Big Data and Analytics – Part 2

Predictive AnalyticsBy Sarianne Gruber
Twitter: @subtleimpact

Read Part 1.

Michael Dulin, MD, PhD was a featured speaker at the Big Data Healthcare Analytics Forum, held in New York City in June. I had the pleasure to interview Dr. Dulin at the conference and learn about the Carolinas HealthCare System’s Dickson Advanced Analytics (DA2) group. They are leaders in Population Health boosting predictive analytics and making a huge impact on preventive care for patients and community health. Their state-of-the art Enterprise Data Warehouse integrates patient information from clinical, billing and claims data. This system brings together information from “more than 5 million patients into one repository that includes 1.5 petabytes of data across the system – equivalent to storing the entire print collection of the Library Congress”.   Here are some of the advantages of a centralized system as shared by Dr. Dulin.

Can you tell us how you manage the systems at Dickson Advanced Analytics?

At the system level, we do some really exciting work there too. Our system has taken on what is called Hoshin planning. Basically using data plans to identify the best way to implement on our strategy in a system and our data team also provides all the information to our high level executives to understand how we are doing against our strategy and also how the course tracks. So we really are across the board not just in the clinical care delivery, but a health system as a whole we are now using data and analytics to really drive decision making. It has been an incredible time for us.

How do you disseminate the information so it actually becomes updates into work flows, or changes for patient engagement? Can you address any of these issues?

That is one of the most difficult parts of analytics is figuring out how to integrate it into the work flow and how not to over burden our physicians. Physicians are already managing incredible amounts of data and doing all sorts of difficult work, how do we make their life easier with the data and analytics. To me the hard part isn’t necessarily all the work behind the scenes to build the analytics but its partnering with the people on the front lines and making sure that we’re engaging them in the process so they understand the changes, they’re informing and then they can take them up and use them every day when working in the clinical domain.

I feel very fortunate to be able to work at Carolinas HealthCare system. It’s exciting that we’ve had the foresight to see how important data and analytics would be. And I feel very fortunate to be in a position to use my skills to help our organization in developing this competency.

What recommendations would you make to other institutions first starting out in analytics?

The most important part is the right people in place. Today there is a lot of demand for the talents that are needed. The banking industry some of the hi-tech industry are trying to find the same data scientists that we need to drive this work. So it is really hard to find the right people now and to bring those people together and develop opportunities for them to develop and apply their skills. And secondary to that is the technology. After that is the data itself. It’s surprising to me since the data hasn’t been actively used for years how the quality of the data can suffer it has taken us years to put governance structures around the data and help them improve the quality of data. So early investments in governance, finding the right people and understanding how to apply the technology and be ready for the next generation technology that is coming out as well.

Have you encountered any interoperability challenges with your hospital systems?

It has definitely been a challenge for us and our hospital. But I think like most hospitals across the country. When we made some decisions about technology, we decided to go with one vendor for most of our EMR system so that has helped us. But it is certainly difficult when you have a new hospital system come join us or new clinic if they have a different medical record interoperability has been very difficult. So we’ve actually as we built up our data and analytics capabilities we built it to be agnostic of any EMR systems we went with a standard commercial data model to help us to build something that was agnostic with EMR systems. I really do feel confident that we can in the future break the code of electrical medical systems and bring that clinical data into our centralized data warehouse. But it is a lot of work, effort and challenge. I am hopeful for the future. I think that interoperability between systems will get better as we move into the future. Hopefully within the next couple of years it will be easier to bring that data together into our system. But we have a lot of the deliveries systems that we use to get the information back to our clinical teams it works outside of our single electronic health record and does allow us in the future to be more agnostic with the EMR systems that are implemented.

How do you think data and analytics impacts utilization?

To the point of utilization, I really think that data and analytics are fundamental to our movement and to a value based care delivery system. And so identifying how to best direct patients to get the right care at the right time, proactive care so they don’t end up inappropriately utilize the healthcare system. So I think it is a very exciting time for us as we move into that value based world.

Would you like to add any final thoughts?

It’s really exciting to be here at the meeting and hear all about the work that is going on behind the scenes. I really feel like this going to be the future of how we deliver healthcare. I think it is going to make it easier for our patients. I think it is going to make it simpler and less complex for our providers once we figure out how to get the data, how to run the analytics behind the scenes. And so I am very much looking forward to the future of healthcare where we rely on and become data-driven organizations. It’s been a long time coming and that day is pretty close at hand.

About Michael Dulin, MD, PhD
Dr. Dulin helped to grow the Dickson Institute for Health Studies from a small research team into a centralized resource for data and analytics services for the system that employs over 100 employees. He was promoted into the position of Chief Clinical Officer for Analytics and Outcomes Research in 2013, where he oversees outcomes research for the system and co-leads the team. He received his undergraduate degree in electrical and biomedical engineering from the University of Texas. He earned his PhD from the University of Texas Health Science Center in Houston, and his medical degree from the University of Texas Medical School in Houston.

About Dickson Advanced Analytics (DA2) at Carolinas Healthcare System
The DA2 vision is to be an innovative leader in advanced analytics and business intelligence that predicts health needs, continually elevates patient outcomes, and drives transformative research and solutions to promote the health of our communities. Carolinas Health System incorporates about 40 hospitals and over 600 care locations in North Carolina, South Carolina and Georgia. It is one of the largest HIT and EMR systems in the country.To learn more about  Dickson Advanced Analytics, please the Carolinas HealthCare System website. Follow them on Twitter (@Carolinas).