Norwegian version of this page

What is your brain age?

PhD candidate Dani Beck

Picture of Dani Beck

Dani Beck. Photo: Kirsten Sjøwall

I have recently noticed a lot of “train your brain” apps that make claims to reveal your “brain age” after a few simple mental tasks. While these apps may be beneficial as cognitive training exercises, none of them can actually estimate the age of your brain. But here’s the good news, I can! – well, sort of. Using a machine learning algorithm and a magnetic resonance imaging (MRI) scan of your brain, research has provided us with a technique that can estimate how old our brains are [1].

How it works

First, we provide our “machine” with a training set made up of MRI scans of the brain from (preferably) thousands of individuals. Here, we also feed the machine the biological age (based on date of birth) of each of these individuals. This process helps the algorithm learn what a brain should look like throughout the human lifespan. Once this training is complete, we can feed the machine your brain. Or at least the MRI scan of it. However, and very importantly, this time we do not tell it what age you are. Finally, the machine learning algorithm will estimate your brain age.

Visual presentation of brain age estimation
Figure 1. A visual presentation of brain age prediction (illustration: Dani Beck).

Brain age gap

As you can see from the illustration above, the brain age estimations can sometimes be different to our biological age. This is known as the brain age gap (BAG). The BAG is measured by calculating the difference between our biological age and our predicted brain age. Using this approach, researchers have learned a lot about normal trajectories of human brain ageing.

Researchers have also been able to compare this to groups that may experience deviation from normal brain ageing trajectories. For example, a recent study [2] found that the brains of people who suffer from a variety of brain disorders look older than the brains of healthy people of the same age, with the biggest brain age gaps being found for schizophrenia, multiple sclerosis and dementia. On the other side of the spectrum, recent findings [3] have revealed that women with a history of previous childbirths have younger looking brains than those without.

My work

My current research also utilize brain age prediction. As part of my PhD project, I work predominantly with cardiovascular risk factors and study their impact on the human brain. Cardiovascular risk factors, including smoking, hypertension, diabetes, obesity (and more) are associated with increased risk of a range of brain disorders, in addition to ageing-related cognitive decline[4]. Moreover, associations between high insulin and obesity in childhood and risk for psychosis and depression at 24 years of age, indicate that cardiometabolic risk factors in childhood represent relevant predictors for mental disorders later in life [5]. Based on these and related findings, my prediction is that those with high (negative) scores relating to cardiovascular risk factors will have brains that appear older in brain age prediction compared to their biological age.

Understanding this so called heart-brain axis between the cardiovascular system and the brain is important for identifying sensitive age periods where therapeutic and preventive interventions for reducing cardiovascular risk diseases may be most efficient. Moreover, maintaining the structure of the brain in a younger state may have profound effects on delaying the onset of age-related neurodegenerative diseases [4].

References

  1. Cole, J. H., & Franke, K. (2017). Predicting age using neuroimaging: innovative brain ageing biomarkers. Trends in neurosciences, 40(12), 681-690.
  2. Kaufmann, T., van der Meer, D., Doan, N. T., Schwarz, E., Lund, M. J., Agartz, I., ... & Bettella, F. (2019). Common brain disorders are associated with heritable patterns of apparent aging of the brain. Nature neuroscience, 22(10), 1617-1623.
  3. de Lange, A. M. G., Kaufmann, T., van der Meer, D., Maglanoc, L. A., Alnæs, D., Moberget, T., ... & Westlye, L. T. (2019). Population-based neuroimaging reveals traces of childbirth in the maternal brain. Proceedings of the National Academy of Sciences, 116(44), 22341-22346.
  4. Qiu, C., & Fratiglioni, L. (2015). A major role for cardiovascular burden in age-related cognitive decline. Nature Reviews Cardiology, 12(5), 267.
  5. Perry, B. I., Stochl, J., Upthegrove, R., Zammit, S., Wareham, N., Langenberg, C., Winpenny, E., Dunger, D., Jones, P. B., & Khandaker, G. M. (2021). Longitudinal Trends in Childhood Insulin Levels and Body Mass Index and Associations With Risks of Psychosis and Depression in Young AdultsJAMA Psychiatry, 2020.  

Contact

 

Published Jan. 29, 2021 9:28 AM - Last modified Oct. 10, 2022 9:41 AM