Speaking at the Office of the National Coordinator for Health Information Technology’s (ONC) annual meeting in Washington, Karen DeSalvo, the national coordinator for health IT, addressed what she believes to be the critical challenges for the healthcare industry: data interoperability and integration.
“We still have so much work to do as an ecosystem to have data that is interoperable, not just systems that are interoperable,” said DeSalvo. “We want to move to a place where we’re working off of the same language so that there’s not the added work and expense, and sometimes frustration, of not having federally recognized standards, but also creating opportunities to really advance new kinds of standards that can advance the field.”
However, for data interoperability and integration to become a reality, it will require a change in healthcare IT industry culture.
“It would be great for the healthcare industry to have a federally recognized format for healthcare data,” said Kirit Pandit, president and CTO of VitreosHealth, a leading predictive analytics company. “Unfortunately, the electronic medical record (EMR) companies have formed factions, with each promoting their standard.”
According to Pandit, until the government is able to create a federal standard for healthcare data, the burden falls to health IT vendors to make connectivity possible.
VitreosHealth is an example of a company that has made integration a reality without getting bogged down by interoperability. As a healthcare analytics company, VitreosHealth understands that their ability to clean massive amounts of data greatly improves the information they deliver to clients.
“We have developed capabilities that enable us to process data in various formats in a highly automated manner,” said Pandit. “This allows us to shorten our implementation time and deliver real value within a few weeks of receiving the data.”
VitreosHealth recognizes that to provide full value to their clients, the company needs to seamlessly utilize multiple sources and formats of data.
“We realized early on that the emergence of digital EMR data is a huge milestone,” said Pandit. “It’s a treasure chest of rich clinical data that tells a detailed clinical story of a patient that can be used to predict clinical outcomes in the future. However, we soon found out that this clinical data needs to be mapped to cost-and-quality data in order to predict cost-and-quality outcomes. For that, we needed claims or billing data. We then realized that getting clean EMR and claims data for all members was not always easy. So we had to leverage sources like risk assessment screenings. Finally, on the non-clinical side, it was important to use information like socio-economic data to calculate non-clinical risk. To complicate this further, it is very difficult to receive all these data sources at the same time. This means our data model has to be ‘additive’ rather than ‘rip and replace.’ This is core architecture that the VitreosHealth platform is built on.”
Recently, VitreosHealth was awarded the 2016 North America Frost & Sullivan Award for New Product Innovation. One of the reasons given by Frost & Sullivan is the robustness of VitreosHealth’s data gathering and analysis.
The Best Practices Research document states, “VitreosHealth created an advanced predictive analytics solution that expands upon traditional risk analysis solutions to provide a more accurate predictive risk analysis. Its advanced capabilities enable the company to identify relevant care management strategies, helping clients reduce the healthcare costs of its patient populations and increase revenues through improved Star scores. VitreosHealth’s highly flexible platform enables it to evolve as its customers’ needs change, enabling long- term partnerships to enact patient lifestyle changes, thereby facilitating high savings for provider networks and care managers.”
“There are very few healthcare analytics companies that are able to seamlessly integrate multiple data formats like we can,” said Pandit. “One thing I have learned in my 20 years of data analysis is that developing data interoperability and integration capabilities is not easy. It takes time because you are inherently dealing with dirty data and there is no short cut to being able to ingest it.”