Let's connect

Synthetic data: key insights from HIMSS20

Nowadays, the consumer revolution in the healthcare industry is rapidly growing and leaving no room for non-digital solutions. Especially, the cost data is a crucial element for any company, and experts from HIMSS say that the synthetic data is a way to deal with financial outcomes smartly.

The problem is that healthcare data often includes a vast amount of different sensitive files, such as procedures, medications, patient condition, follow-up tests, etc. For example, serving a million patients can reach dozens of gigabytes on your data storage. Not to mention that those files are often not synced and store outside the system.

As an example, Healthcare IT news cites the example of the patients who waste their time on having the same lab work done by both the doctor’s office and hospital without leaving the building.

According to Robert Lieberthal, an economist from the MITRE Corporation, healthcare data is one of the most sensitive information types today. Healthcare is completely personal; the regulations such as GDPR or HIPAA is crucial for today’s health care providers.

But those healthcare data protocols sophisticate the data analysis process for predictive modeling in retail, housing, or transportation industries. And the same is for the financial sector of healthcare. 

Total claims, negotiated rates, and billing codes aren’t interoperable with EHR data. It makes prices hard to obtain for various analytical sources. Most of the providers are often just unaware of the negotiated and paid cost of a particular service until well after the care is delivered, says Robert.

This situation clarifies the industry challenges for the next years, such as:

  • poor outcomes
  • high service cost
  • low-level patient experience
  • bureaucracy burdens

And here comes the synthetic data. This is a complex of totally fabricated patient records and claims data sets. It never links back to personal data, as it never based on it. Instead, the data is gathered and calibrated based on real-world data. Once the synthetic data is created, it can simulate the health IT system as well as clinical and EHR systems.

To face real-world problems, synthetic data algorithms often being developed from scratch. It’s not only about replacing the paper records but to solve real problems with a real weapon.

“Researchers, innovators, entrepreneurs, and policymakers all are creating synthetic patient records to answer a number of important healthcare questions,” says Robert Lieberthal in his interview to the HealthcareITNews. “At MITRE, we are working on Synthea, an open-source, fully synthetic set of EHR data. Synthea is based on realistic patient transitions for a wide range of conditions and has been used to create synthetic cohorts of entire states and important disease states and populations ā€“ for example, cardiovascular disease, veteran populations, and end-stage renal disease.”

Synthetic data usage also enables developers and clinicians to test the EHR systems in a sort of “sandbox” just before deploying them. It will make the release process smooth, safe, and cost-efficient.

Although synthetic data is not a one-size-fits-all solution and definitely not a wizard, it enables you with a high-level accuracy for the approximation. Thanks to the open-source nature of the synthetic data algorithms, it can easily be displayed as a graph, diagram, or any other real-time analysis user interface.