Skip to main content

Because your voice matters.

Member, Predictive Modelling of Healthcare Utilization Research Team

Posted • Last updated


Commitment: Short-term

Connection method: Virtual

Open to Northern Region

Last updated

Volunteer Opportunity
Here is an opportunity to predict the future! Join our team in using quantitative evidence and data analysis techniques to predict future needs for health care utilization.


Lead Organization/Department
School of Nursing, University of Northern British Columbia and Computer Science, Thompson Rivers University

We are excited to apply modern statistical methods, such as machine learning techniques, as we predict the need for health care services across interior and northern British Columbia. We aim to support better use of the statistical findings and models with the development of a user-friendly platform to support the understanding of the findings. We are looking for patient partners who are excited to work together with us throughout the process and who will be able to provide feedback on our data. visualization platform.

Level of Engagement
This opportunity is at the level of collaborate on the spectrum of engagement. The promise to you is that the health care partner will work together with you to formulate solutions and incorporate your advice and recommendations into the decisions to the maximum extent possible.

• Experience using data to inform decision-making
Experience working collaboratively in a team
Confident sharing opinions
Some familiarity with numbers and data analysis

• Number of vacancies: 1
Location, Date, Time and Frequency: Team meetings are held monthly on the 2nd Wednesday of the month via video conference. Patient partners will review study findings and provide feedback by e-mail or video conference during or in between monthly meeting times. Project runs until December 31, 2021.

Pre-approved travel expenses will be reimbursed.

Key health care system resources for supporting the health and well-being of Canadians, such as space in hospitals and continuing care facilities, are costly and finite. Ensuring the most appropriate and effective use of these resources is crucial to health care system performance. Ongoing data gathering activities, such as the interRAI Resident Assessment Instruments for Home Care and Long-term Care (RAI HC and RAI MDS), capture rich information about the people currently and previously within the healthcare system. However, accessing and utilizing this information is not always straightforward. In particular, relying not just on aggregate results can improve the precision of decision making and acknowledge the differences among people and groups.

Mathematical and statistical modelling provides rigorous and informative methods for guiding health care policy and decision making. Bed modelling is a well-studied subject within the field of discrete event modelling, with seminal papers going back to the 1990s. More recently, machine learning methods have been combined with health data to predict clinical outcomes such as disease diagnoses and changes in health status. This is based on a wider literature of using highly multi-dimensional and/or longitudinal data to make predictions based on individual cases. Mathematical modelling is an effective tool for investigating a system based on its structure, characteristics, and behaviours. Modern statistical methods such as machine learning are capable of developing sophisticated models that take into individual-scale effects and complex interactions. Combining the two approaches will allow us to address system level concerns (e.g., needs for resources like hospital beds) by drawing upon (and not ignoring) the unique characteristics of the people inhabiting our distinct region.

Health Care Partner Contact Information

Carol Stathers
Engagement Leader, Patient and Public Engagement | Interior Region

From Our Community

Ovey Yeung

Patient Partner, Vancouver

Ovey Yeung

Being involved in the Patient Voices Network has broadened my understanding of the system and helped me empathize with health care challenges and limitations. What matters to me is to walk away feeling that my experience matters, that I matter!