Defining a health care data science strategy can be daunting. Do you build a team or buy services as needed? Where do you find and validate talent? Can an internal team really produce enough value to make it worth the effort and cost? What do you need in place to get started? At OSF HealthCare, we built our Advanced Analytics team, comprised of data scientists and statisticians, more than three years ago and have learned a lot along the way.
The Advanced Analytics team was established October 2013 to specialize in utilizing data science techniques and robust statistical analysis to serve high-performing care delivery teams and their patients. We do this by closely collaborating with business and clinical leaders within OSF to understand the problems the health care system is facing.
From there, we explore and collect data around the issues in question, prepare the data needed to find solutions, build effective models that we believe will best fit a particular problem, validate solutions with business and clinical leaders and implement solutions to enable business and clinical actions guided by model results.
We recently received the opportunity to present how we developed our group and the successes we’ve accomplished since establishing the Advanced Analytics team at the Predictive Analytics World Healthcare Conference in New York.
Why and How We Developed an Advanced Analytics Team
OSF chose to create an Advanced Analytics team for a variety of reasons:
- The dilemma is not about understanding the population’s risk but identifying WHO is at high risk
- Reduce internal costs through appropriate intervention targeting
- Reduce clinical variation to improve clinical care
- Evaluate effectiveness of process changes or interventions
- Reduce non-value added work by appropriately leveraging normally collected clinical data
- Drive additional value from our electronic medical record system investment
The Advanced Analytics team is relatively new, so the Healthcare Analytics division at OSF researched comparable jobs in the country, developed new job descriptions and engaged the members of the division to discuss what we wanted to see in a data science group.
We have found a variety of benefits since this team’s development. These include better alignment with the strategic initiatives set forth by OSF leadership, full intellectual property of the models we develop, the development of expert knowledge and the ability to make improvements quickly.
What Advanced Analytics Has Achieved
Since the Advanced Analytics team’s inception, it has built a variety of models to help OSF innovatively solve a number of issues. The most highly touted is a predictive model that helps clinicians identify patients most at risk for hospital readmissions within a 30-day period. Over the course of a year, this resulted in more than 400 fewer readmissions than expected in our medium-high and high-risk patients. Compared to a prior approach of reducing readmissions, the team also found it was able to reduce about 67 percent of nursing assessment activities and decrease the flow into case management by about 44 percent. These staff time reductions translate to a little more than $2 million per year that we can put back into direct patient care.
Another model helps clinicians recognize the risk of sepsis in patients quickly. The product resulted in care teams being alerted of possible septic patients 68 minutes faster than a solution previously used. The model also resulted in the development of strong collaborative relationships across multiple teams.
The Advanced Analytics team has created multiple different models to solve various health care problems. While these models have realized successes, there are plenty of challenges along the way. We expect to continually update and enhance our predictive models as this program grows. We look forward to working with the rest of OSF Innovation to generate even more solutions that will help us tackle our focus areas of aging in place, more for those with less and radical access to care.