This paper proposed new mathematical models for the estimation of fat free mass index directly from the bioelectrical impedance analysis to detect different types of diseases. To develop model, multivariate regression algorithm has been applied on the database of National Health and Nutrition Examination Survey (NHANES). In the database there are 2900 people’s data from which 1500 data have been used for the model development and validated over the remaining data. The correlation coefficients are 0.98 for both male and female model which is close to unity. The other elements of statistical analysis also show better performance of the proposed models comparing recent models and hence the new developed models can be a good alternative solution for the diseases detection scheme.
Keywords : Bioelectrical Impedance, Body Composition, DXA, Fat Free Mass Index, Multivariate Regression Analysis.