Risk score-embedded deep learning for biological age estimation: Development and validation

The health index measures a person’s overall status which provides useful information for people to manage their health, so developing precise and relevant is urgent. Currently, many researchers have studied the biological age (BA) estimation, one of beneficial indices, by applying machine learning deep techniques data. However, most them focused on chronological prediction or basic latent feature extraction methods. In this paper, we present new algorithm estimate BA, called Risk Score-Embedded Autoencoder-based BA (RSAE-BA). RSAE-BA can provide an accurate using representation with individual’s risk. We first proposed notion risk score (RS) calculation monitor Then extracted features autoencoder embedding RS, used generate BA. To evaluate RSAE-BA, presented validation method applicable both unlabeled labeled compared results existing methods, demonstrated accuracy its applicability predict disease incidence. believe that will be alternative measure health.