Mortality Risk Algorithm

Name: Mortality Population Risk Tool (MPoRT)

Version: 1.0

Calulates risk of mortality (all-causes) from health behaviours and sociodemographic risks. Also used to calculate life expectancy and related outcomes (e.g. survival to age).

Algorithm Type

Survival Model, use SurvivalModelBuilder.

Algorithm Outcome

5-year risk of all-cause mortality.

Algorithm Predictors

Age, sex, four health behaviours (smoking, alcohol consumption, physical activity, and diet; three sociodemographic factors (ethnicity, immigration status, and education), four chronic conditions (self-report of physician-diagnosed diabetes, coronary heart disease, stroke, and cancer), and body mass index. Also included area-based measures: neighbourhood deprivation, local planning region, and rurality. See Table 1

Documentation

https://docs.projectbiglife.ca

References

Manuel DG, Perez R, Sanmartin C, Taljaard M, Hennessy D, et al Measuring Burden of Unhealthy Behaviours Using a Multivariable Predictive Approach: Life Expectancy Lost in Canada Attributable to Smoking, Alcohol, Physical Inactivity, and Diet. PLoS Medicine 2016 13(8):e1002082. https://doi.org/10.1371/journal.pmed.1002082

Additional supporting documents (PMML, Lime, testing data, etc.)

https://github.com/Big-Life-Lab/predictive-algorithms/tree/master/MPoRT