A computer implemented method of generating a personalized health rating for a person uses one or more processors. The one or more processors execute instructions to perform the method including obtaining, by the one or more processors, measured data associated with the person, obtaining, by the one or more processors, a facial image of the person, extracting, by the one or more processors, emotional based features from the facial image, using a deep learning model trained on emotion labeled facial images to associate an emotional state with the extracted features to generate emotional data, and fusing, by the one or more processors, the measured data with the emotional data to generate the personalized health rating.
