The SCIENCE

Introduction

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:

  • Risk of developing diseases and life expectancy
  • Risk of dying if you are near the end of your life
  • Diet quality

Big data = precision health

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.

Calculators for the risk of chronic diseases and life expectancy

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.

Our Calculators

Heart Attack and Stroke Calculator (Cardiovascular disease)

"What sets this cardiovascular risk calculator apart from other calculators worldwide is that it looks at healthy living, and it is better calibrated to the Canadian population," says Dr. Doug Manuel, lead author of the Cardiovascular Disease Population Risk Tool (CVDPoRT) in the Canadian Medical Association Journal.

The calculator uses responses from 104,219 Ontario residents from the Canadian Community Health Surveys (2001 to 2007) linked to hospitalizations and deaths to develop and validate CVDPoRT.

The calculator allows individuals to predict their risk of hospitalization or death from cardiovascular disease within the next five years. For example, if their risk is 5%, it means that 5 in 100 people like them will experience a serious cardiovascular event in the next five years. The calculator also provides heart age, an easy-to-understand measure of heart
health.

The Cardiovascular Disease Population Risk Tool considers many factors, including sociodemographic risks, health behaviour risks (smoking status, alcohol intake, diet and  physical activity), health conditions and more.

"People are interested in healthy living, but we don't often have that discussion in the doctor's office," says Dr. Manuel. "Doctors will check your blood pressure and cholesterol levels, but they don't necessarily ask about lifestyle factors that could put you at risk for a heart attack and stroke. We hope this tool can help people—and their care team—obtain better information about healthy living and options for reducing their risk of heart attack and stroke."

In addition to personal use, policy-makers can use the tool to calculate risk profiles for different populations. Currently set up for use in Canada, it can be adapted for any of the 100 countries around the world that collect health survey data.

Life Expectancy Calculator

The life expectancy calculator was developed using a statistical model to estimate the risk of death associated with smoking, unhealthy alcohol consumption, poor diet, and physical inactivity in Ontario. We calculated the risk of death for Ontarians who responded to Canadian Community Health Surveys from 2001 to 2008 and agreed to have their responses linked to their personal health information. There were approximately 1 million person-years of follow-up and over 9000 deaths in the development and validation datasets. The study adjusted for a wide range of risk factors, in addition to health behaviours and was published in PLoS Medicine.

The original life expectancy calculator was developed using Canadian Community Health Surveys from 2001 to 2005 (550 000 person-years of follow-up, with over 6000 deaths). For more information about the original study see www.publichealthontario.ca or www.ices.on.ca.

Stroke Calculator

The stroke calculator was created with the Stroke Population Risk Tool (SPoRT). SPoRT is a predictive risk algorithm that estimates the risk of hospitalized stroke based on healthy living and other sociodemographic and health indicators. Risk of stroke was assessed for 82 259 Ontarians who responded to Canadian Community Health Surveys from 2001 to 2005 and agreed to have their responses linked to their personal health information. People were followed for over 668 000 person years, with over 3 236 incident stroke events observed. The study adjusted for a wide range of risk factors, in addition to smoking, physical activity, diet, alcohol and stress. For more information, see the PLoS One Study here.

Health Care Cost Calculator

The health use calculator was based on the largest study to directly link healthy living and sociodemographic indicators to comprehensive health care. Health care costs for hospital, drugs, physician services and other government-funded health care were examined for 80,000 Ontarian respondents of the Canadian Community Health Survey who agreed to have their responses linked to their personal health information. In total, there was $430 billion in Ontario government-funded health care from 2004 to 2013. We observed a $4.9 Billion decrease in health care expenditure from improving healthy living over the ten-year study. For more information, see the report here.

Air Pollution for Life Expectancy Calculator

The effect of long-term exposure to air pollution and risk of dying was examined for over 2.5 million Canadian adults who completed the 1991 long-form census. People were followed for over 36 million person-years, with over 300 000 deaths observed. Residential postal codes of person for each year, during sixteen years of follow-up, allowed Dr. Crouse and his collaborators to estimate each person’s exposure to fine particulate matter (PM2.5), ozone (O3), and nitrogen dioxide (NO2). Annual average pollutant concentrations were derived from data from ground-based air pollution monitors, satellite measurements, and atmospheric models. For more information about the study see ehp.niehs.nih.gov.

Nursing Home Calculator

The nursing home calculator was developed using a statistical model to estimate the risk of death and hospital admission for 53,739 people newly admitted to long-term care facilities in Ontario. We measured adjusted rates of hospital admissions and mortality, per 1000 person-years (PY) of follow-up, among for-profit and not-for-profit facilities at 3, 6, and 12 months post-admission. Rates were measured post-admission and until discharge or death, whichever came first. For more information about the study see www.jamda.com.

Salt Calculator

Developing a Web-based dietary sodium screening tool for personalized assessment and feedback. For more information about the study see www.ncbi.nih.gov.

Hospital Use Calculator

900,000 Days in Hospital: The annual impact of smoking, alcohol, diet, and physical activity on hospital use in Ontario. The hospital use calculator is from this report. For more information see www.ices.ca.

For Researchers

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.

Cardiovascular Disease Population Risk Tool (CVDPoRT)

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

Algorithm viewer

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.

Reference data

Additional reference data includes:

  • CVDPoRT model in XML format (Predictive Modelling Markup Language);
  • 500 beta coefficients to calculate statistical uncertainty; and,
  • fictitious examples (n = 20 000) of exposure input and output, including intermediate calculation steps.

See the API/developer page for additional information.

References

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