This is an interactive graph that shows how closely 643 measurements (variables) collected in UK Biobank are associated with different causes of death and how accurately a variable can predict the risk of death within five years in women.
* The higher the C-index, the more accurate the variable is at predicting death within five years. For example, 'Usual walking pace' is a more accurate predictor of five-year mortality (C-index = 0.69), than 'Number of days per week of moderate physical activity' (C-index = 0.65). Read more.
The variables with the least predictive ability do not increase the C-index beyond what is predicted by age alone [the baseline in the graph (C-index=0.65)], while those with the most predictive ability increase C-index several percentage points.
** The higher the R2 value, the more strongly associated the variable is with age. For example, 'Weekly usage of mobile phone in last 3 months' is more strongly associated with age (R2 = 0.09), than 'Salt added to food' (R2 = 0.0009). Read more.
Expand all categories Collapse all categories