Decision makers at NYGH must monitor key metrics that influence the hospital’s care processes and funding reimbursement. The hospital needed an analytics architecture that could provide dynamic insight into large volumes of data.
The hospital redesigned its analytics architecture around an IBM PureData® System for Analytics data warehouse, with IBM Cognos® Analytics providing sophisticated interactive dashboards.
Powerfulvisualizations give clinicians and managers instant insight into operations
Yearsof data can be analyzed in minutes, accelerating trend analysis and drill-down reporting
Onedashboard can replace 20 to 100 static reports, streamlining development and increasing granularity
Business challenge story
As a community hospital, NYGH receives the majority of its funding from the Ontario Ministry of Health and Long-Term Care. To secure the funds it requires to serve the diverse communities in the North Toronto area, the hospital must be able to demonstrate that it is providing healthcare services that meet and exceed the province’s standards.
In Ontario, one of the key components for the funding model is Quality Based Procedures (QBP), where hospitals are reimbursed based on the types and quantities of patients they treat, using evidence-informed rates that are associated with the quality of care delivered. The QBP model aims to ensure that each hospital handles the required number of simple and complex cases for each type of procedure, while meeting targets around specific metrics such as readmission rates and length of stay.
To monitor and improve QBP performance, NYGH needs to be able to analyze each case along multiple dimensions—the cost per case, length of stay, discharge destination, complexity of case, age of patient, and so on. To meet this need, the hospital’s Analytics and Business Intelligence team built dozens of static reports for each QBP category, with each report giving a single perspective on the data.
Asmaa Maloul, Manager of the Analytics and Business Intelligence team at NYGH, comments: “With the analytics infrastructure we were using at the time, static reports were the only viable option—but we really wanted to be able to offer our users more dynamic insight.”
Sri Vijay Bharat Peddi, Business Intelligence Report Writer in the Analytics and Business Intelligence team, adds: “In the old model, if a user wanted to look at the relationship between multiple dimensions—for example, to assess the effect of patient age on the complexity of cases for a particular QBP—then we had to create a new report. The need to write and maintain hundreds of reports was becoming a major burden on our team.”
Re-engineering analytics for dynamic insight
To provide a more powerful and flexible way to monitor QBP performance, NYGH decided to re-engineer its analytics platform. The first task was to substantially increase the speed of the platform, which would make it possible to create more dynamic, interactive reports and dashboards.
The team started by migrating its existing data warehouse to IBM PureData System for Analytics. The new platform is a data warehouse appliance that integrates server and storage hardware with database and analytics software, providing a single easy-to-manage system. It uses a massively parallel architecture to accelerate queries, which means that unlike most data warehouse platforms, there is no need for time-consuming manual optimization techniques such as tuning, indexing and aggregated tables.
To feed the new data warehouse with data from source systems throughout the hospital, NYGH deployed IBM InfoSphere® DataStage® , which helps the team create, manage and monitor all the necessary extract, transform and load (ETL) processes.
Steven Bernard, Business Intelligence and Data Architect, comments: “The PureData System infrastructure makes it possible to load multiple years of data into the warehouse and achieve sub-second response times for complex queries on data-sets with up to 500,000 data-points. That opens up a new range of possibilities for trend analysis and interactive slice-and-dice reporting that would have been impossible with our old platform.”
Next, the NYGH team enhanced its reporting and dashboarding capabilities by upgrading to the latest version of IBM Cognos Analytics. This significantly improved the range of visualization options available to the organization’s report-writers and analysts, enabling them to create richer, more interactive charts that combine multiple dimensions into a single graphic.
“Cognos Analytics’ new visualizations are very powerful,” says Sri Vijay Bharat Peddi. “A physician or nurse manager can look at a graph and see at a glance if something isn’t right. If they want to investigate further, they can filter the data and harness powerful drill-through reports to gain deeper insights into performance and outcomes.”
Asmaa Maloul adds: “Cognos Analytics also makes data governance much easier, which is critical when you are working with sensitive healthcare data. For example, with our QBP dashboards, it’s possible to drill right down to the level of individual patients—but only certain users are allowed to do this. Cognos makes it easy to set access permissions on a very fine-grained level, and to audit the whole environment to ensure that each user is authorized only to view the data they need.”
Rich insight into hospital operations
With the new analytics platform in place, NYGH is able to provide clinicians and managers with much richer insight into the hospital’s operations.
For example, in the emergency department, clinical and non-clinical staff now have access to a dashboard that highlights daily and weekly performance across multiple dimensions.
Sri Vijay Bharat Peddi explains: “Metrics like patient wait times and length of stay are critical to the performance of the emergency department and inpatient units, but from an operational perspective, there might be dozens of factors that drive those metrics. With the new dashboards, we can monitor each dimension both individually and in its relationships with other dimensions, which helps to understand the real drivers of hospital performance.
“We can look at factors like time of day, for example—perhaps there are unexpected busy periods that cause a backlog. We can then try different staffing strategies to address the issue. And by constantly monitoring the results, we can find out what works and what doesn’t—so we can continuously improve.”
Asmaa Maloul adds: “From our perspective in the Analytics and Business Intelligence team, Cognos Analytics makes our reporting portfolio much easier to manage. We’ve been able to replace literally hundreds of static QBP reports with a handful of interactive dashboards, so there are far fewer assets to maintain; and because the data is all connected, there is much less risk of inconsistencies.”
Steven Bernard concludes: “With our new IBM Analytics platform, we now have a fast, powerful operational decision support solution that is easy to use and helps clinicians and administrators serve themselves with the data they need. As a result, our team has more time to focus on next-level analytics projects, such as building predictive models with IBM SPSS® Modeler.
“Above all, the solution gives us the insight we need to understand and improve QBP performance, helping us secure vital funding for our services and continue to provide our diverse communities with the best possible quality of care.”
About North York General Hospital
As one of Canada’s leading community academic hospitals, North York General Hospital (NYGH) provides an exceptional care experience for its patients and their families. Since 1968, NYGH has proudly served its diverse communities in North Toronto and beyond, offering a range of acute care, ambulatory and long-term care services.
Take the next step
IBM Analytics offers one of the world's deepest and broadest analytics platform, domain and industry solutions that deliver new value to businesses, governments and individuals. For more information about how IBM Analytics helps to transform industries and professions with data, visit ibm.com/analytics. Follow us on Twitter at @IBMAnalytics, on our blog at ibmbigdatahub.com and join the conversation #IBMAnalytics.