Computerized system and method for estimating levels of obesity in an insured population

A computerized system for estimating obesity in an insured population, comprising:

• (a) memory at a computer for storing for a member of said insured population member health data exclusive of height and weight data and for said member a feature vector comprising:
• (1) an age;
• (2) a gender;
• (3) claim data for each of a plurality of obesity factors;
• (4) a total number of claims in each of said plurality of obesity factors;
• (5) a total number of claims for all of said obesity factors;
• (6) a co-morbidity score;
• (7) a plurality of chronic condition metrics;
• and
• (8) a plurality of census metrics;
• (b) an executable process at said computer configured to:
• (1) present said feature vector in parallel to a trained obesity inference model wherein said model is trained according to:
• (A) a body mass index for each member of a subset of said insured population for which height and weight data is available, said body mass index calculated from said height and weight data for each member of said subset;
• (B) feature vector data for each member of said subset of said insured population;
• (2) receive for output at said computer from said obesity inference model an estimated body mass index for said member of said insured population.

A computerized method for estimating obesity in an insured population comprising:

• (a) identifying in a computer a plurality of obesity factor areas for said insured population;
• (b) creating in said computer a feature vector comprising for each member of said insured population:
• (1) demographic data;
• (2) claim data for each of said plurality of obesity factor areas;
• and
• (3) a plurality of census metrics;
• (c) presenting said feature vector in parallel to modules in said computer comprising:
• (1) a support vector machine that divides said feature vector data into classes and generates a first output of a distance from classification boundaries for said classes;
• (2) a rule-based engine that generates a second output of a probability of obesity based on said feature vector data;
• (3) a generalized linear model that generates a third output of a continuous estimate of body mass index;
• (d) appending in said computer to said feature vector said first output from said support vector machine, said second output from said rule-based engine, and said third output from said generalized linear model;
• (e) presenting at said computer said feature vector to a plurality of regression neural networks;
• and
• (f) receiving for output at said computer from said regression neural networks an estimated body mass index for said insured population.