one hundred other things. So from my former point of view as an insurance data geek, this merger offers an incredibly rich vein of data that can be mined and minted.”

Consulting group Kaufman Hall tracks hospital and health system partnership transactions. As of this past November, there had already been more deals in the current year than in all of 2016, and 2017 was set to be the busiest year ever. Expect more of these mergers and partnerships in 2018.

The blockchain

Another big trend in EHR interoperability for PHI that we’ll see more of in 2018 is blockchain usage.

In South Korea, it’s national policy for the Korea National Health Insurance Service to collect medical records for all Koreans. With access to genuinely representative data, researchers were able to predict—with 80% accuracy—which citizens would develop dementia.

Without this kind of nationwide data sharing, blockchain usage could facilitate interoperability. Information stored on the blockchain is extremely easy to share and difficult to falsify, an obvious boon for PHI. Crypt Bytes Tech notes that “Instead of relying on a designated intermediary for information exchange, such as a state-designated HIE or a private network established between local hospitals, the decentralized nature of the blockchain would allow any approved participants to join an exchange community, without the need to build data exchange pipes between certain organizations.”

Experts including Maria Palombini—director of emerging communities and initiatives development at the IEEE Standards Association—and EHR Intelligence’s Kate Monica see blockchain being increasingly used to standardize and secure health data.

Humana CEO Bruce Broussard described blockchain as the next big healthcare technology innovation.

How to get your EHR data in shape for for public health informatics in 2018

If you’re shopping for a new EHR, interoperability should be one of your primary considerations.

One requirement for interoperability is well-developed documentation standards for EHR systems. For medications, most EHRs speak the same language. For allergies, that’s not always the case. A new Journal of the American Medical Informatics Association (JAMIA) report suggests changes to the way EHRs document adverse drug reactions in order to improve allergy-related clinical decision support. When comparing vendors, ask how the EHR documents a variety of information, including adverse drug reactions.

Also look into companies experimenting with healthcare blockchains. For example, in 2017 the FDA began a research partnership with IBM Watson to use blockchain to securely share EHR, clinical trials, genetic sequencing, and even mobile wearables data.

For more tips on buying a new EHR, check out these posts:

Is Your EHR New Payment Model Ready? Questions to Ask Your Vendor

3 SOAPWare EMR Alternatives Compared

The Top 6 Free and Open Source EMR Software Products

Looking for Medical Practice Management software? Check out Capterra's list of the best Medical Practice Management software solutions.

About the Author

Cathy Reisenwitz

Cathy Reisenwitz

Cathy Reisenwitz is a former Capterra analyst.


No comments yet. Be the first!

Comment on this article:

Comment Guidelines:
All comments are moderated before publication and must meet our guidelines. Comments must be substantive, professional, and avoid self promotion. Moderators use discretion when approving comments.

For example, comments may not:
• Contain personal information like phone numbers or email addresses
• Be self-promotional or link to other websites
• Contain hateful or disparaging language
• Use fake names or spam content
Your privacy is important to us. Check out our Privacy Policy.