These models often compensate for competing risks of death—if you're curious, look up "Cox proportional hazard" to understand some of the math behind this.

Your meta point is a good one—I would like to see a model that predicts either your total lifespan, or probability of living to (say) 80 years of age heart attack-free. Perhaps I'll try to get access to the raw Framingham data and build a model to do that.

(For this particular page, I just bootstrapped from the existing medical research, which, while it has its limitations, has at least been thoroughly studied.)