Advancing mental health care with predictive analytics
SAS enables a data-driven approach to health treatment and hospital operations.
Optimized health outcomes and hospital resources
Canada’s Centre for Addiction and Mental Health uses SAS® Analytics to improve care and streamline hospital operations
In Canada, one in five people experience a mental illness or addiction problem – well above the global average. But unlike physical illness, mental afflictions such as depression, anxiety, PTSD and eating disorders often go untreated as too many people choose to suffer in silence rather than seek professional help.
The Centre for Addiction and Mental Health (CAMH) is working to remove the stigma from mental illness and addiction while providing world-class care to those in need. As Canada's largest mental health teaching hospital, CAMH is a national leader in care, research, education and social change. The Toronto-based institution treats more than 34,000 patients each year.
Rebecca Comrie, CAMH’s Executive Director of Performance Improvement, is responsible for using data and analytics to advance the hospital’s mission.
“Today, there’s a dearth of knowledge about the incidence and prevalence of mental illness in Canada and worldwide,” Comrie says. “We’re at the forefront of capturing meaningful information about the state of mental illness to better measure and improve health outcomes.”
We’re at the forefront of capturing meaningful information about the state of mental illness to better measure and improve health outcomes. Rebecca Comrie Executive Director of Performance Improvement CAMH
Marrying EHR data with analytics
Comrie joined CAMH shortly after it implemented electronic health records (EHR), a major IT project that centralized patient records into an enterprise data warehouse. “But we quickly realized an EHR system alone doesn’t mean meaningful data,” she says. “And it certainly doesn't mean meaningful information.”
Curiosity was starting to build around how EHR information could help solve clinical problems. CAMH was amassing copious patient data on appointments, labs, medications, demographics and medical history. Comrie and others were eager to explore how CAMH could use this valuable information to improve clinical outcomes and streamline operations.
CAMH embarked on an enterprise analytics strategy aimed to combine its disparate tools, methodologies and processes into a single cohesive and consistent environment for analytics. “We had the ambitious goal of developing the best hospital analytics practice in the province, if not the country,” Comrie says. “And we needed a solution to provide robust analytics for everything we might need.”
CAMH licensed SAS Analytics, gaining a versatile analytics platform to manage, model and visualize data for a range of purposes. Comrie and her team soon began using analytics to address specific challenges across the organization.
Predictive modeling in the emergency department
One of Comrie’s first projects was to analyze emergency department activity. To her clinical colleagues, the department was feeling busier than normal. Comrie offered to look into it.
After analyzing the data, Comrie and her team discovered that emergency department visits had jumped 82% in the last six years. Next, they began modeling population data provided by the Ministry of Health to predict future emergency department activity. By knowing how many patients to expect, CAMH officials could devise the right care models and process optimization projects to accommodate future needs.
“We were able to provide a holistic data and analytics solution to support them not just in understanding the current situation but also to support their decision making in terms of program planning and quality improvement,” Comrie explains.
In a similar project, Comrie and her team used SAS to optimize care for alternate level of care (ALC) patients – people who occupy acute care hospital beds but no longer require hospital care. By predicting which patients are ALC upon admission, CAMH can ensure these patients are seamlessly moved into the right care setting at the appropriate time. This also benefits the hospital and other patients by freeing up beds for those who need them most.
CAMH uses social determinant data captured at admission to perform this analysis. Throughout the project, they tested several predictive models including univariate and multivariate analysis. In the end, they landed on a predictive model that was 80% accurate – a major step forward in streamlining treatment for ALC patients and optimizing bed space.
CAMH – Facts & Figures
patients seen annually
physicians, clinicians, researchers and support staff
Securing government funding
As a public organization, CAMH receives government funding and thus must be adept at justifying funding requests for capital projects. If funding is unavailable from the government, money must come from private donors, which are not always easy to obtain.
Having succeeded in articulating operational needs for the emergency department and ALC patients, CAMH began looking at how to use data and analytics to secure government funding for a new bridging clinic – the Canadian equivalent to a US urgent care center. The new clinic would divert emergency department traffic and provide a better care setting for certain patients.
Once again, Comrie and her team helped their clinical partners formulate a business case to validate the demand for a new clinic. Using SAS predictive analytics, they were able to forecast things such as bedding and staffing needs, the number of patients expected each year and how many patients would be diverted from emergency departments.
In the end, the analysis helped secure 100% government funding for the new 23-bed bridging clinic. “I can't think of any other hospitals that are being given funding to open brand-new entire units,” Comrie says. “By presenting the needs and doing robust modeling of the needs going forward, we were able to secure government funding without having to seek outside donations. As you can imagine, this is difficult and rare in a publicly funded system.
“Funders have to be confident in your data, your methodology and your approach,” Comrie continues. “With SAS, we've been very successful on that front.”
Looking ahead, thinking holistically
The Canadian government recently announced a historic four-year investment of $2.1 billion to further improve mental health and addiction services in Canada. With momentum building around its predictive modeling and analytics capabilities, CAMH is well-positioned to maximize this investment for those experiencing mental illness.
“Our partnership with SAS has really helped us give people a very strong impression of the ‘art of the possible’ when it comes to data,” Comrie says. “We now have tools at our disposal to do all manner of things from an analytic perspective, and we've been able to open up people’s eyes to what we can do with data and how it can really assist us in providing the best clinical care.”
CAMH now is looking at things like artificial intelligence, telemedicine and genomic data analysis to provide a more personalized approach to mental health treatment.
“We're really trying to be more holistic in our understanding of the people we serve who may have other chronic illnesses and primary care needs,” Comrie says. “The better we get at measuring success, the more we can deploy personalized treatments for our patients’ well-being and health.”
본 문서에 나오는 결과는 본 문서에 설명된 특정 상황, 비즈니스 모델, 데이터 입력 및 컴퓨팅 환경에 적합하게 되어 있습니다. 각 SAS 고객의 경험은 고유한 것으로, 비즈니스 및 기술적 변수에 따라 달라집니다. 따라서 모든 서술은 비전형적인 것이라는 점을 고려해야 합니다. 실제 절약, 결과 및 성능 특성은 개별 고객의 구성 및 조건에 따라 달라질 수 있습니다. SAS는 모든 고객이 비슷한 결과를 달성할 수 있다고 보증하거나 진술하지 않습니다. SAS 제품과 서비스에 대한 유일한 보증은 해당 제품 및 서비스에 대한 서면 계약의 보증서에 명시되어 있습니다. 본 문서의 어떠한 내용도 추가 보증을 구성하는 것으로 해석될 수 없습니다. 고객은 SAS 소프트웨어의 성공적인 구현에 따라 합의된 계약적 교환 또는 프로젝트 성공 요약의 일환으로 성공 사례를 SAS와 공유했습니다. 브랜드 및 제품 명칭은 각 기업의 상표입니다.