Humana's health analytics arm succeeds with help from SAS®
What if you could partner with a company that uses fully integrated pharmacy, medical, lab and behavioral health patient-level data of more than 12.5 million members to provide insight and evidence for your health economics, outcomes research and observational study needs?
Competitive Health Analytics (CHA), a Humana company that provides research and analytic services to the pharmaceutical and health care industries, is doing that and more using SAS® for health analytics.
"Our vision is to provide insights and evidence that improve overall health and well-being," explains Sarah Priddy, PhD, Director of Competitive Health Analytics. "We take a holistic approach in looking at total cost of care."
Priddy's team works on four project types: joint projects with Humana's other business units; collaborative work between Humana and major drug companies like Pfizer and Novo Nordisk; contract work exclusively for pharmaceutical companies; and projects for the federal government, such as the US Food and Drug Administration's Mini-Sentinel project.
All of the work involves tapping into Humana's extensive database of medical, laboratory and pharmaceutical claims data. CHA performs comparative effectiveness studies, drug safety analysis and subgroup analysis to find drugs that work particularly well in certain types of patients.
Humana used SAS Analytics before starting the CHA organization.
“SAS is something that is nested very deeply within Humana,” Priddy notes. So there was no question when CHA was formed that SAS would provide the analytics. What came as a pleasant surprise to SAS veterans at CHA was how newer versions of SAS, particularly the stored process and template features of SAS® Enterprise Guide®, expedite their work.
To remain competitive in improving quality and outcomes, CHA must quickly figure out whether it has enough claims information in its databases to meet the requirements of a prospective customer's proposal.
Although it has about 5 billion lines of data, a study might require that enough data is available on, say, diabetic patients with a heart condition taking one specific type of diabetes drug and another specific type of heart medicine.
CHA needs to quickly find the claims that meet the criteria and exclude the others. Using SAS, these feasibility studies take less than a day.
"With SAS we have a standardized way to do these studies," explains Anthony Louder, a CHA Research Leader.
"SAS has the power to handle large volumes of data," adds Robert Dufour, Research Manager. "In terms of quality control, even though many different research scientists might work on a project, we're all recording it the same way in SAS.''
Mining the data to improve health
CHA's successes include:
In addition to the work it has done for Humana and with private partners, CHA has won letters of commendation for its work on the Mini-Sentinel project. This FDA project involves monitoring the safety of drugs and medical products already on the market. The Mini-Sentinel uses pre-existing electronic health care data from multiple sources. Collaborating institutions, like Humana, provide access to data as well as scientific and organizational expertise.
- Studying medical and prescription use for patients later diagnosed with opiate abuse. CHA and a partner pharmaceutical company wanted to see if there was a pattern of medical utilization before diagnosis that could inform physicians of at-risk patients. CHA and its partner plan to publish the results of the study.
- Identifying the optimal price point for prescription co-pays within a benefit plan, so that the plan can be cost-effective, but the member continues to fill the prescription. Benefit administrators sometimes choose high prescription co-pays as a way to save money. CHA’s work with a pharmaceutical partner found a threshold where the higher co-pay actually cost the plan because people weren’t filling their prescriptions. Some of those patients ended up in the hospital with complications from their untreated illness.
- Analyzing the value of individual drugs within a class designed to treat a specific illness. "We study questions like, 'Do they act the same?', 'Do they cost the same?'" Priddy says. The goal is to provide guidance and insight to clients who can use the results to make formulary changes that will increase the desired outcomes for consumers.
"This is the fourth year of our participation, and it's been exciting," Priddy says.
She points to Humana’s work in tracking the adoption and use of the H1N1 vaccine and tracking of vaccine-related safety issues. “To have an insurance company commended by the FDA – I can’t say that happens every day,” Priddy added.
SAS is the standard for submission to the FDA, and using it with clients in the medical/pharmaceutical world helps CHA land business. "One of the reasons many of our clients talk to us is because of SAS," Priddy says. "It's like a common language now."
CHA is moving into doing studies that use SAS to predict outcomes. Rather than historic studies on how much people pay for a prescription, and then the resulting hospitalization costs if they don't fill it, the CHA scientists would like to be able to predict the ideal price point.
They also want to use SAS to help them predict underdiagnosed populations. An example is identifying people who have the types of claims associated with diabetes, but have not received a formal diagnosis.
Priddy is confident that her staff can deliver on these kinds of projects because of the success to date. Not only is CHA bringing in a regular stream of new customers, almost all of their business partners return to collaborate on additional projects. That repeat business metric says a lot, Priddy notes.
"We have been able to get the projects done on time, within cost and with high-quality results that our customers can act on," she says. "That's why they come back."
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.
Competitive Health Analytics (Division of Humana)
Analyze 5 billion lines of claims data for comparative effectiveness and drug safety studies. In particular, CHA needed to do feasibility studies quickly.
Complex feasibility study calculations can be done in a day. Clients often trust CHA because of their knowledge and use of SAS, a statistic confirmed by the business generated from repeat customers. The unit expects to grow by 50 percent this coming year.
““Our vision is to provide insights and evidence that improve overall health and well-being. We take a holistic approach in looking at total cost of care.””
Sarah Priddy, PhD
Director of Competitive Health Analytics