MCHP drives health care policy, compliancy with SAS®

The Manitoba Centre for Health Policy analyzes huge volumes of data from multiple databases every year, but was challenged with meeting stringent provincial requirements for auditing and access control. Using SAS, the research centre has been able to better manage its data in a clustered environment, allowing it to study disease trends, service use and quality indicators to ensure the Manitoba Department of Health has the evidence it needs to make policy decisions.

Since 1970, the Manitoba Centre for Health Policy (MCHP) has analyzed more than 20 million pieces of information every year from 90 government, health and education databases that maintain characteristics about patients, doctors and health-related issues. And that data is growing – the provincial physician-billing database alone produces 16 million records a year.

MCHP, a research unit in the Department of Community Health Sciences with the University of Manitoba's Faculty of Medicine, conducts population-based research on health services to study disease trends, service use and quality indicators using socioeconomic determinants of health. After analyzing the data, evidence from published MCHP reports are used to inform policy decisions and program delivery.

While Base SAS was being used for the bulk of the analysis, the volume of data was continuing to grow at an unprecedented rate. MCHP has a core base of 12 researchers with 40 people directly using the data. The research unit has about 100 active research projects in the past couple of years. "We also had to meet new requirements around auditing and access control in the province, which have become more stringent," said Charles Burchill, Manager of Program and Analysis Systems with MCHP. "We needed a database management solution that would help us manage all of this data, while meeting government regulations and privacy requirements."

After looking at its options, MCHP chose to move its entire data repository over to the SAS® Scalable Performance Data Server®, which delivers subsets of information harvested from large stores of enterprise data quickly and on demand. All of the data is linkable so MCHP can look at a broader perspective of health. MCHP is also using SAS® Enterprise Miner™, which streamlines the data mining process to create highly accurate predictive and descriptive models based on analysis of vast amounts of data to identify chronic diseases and their associates, and then test those assumptions.

"We're not mining for data," said Burchill. "We're putting forth a hypothesis and letting SAS Enterprise Miner come up with decision trees to find out what's important in the identification of chronic diseases such as diabetes, asthma and heart disease."

MCHP develops and maintains a comprehensive population-based data repository on behalf of the province for use by the local, national and international research community, which supports the development of policies, programs and services that maintain and improve the health of Manitobans. This provides health care insights about the types of treatments that various population segments are receiving, probable outcomes and general trends.

These findings are made available to the Manitoba Department of Health and regional health authorities to help make decisions about which services are required in which regions, depending on socioeconomic factors. The burden of diabetes in Manitoba, for example, is variable depending on the community. SAS helps MCHP determine how many people have diabetes within a certain community and how many are using health care services associated with diabetes, which allows regional health authorities and other health care planners to target education or service campaigns where they're needed most.

One of MCHP's reports found 37 percent of Manitobans were diagnosed with a mental illness over a five-year period where one in 10 physician visits and one in 10 hospitalizations were related to these conditions. MCHP spotted that trend using SAS, which highlighted the need to examine resources and program delivery throughout the province, including its Provincial Suicide Prevention Strategy. "We are using the data as further evidence of the need for a new mental health and addictions data system," said Yvonne Block, Director of Mental Health, Addictions and Agency Relations for Manitoba Health. "We've also used it to pull together a planning group to look at current and future needs in the area of access to psychiatrists, and as further evidence of the need for collaboration between mental health and primary health care initiatives."

Using the SAS Scalable Performance Data Server, MCHP can take data sets going back 30 to 40 years and combine them into more manageable clusters so researchers will only see one file, which has been optimized to provide the information the researchers are looking for. "In an ad hoc environment, it used to take a researcher two or three days to sort through files and clean data," said Burchill. "Now some of those queries are being built up in a matter of hours. We've seen significant efficiency improvements, and we also have much better auditing capabilities."

MCHP also expects to see related cost savings from its use of SAS. In the past, researchers and analysts had to physically sit in the office to use the system. MCHP is piloting remote sites that run clients through a virtual private network so researchers can access the system remotely. "The external researchers are happier because they get access to the data they need, rather than having to sift through irrelevant information, which saves time and money. And all of this is accomplished within a compliant environment," said Burchill. "Our use of SAS allows us to do that."

Charles Burchill was nominated for the 2006 SAS Customer Value Award and received an Honorable Mention. The SAS Customer Value Award was created to honor and reward an individual for ongoing support in his or her local SAS community.

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.