The Brain Age Gap

The Trending With Impact series highlights Aging publications (listed by MEDLINE/PubMed as “Aging (Albany NY)” and “Aging-US” by Web of Science) that attract higher visibility among readers around the world online, in the news and on social media—beyond normal readership levels. Look for future science news about the latest trending publications here, and at Aging-US.com.

Listen to an audio version of this article

Aging is a risk factor for many diseases, including Alzheimer’s disease (AD). While scientists have made some progress in understanding the physiology of aging and its relationship to AD and related disorders, our understanding remains incomplete (to say the least). It is possible that civilization is currently in the midst of an artificial intelligence (AI) and machine learning (ML) “boom.” Researchers are now using AI and ML technologies to elevate our comprehension of aging and aging-related diseases.

“Artificial intelligence (AI) and machine learning (ML) technologies can help us better understand these diseases and aging itself by using biological data from the brain or other sources to create a mapping between age and biological data.”

In a new editorial paper, researchers Jeyeon Lee, Leland R. Barnard and David T. Jones from the Mayo Clinic in Rochester, Minnesota, discuss a recent study they conducted and explore the potential of AI to revolutionize the field of geriatrics. Their editorial was published in Aging’s Volume 15, Issue 8, on April 3, 2023, entitled, “Artificial intelligence and the aging mind.”

Their Study

In a recent 2022 study, Lee, Barnard, Jones, and the rest of their team developed convolutional neural network-based brain age prediction models using a large collection of data from brain magnetic resonance imaging (MRI) and brain fluorodeoxyglucose positron-emission tomography (FDG-PET) in people aged from 26 to 98 years old. In a sample of cognitively normal individuals, the AI models showed accurate brain age estimation of which a mean absolute error (MAE; unit, years) was 3.08±0.14 for the FDG-based model and 3.49±0.16 for the MRI-based model. 

The team found that higher brain age gaps (the difference between biological age and chronological age) were estimated in cohorts with neurodegenerative disorders—including mild cognitive impairment (MCI), AD, frontotemporal dementia (FTD), and dementia with Lewy bodies (DLB)—than normal controls. The brain age gap was strongly associated with pathologic tau protein levels and cognitive test scores. This gap also showed longitudinal predictive ability for cognitive decline in AD-related disorders.

“Interestingly, the brain imaging patterns generating brain age gaps in AD showed higher similarity with normal aging than other neurodegenerative syndromes implying that AD might be more like an accelerated representation of biological aging than others.”

Summary & Conclusions

The study conducted by Lee, Barnard, Jones, and their team using neural network-based brain age prediction models has shown promising results in accurately estimating brain age and identifying differences between normal aging and neurodegenerative disorders. However, the authors of this editorial note that variations in data make creating a uniform language used to compare and contrast large sums of data very difficult.

“Although more research and optimization are needed to determine its clinical usefulness, the study of brain age has great potential as a tool for understanding brain aging and age-related diseases.”

In conclusion, aging is a complex process that increases the risk of Alzheimer’s disease and various diseases. Recent advancements in artificial intelligence and machine learning technologies offer new opportunities to better understand the underlying mechanisms of aging and aging-related disorders. This research opens up exciting possibilities for the future of geriatric care and improving the lives of aging populations. As technology continues to advance, it is likely that we will gain further insights into aging through the brain age gap, ultimately leading to better prevention, diagnosis and treatment options.

“The fact that the brain age gap is a comprehensive and intuitive measure of disease severity using biological data that is already being acquired in clinical practice, makes it an attractive biomarker for further development for clinical use [8].”

Click here to read the full editorial paper published by Aging.

Aging is an open-access, peer-reviewed journal that has been publishing high-impact papers in all fields of aging research since 2009. These papers are available to readers (at no cost and free of subscription barriers) in bi-monthly issues at Aging-US.com.

Click here to subscribe to Aging publication updates.

For media inquiries, please contact [email protected].

Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *

  • Follow Us