Research Paper Volume 8, Issue 5 pp 1021—1030
Deep biomarkers of human aging: Application of deep neural networks to biomarker development
Figure 1. Project pipeline. Laboratory blood biochemistry data sets were normalized and cleaned of outliers and some abnormal markers. For biological age prediction, 21 different DNNs with different parameters were combined in ensemble based on ElasticNet model. For biological sex prediction, single DNN were trained.