At the heart of Project Big Life are algorithms that predict the risk of developing diseases, dying, or using health care. There are three types of predictions at Project Big Life:
Project Big Life algorithms are developed using Canadian big health data that is routinely-collected by Statistics Canada and provincial health agencies. The 'big data' approach enables an effective ability to develop precision health algorithms. Algorithms at Project Big Life can accurately assess risk for groups of people with distinct characteristics or health profiles—including situations where a health profile represents only a fraction of the overall population.
Disease and life expectancy algorithms start with data from the Canadian Community Health Survey (CCHS), which asks people questions about their general health and lifestyle (smoking, alcohol, diet and physical activity). Continuously collected since 2001, the CCHS has over 1 million respondents—one of the largest surveys of its kind worldwide. What is even more unique is the ability to follow survey respondents over time. Respondents to Statistics Canada’s health surveys have generously given permission to link their responses to their health records—providing researchers with a unique resource to examine how healthy living affects future health. How unique? Physicians, nurses, health planners and others use Project Big Life algorithms in their work (and personal life) because there is no other source of information that better reflects healthy living in the diverse Canadian population.
The algorithms used on the Project Big Life website are published in peer-review literature. Individual algorithms may have additional web appendices, visualization tools and other resources to describe how the algorithms were developed and/or how to use the algorithms. These resources can be found through our GitHub repository and/or the algorithm publications.
A predictive algorithm for the calculation of 5-year risk of cardiovascular disease. Developed and validated using the 2001 to 2008 Canadian Community Health Surveys (CCHS). Focus is on health behaviours (smoking, diet, physical activity and alcohol consumption). The model is currently calibrated for Canada 2013, with provisions to calibrate to other countries.
There were 104 219 respondents aged 20 to 105 years, 3 709 cardiovascular events, and 818 478 person-years follow-up in the combined derivation and validation cohorts.
5-year cumulative incidence - males = 0.026, 95% confidence interval [CI] 0.025–0.028; females = 0.018, 95% 0.017–0.019.
Discrimination - c-statistic: male model = 0.82, 95% CI 0.81–0.83; female model = 0.86, 95% CI 0.85–0.87.
Calibration - overall population 5-year observed cumulative incidence versus predicted risk: males = 0.28%; females = 0.38%. Calibration slope females: 0.9734, SE 0.0698; for males: 0.9295, SE 0.0731. Observed versus predicted < 20% difference in predefined policy-relevant subgroups (206 of 208 groups) at P
Trial registration: ClinicalTrials.gov, no. NCT02267447
The CVDPoRT algorithm viewer shows how each predictor contributes to overall risk. Many of the predictors are included as continuous exposures using restrictive cubic splines with age interaction. The algorithm viewer was created to explore the relationship between these exposures and the predicted 5-year risk of cardiovascular disease.
Additional reference data includes:
See the API/developer page for additional information.
Manuel, D., Tuna, M., Bennett, C., Hennessy, D., Rosella, L., Sanmartin, C., . . . Taljaard, M. (2018). Development and validation of a cardiovascular disease risk-prediction model using population health surveys: the Cardiovascular Disease Population Risk Tool (CVDPoRT). Canadian Medical Association Journal, 190(29), E871-882. doi:doi: 10.1503/cmaj.170914
Taljaard, M., Tuna, M., Bennett, C., Perez, R., Rosella, L., Tu, J. V., . . . Manuel, D. G. (2014). Cardiovascular Disease Population Risk Tool (CVDPoRT): predictive algorithm for assessing CVD risk in the community setting. A study protocol. BMJ Open, 4(10), e006701. doi:10.1136/bmjopen-2014-006701