TY - JOUR
T1 - Deep biomarkers of human aging
T2 - Application of deep neural networks to biomarker development
AU - Putin, Evgeny
AU - Mamoshina, Polina
AU - Aliper, Alexander
AU - Korzinkin, Mikhail
AU - Moskalev, Alexey
AU - Kolosov, Alexey
AU - Ostrovskiy, Alexander
AU - Cantor, Charles
AU - Vijg, Jan
AU - Zhavoronkov, Alex
N1 - Publisher Copyright:
© Putin et al.
PY - 2016
Y1 - 2016
N2 - One of the major impediments in human aging research is the absence of a comprehensive and actionable set of biomarkers that may be targeted and measured to track the effectiveness of therapeutic interventions. In this study, we designed a modular ensemble of 21 deep neural networks (DNNs) of varying depth, structure and optimization to predict human chronological age using a basic blood test. To train the DNNs, we used over 60,000 samples from common blood biochemistry and cell count tests from routine health exams performed by a single laboratory and linked to chronological age and sex. The best performing DNN in the ensemble demonstrated 81.5 % epsilon-accuracy r = 0.90 with R2 = 0.80 and MAE = 6.07 years in predicting chronological age within a 10 year frame, while the entire ensemble achieved 83.5% epsilon-accuracy r = 0.91 with R2 = 0.82 and MAE = 5.55 years. The ensemble also identified the 5 most important markers for predicting human chronological age: albumin, glucose, alkaline phosphatase, urea and erythrocytes. To allow for public testing and evaluate real-life performance of the predictor, we developed an online system available at http://www.aging.ai. The ensemble approach may facilitate integration of multi-modal data linked to chronological age and sex that may lead to simple, minimally invasive, and affordable methods of tracking integrated biomarkers of aging in humans and performing cross-species feature importance analysis.
AB - One of the major impediments in human aging research is the absence of a comprehensive and actionable set of biomarkers that may be targeted and measured to track the effectiveness of therapeutic interventions. In this study, we designed a modular ensemble of 21 deep neural networks (DNNs) of varying depth, structure and optimization to predict human chronological age using a basic blood test. To train the DNNs, we used over 60,000 samples from common blood biochemistry and cell count tests from routine health exams performed by a single laboratory and linked to chronological age and sex. The best performing DNN in the ensemble demonstrated 81.5 % epsilon-accuracy r = 0.90 with R2 = 0.80 and MAE = 6.07 years in predicting chronological age within a 10 year frame, while the entire ensemble achieved 83.5% epsilon-accuracy r = 0.91 with R2 = 0.82 and MAE = 5.55 years. The ensemble also identified the 5 most important markers for predicting human chronological age: albumin, glucose, alkaline phosphatase, urea and erythrocytes. To allow for public testing and evaluate real-life performance of the predictor, we developed an online system available at http://www.aging.ai. The ensemble approach may facilitate integration of multi-modal data linked to chronological age and sex that may lead to simple, minimally invasive, and affordable methods of tracking integrated biomarkers of aging in humans and performing cross-species feature importance analysis.
KW - Aging biomarkers
KW - Biomarker development
KW - Deep learning
KW - Deep neural networks
KW - Human aging
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=84976407069&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84976407069&partnerID=8YFLogxK
U2 - 10.18632/aging.100968
DO - 10.18632/aging.100968
M3 - Article
C2 - 27191382
AN - SCOPUS:84976407069
SN - 1945-4589
VL - 8
SP - 1021
EP - 1033
JO - Aging
JF - Aging
IS - 5
ER -