The Dirty-Data Problem in Data Science

HealthShare Clean Data as a Solution flyer image
HealthShare Clean Data as a Solution

The health data required for analytics, machine learning, and artificial intelligence algorithms is complex, decentralized, diverse, and difficult to gather. It may be structured, or unstructured. It’s hard to link data across health information systems to the same patient. Even the same data elements may be identified and stored differently in different systems. When you do reach across systems and locations to aggregate the data, it often creates a dirty mess, not a usable database. This lack of comprehensive, normalized, and clean data for the target population is holding back your progress, and that of the entire healthcare industry.

Introducing Clean Data as a Solution*

Clean Data as a Solution is InterSystems turnkey, hosted health data pipeline for analytics, dashboards, population health management, artificial intelligence, and machine learning applications. It connects to your data sources, aggregates, deduplicates, and normalizes the data, and delivers the clean inputs you need.

Clean Data as a Solution is completely delivered and managed by InterSystems. Each implementation uses selected InterSystems HealthShare functionality, configured to address your specific needs and linked via managed interfaces to target systems.

Interoperability Expertise

No other vendor has more experience connecting to health information systems and aggregating patient records than InterSystems. Providence Saint Joseph Health, for example, is a U.S. health system operating in seven states, with 119,000 caregivers serving a population of 9 million. In two Providence regions, HealthShare aggregates patient records from 45 unique electronic medical record systems to create one clean, consistent, unified care record for each patient.

Data In

Clean Data as a Solution simplifies and accelerates achievement of your goals. Once you establish business relationships with the data source owners, InterSystems can bring in the data. Your own sources might include electronic health record and insurance claims systems, molecular diagnostics, social determinants of health, and remote patient monitoring systems. Unstructured data, such as clinical notes, can also be incorporated.

Data Out

Clean Data as a Solution uses select HealthShare features to support different use cases. Features may include integration, patient matching, aggregation, normalization, terminology and data enrichment, de-duplication into a unified care record, and clinical viewing capabilities. The result is a data set without duplicate records, formatting errors, incorrect information, or mismatched terminology. You can receive the data in a variety of ways:

  • Through InterSystems product user interfaces, or APIs such as FHIR or SQL that are part of Clean Data as a Solution
  • Via Spark or SQL to Tableau, PowerBI, or similar applications
  • Pushed to your applications in a format they can consume, such as CCDA or FHIR
  • To your own cloud or on-premises applications developed with a licensed instance of InterSystems IRIS for Health

InterSystems Managed Services

InterSystems designs, operates, and maintains Managed Services, such
as Clean Data as a Solution, in independent environments for each client.
We eliminate the burden of purchasing and managing the infrastructure
required for highly available solutions. Managed Services include:

  • Selected InterSystems product functionality
  • All data center resources, including hosting, hardware, and network capacity needed to run the solution
  • Ongoing maintenance of all solution components
  • Customer-specific configuration and implementation services to bring the solution live, including building connections
  • 24/7 support for the solution including real-time monitoring
  • Seamless upgrades
  • Sophisticated security and data protection programs

InterSystems Managed Operations

InterSystems operates geographically dispersed U.S. data centers for resiliency, with experienced staff managing infrastructure, security, and performance on a 24/7 basis. Managed operations include hosting, automated monitoring and alerting, ongoing maintenance, and monthly operational reports.

Learn More

To learn more about Clean Data as a Solution, HealthShare, or InterSystems Managed Solutions, call us at 1-800-753-2571.


*HealthShare Clean Data as a Solution is available in the United States only.

“The tool acts as a clearinghouse for data so that we aren’t building a number of legacy pipes every time we want to connect to a new system. Out of the box, InterSystems product comes with a lot of standard APIs…InterSystems is very good at trying to democratize healthcare data.”

HIE Director
KLAS Performance Report
“Interoperability Platforms 2019: Shifting Away From Traditional HIE”, October 2019
background image of glasses

How can we help?

How can we help you meet your needs and help your organization reach its goals.

Take the Next Step

We don’t share your personal info with anyone.
Check out our Privacy Statement for more information.