| abstract |
A computer-implemented method for personalized assessment of a subject's bone health includes extracting multiple features of interest from non-invasive subject data, subject medical images, and sample-specific bone turnover marker values. A replacement model and the multiple features of interest are used to predict one or more subject-specific measures of interest with respect to bone health. Then, visualization of the one or more subject-specific measures of interest with respect to bone health is generated. |