Deep Biomarkers Of Human Aging


How old by basic blood test

Aging.AI 2.0

  • 33 input parameters
  • r = 0.79
  • Rsq = 0.63
  • MAE = 6.2 years
Test your samples

Aging.AI 1.0

  • 41 input parameters
  • r = 0.91
  • Rsq = 0.82
  • MAE = 5.5 years
Test your samples


This is a deep-learned predictor of your age made with a deep neural network trained on hundreds of thousands anonymized human blood tests. Enter your data below and Aging.ai will guess your age and gender




First choose the sample metric: 

Enter your weight: kg       Enter your height: cm       Do you smoke?  
Blood Marker* Your Value Units and Sample Metric***
Albumin** 35 - 52 g/l
Glucose** 3.9 - 5.8 mmole/l
Urea**(BUN) 2.5 - 6.4 mmole/l
ALT** < 41 U/l
Cholesterol** 3.37 - 5.96 mmole/l
Protein total** 64 - 83 g/l
Globulins** 14 - 49 g/l
Alkaline phosphatase** 20 - 120 U/l
Sodium** 136 - 146 mmole/l
Lactate dehydrogenase** < 248 U/l
Creatinine** 53 - 97 mmole/l
Hemoglobin** 11.7 - 15.5 g/dl
Bilirubin total 1.7 - 21 mcmole/l
Triglycerides 0.68 - 6 mmole/l
HDL Cholesterol < 3.3 mmole/l
LDL cholesterol (by Friedewald) 1.81- 4.04 mmole/l
Calcium 2.15 - 2.65 mmole/l
Chloride 101 - 110 mmole/l
Potassium 3.4 - 5.1 mmole/l
Iron 7.20 - 25.90 mcmole/l
Hematocrit 37 - 50 %
MCH 27 - 31 pg/cell
MCHC 31.5 - 35.7 g/dL
MCV 82 - 95 fl
Platelets 150 - 450 103 /mcl
Erythrocytes (RBC) 3.5 - 5.5 106 /mcl
Leukocytes (WBC) 4 - 10 103 /mcl
AST < 47 U/l
Basophils < 1.0 %
Eosinophils < 5.0 %
Lymphocytes 20 - 40 %
Monocytes 3 - 9 %
Neutrophils 45 - 70 %
Show Additional Markers
(improves accuracy by ~10%)
* This should be in your clinical biochemistry blood test results
** Required parameter for minimal prediction accuracy of 70% within 10 year frame
*** We can not show you reference values before knowing your age apriori, so this is only a reference metric

Click on a marker to know more about what it is. Knowing your blood biochemistry markers is the new ABCs. Everyone should know it.

Our team is expert in human gene expression data analysis, biomarker development and drug discovery for aging research, so this predictor is a small by-product of our work. But if we see that people like it, we will develop a biomarker, where you will be able to log in and track the changes in predicted age while testing some of the interventions like diet, exercise or supplements to see if any of these “make you younger”. If you decide to use this system, all data submitted will be used for research purposes and will be used to help train the predictor, so it will not be possible for us to delete it. Please do not submit anything if you don’t want your data to be used freely


In collaboration with:
DNNs were trained on NVIDIA GPU


We thank NVIDIA for providing valuable GPU equipment for deep learning to Insilico Medicine.