How Cleveland Clinic and Cox Automotive are Transforming with Analytics


Chris Donovan, Executive Director  
of Enterprise Information Management  
and Analytics at the Cleveland Clinic

Chris Donovan, Executive Director
of Enterprise Information Management
and Analytics at the Cleveland Clinic

Healthcare, like many industries, is in the midst of a paradigm shift, says Chris Donovan, Executive Director of Enterprise Information Management & Analytics for the Cleveland Clinic. "Historically, healthcare was really about intervention, and about taking care of you when you were sick and getting you better."

That type of care depends a lot on treatments like surgery, and as the largest single-site OR in the world, the Cleveland Clinic is good at that kind of care, says Donovan. But there's a shift occurring.

What's happening in healthcare now is a focus on preventative care. "How can we move away from just taking care of you when you show up as an individual patient in the ER or the doctor's office, to looking at a population of patients and thinking about how to prevent people from getting sick in the first place," says Donovan.

As you can imagine, this type of transformation requires analytics.

"Now we have to know, within the population we're trying to take care of, who are the highest-risk patients, and how best to intervene to drive a better outcome," he says.

That requires gathering a whole bunch of social data, demographic data, economic data. For some populations, sending an email works better, but for others a phone call or an in-home visit with a nurse will be more effective.

"We need to be able to do predictive models, to run clustering algorithms to understand how patients are connected to each other, and to run machine learning models so we can do this at scale," explains Donovan.

One example Donovan used is a change in post-surgery care for knee replacement patients. Using analytics, Cleveland Clinic developed a model to identify which patients would recover successfully at home instead of requiring post-acute care in a facility for all patients.

"We put the propensity score right into the clinical workflow, so when the doctor is determining the care path for the patient, they saw that score and had the conversation with the patient." The program was successful at taking patient needs into account and driving costs down, says Donovan.

Donovan spoke during the opening session of Analytics Experience in Washington DC on a panel, along with SAS CEO Jim Goodnight, SAS CTO Oliver Schabenberger and Shawn Hushman, Vice President of Decision Sciences and Valuations for Cox Automotive.

Jim Goodnight, SAS CEO; Shawn Hushman, Vice President of Decision Sciences for Cox Automotive; Chris Donovan, Executive Director of Enterprise Information Management and Analytics at the Cleveland Clinic; Oliver Schabenberger, SAS CTO.

Jim Goodnight, SAS CEO; Shawn Hushman, Vice President of Decision Sciences for Cox Automotive; Chris Donovan, Executive Director of Enterprise Information Management and Analytics at the Cleveland Clinic; Oliver Schabenberger, SAS CTO.

Shawn Hushman, Vice President of  
Decision Sciences for Cox Automotive.

Shawn Hushman, Vice President of
Decision Sciences for Cox Automotive.

Hushman describes data intelligence as the process of moving from specific analytics projects to building analytics frameworks. Instead of just building churn or retention models, he asks analysts to pull back and look at the original problems: dealers need more customers, the Web site needs to answer customer's questions -- and then solve for that problem.

This type of thinking is essential for new services like "instant cash offers" that simplify the trade-in process to a single click online.

"We now process petabytes of behavior information across our brands, which we leverage to build better consumer experiences, increase our vehicle valuation accuracy, provide consumers with relevant content, and expand our brand to address unmet needs."

Watch the full panel discussion below to hear what else Donovan and Hushman have to say, and to learn about the benefits of using SAS Viya. (The panel discussion starts around the 17-minute mark.)

See more videos from Analytis Experience, including talks from basketball star Magic Johnson and former US CTO Megan Smith.

Heather Lowe and Lane Whatley also contributed to this post.

[This post originally appeared on SAS Voices.]

Alison Bolen, Editor of Blogs and Social Content

Alison Bolen is an editor at SAS, where she writes and edits blog content and publishes the Intelligence Quarterly magazine. She recently picked up and moved her family and her home office from Ohio to New York. Since starting at SAS in 1999, Alison has edited print publications, Web sites, e-newsletters, customer success stories and blogs. She has a bachelor's degree in magazine journalism from Ohio University and a master's degree in technical writing from North Carolina State University.

How Can Marketing and IT Work Better Together?

If your marketing team is running up against obstacles when dealing with IT, here's a roadmap for communications to help get projects moving again.

3 Machine Learning Technologies to Watch Over the Next 3 Years

Booz Allen Hamilton's Principal Data Scientist and Executive Advisor Kirk Borne recently weighed in on a few of the rising technologies for machine learning. Here's what he said.


Re: Insurance companies
  • 10/16/2017 6:12:13 AM
NO RATINGS

That really means we need to work on both ends of the problems- doctors and insurance companies.

Re: Insurance companies
  • 10/15/2017 11:20:13 PM
NO RATINGS

I'm all for a health care score to predict outcomes as long as doctors are trained and have information on how that score is obtained, what are the contributing parts and the weight of each part.   I agree that scores can be highly predictive but they also need to be able to recoginize when it may be off. 

Insurance companies
  • 10/4/2017 9:33:26 AM
NO RATINGS

What we need now is the insurance industry to support this approach and change reimbursements. IN the long run, prevention is much less expensive that acute treatment. Our system just doesnt work this way currently.

Re: health analytics
  • 10/4/2017 9:26:39 AM
NO RATINGS

@kq4ym It's alo possible to trck if people are following their prescribed course -- not just taking the medication prescribed but doing the amount of exercise they should, etc.

Re: health analytics
  • 10/4/2017 9:25:19 AM
NO RATINGS

I would think we know quite a lot already about prevention of many diseases; changing diet, exercising more, eliminating unhealthy habits, etc. but getting folks to take those prevventative actions is maybe the more challenging problem. How analytics might be coordinated with changing people's attitudes and behavior might be an interesting journey to better overall societal health.

health analytics
  • 10/3/2017 9:11:43 PM
NO RATINGS

Three years ago, I intereviewed  Dr. Michael Dulin, chief clinical officer for analytics and outcomes research at Carolinas for More Info in the Name of Better Healthcare. He also believed in using analytics for proactive healthcare:

He explained that analytics can also track the correlation between those who end up in hospitals with the failure to adhere to one's prescribed treatment. A practical application that could emerge from such analysis could be a directive to "give away the medications in certain situations in order to keep people healthy and out of the hospital."

 

INFORMATION RESOURCES
ANALYTICS IN ACTION
CARTERTOONS
VIEW ALL +
QUICK POLL
VIEW ALL +