Title |
Deep biomarkers of human aging: Application of deep neural networks to biomarker development
|
---|---|
Published in |
Aging, May 2016
|
DOI | 10.18632/aging.100968 |
Pubmed ID | |
Authors |
Evgeny Putin, Polina Mamoshina, Alexander Aliper, Mikhail Korzinkin, Alexey Moskalev, Alexey Kolosov, Alexander Ostrovskiy, Charles Cantor, Jan Vijg, Alex Zhavoronkov |
Abstract |
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 R(2) = 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 R(2) = 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. |
Twitter Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 6 | 12% |
Australia | 3 | 6% |
Hong Kong | 2 | 4% |
Russia | 2 | 4% |
Namibia | 1 | 2% |
France | 1 | 2% |
Switzerland | 1 | 2% |
Spain | 1 | 2% |
Austria | 1 | 2% |
Other | 0 | 0% |
Unknown | 31 | 63% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 43 | 88% |
Scientists | 3 | 6% |
Science communicators (journalists, bloggers, editors) | 2 | 4% |
Practitioners (doctors, other healthcare professionals) | 1 | 2% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Russia | 2 | <1% |
Brazil | 1 | <1% |
Canada | 1 | <1% |
United Kingdom | 1 | <1% |
Japan | 1 | <1% |
United States | 1 | <1% |
Unknown | 360 | 98% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 71 | 19% |
Student > Ph. D. Student | 69 | 19% |
Student > Master | 45 | 12% |
Student > Bachelor | 31 | 8% |
Other | 29 | 8% |
Other | 69 | 19% |
Unknown | 53 | 14% |
Readers by discipline | Count | As % |
---|---|---|
Biochemistry, Genetics and Molecular Biology | 71 | 19% |
Agricultural and Biological Sciences | 49 | 13% |
Computer Science | 45 | 12% |
Medicine and Dentistry | 30 | 8% |
Engineering | 21 | 6% |
Other | 80 | 22% |
Unknown | 71 | 19% |