Healthways Heads Off Increased Costs with SAS^®

Healthways, the leading provider of specialized, comprehensive solutions to help millions of people maintain or improve their health and well-being, relies on SAS to identify high-risk patients and implement preventative actions.

Healthways knows that a key to successful disease management is the correct identification of those members in greatest need of care. Using SAS, Healthways reduces costs and helps to improve member health outcomes by predicting who is at most risk for developing specific health problems. In doing so, Healthways is able to coordinate intervention plans that address care designed to avoid complications down the road.

At Healthways, the goal is to empower health-plan members to manage their health effectively. The company achieves its objective using SAS for data mining and a group of robust artificial intelligence neural networks. To support predictive analytics, Healthways accesses hundreds of data points involving care for millions of health-plan members.

“We want to develop predictive models that not only identify and classify members who are at risk, but also anticipate who is at the highest risk for specific diseases and complications and then determine which of those are most likely to comply with recommended standards of care,” says Adam Hobgood, Team Lead, Advanced Analytics, at Healthways’ Center for Health Research in Franklin, TN. “Most of all we want to predict their likelihood of success with our support programs. By identifying high-risk members and implementing preventative actions against future conditions, we hope to head off the increased costs of care before they occur.”

Identifying potential problems
Healthways does more than just look at the most costly diseases. Using SAS’ advanced analytics to identify and deliver new healthcare resources to the individuals who can most benefit from them, Healthways improves outcomes, ultimately resulting in healthier members with reduced total medical costs.

Still, Healthways’ level of expertise in identifying members who are at risk goes deeper than risk stratification. Healthways also wants to identify members who are likely to experience future gaps in care so that they can intervene and provide care or advice through its extensive network before the problems actually occur.

How does Healthways use SAS?
Healthways provides disease and care management to more than two million health-plan members in all 50 states, the District of Columbia, Guam and Puerto Rico. The company provides its services on behalf of the nation’s leading health plans. It employs thousands of nurses at call centers throughout the country who collect data and provide clinical support to health-plan members and their physicians.

With SAS, Healthways builds predictive models that assess risk for certain outcomes and establishes starting points for providing services. Once Healthways loads risk-stratification levels into its own “clinical expert system,” the system evaluates clinical information from hospitals, data that nurses collect by phone and information that employer groups and health-plan members report.

Finally, the clinical expert system adjusts the initial risk-stratification levels based on the new inputs and expert clinical judgment. The resulting approach to member stratification is a hybrid solution that incorporates sophisticated artificial intelligence neural network predictive models, clinically relevant rule-based models and expert clinician judgment.

How does SAS improve performance?
Because models are run on an ongoing basis, health-plan populations are scored based on the most recent data available -- such as diagnostic and treatment codes and the demographic makeup of plan members. Healthways can easily recalibrate the models and reflect the impact of changes in benefit plans within the total member population.

“With Healthways constantly adding new members, we have a rich data set for building artificial intelligence predictive models,” Hobgood says. “SAS simply has the power to accommodate the massive data sets used in our predictive models. With SAS, we can rank-order our massive membership according to risk and prioritize the utilization of our expert clinical resources.”

Hobgood adds, “Powerful predictive modeling within large populations becomes increasingly valuable given the ability to focus in on the right people at the right time. “

The research team at Healthways is continuously working to fine-tune both the sensitivity and specificity of their predictive models. Medical care and evidence-based medicine models, based on a large number of variables, can result in a fairly wide target range without this attention.

Features embedded within SAS make this process more direct and ultimately make better use of limited resources for intervention. The Healthways team experience and rich data sets, combined with SAS functionality, result in a better process for identifying the right members for the best care intervention at the right time and for significant competitive advantage.

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Copyright © SAS Institute Inc. All Rights Reserved.