New AI model uncovers how and why the human brain ages
As we age, our brains undergo structural and cellular changes influenced by intrinsic and external factors. Accelerated aging in the brain can result in an increased risk of neurodegenerative conditions, bipolar disorder, and mortality. In a bid to deeply understand how an aging brain works, researchers say they have built a powerful AI tool that can identify regions in the brain vulnerable to age-related changes.
The team used AI to develop an algorithm called ‘HistoAge,’ which predicts age at death based on the cellular composition of human brain tissue specimens with an average accuracy of 5.45 years (± 0.22 years). The team used digitized human hippocampal (part of the brain) sections of 689 deceased people to develop a brain age estimation model.
Mapping what makes brain age faster
The hippocampus is known to be involved in both brain aging and age-dependent neurodegenerative diseases and, thus, is an ideal region for this analysis.
The team trained the AI model on the digitized section of the brain to estimate the age of deaths. They used the difference between the model-predicted age and actual age to derive the amount of age acceleration in the brain, said the press release.
“Our data suggest that HistoAge may offer a holistic quantitative metric of pathologic brain aging, which has the potential to advance our understanding of the underlying mechanisms of brain aging and the development of age-related disorders,” wrote the researchers.
The team demonstrated that their model can effectively utilize features of aging to make estimations about risk factors for pathologic aging and protective factors that contribute to successful aging. The model also uncovers novel anatomical regions in the brain which are vulnerable to age-related changes.
AI in diagnostics
Previous approaches, such as an MRI scan, to study brain aging and neurodegenerative diseases have been limited in their ability to comprehensively quantify pathological brain aging at the histologic level, explain the researchers in the study. Authors note that while MRI can only capture macroscopic changes occurring at the level of cell populations, their technique provides an ability to assess cellular features not captured by conventional neuroimaging.
“Our novel HistoAge model is just one example of the way AI is paving the way for further discovery about the mechanisms of aging and neurodegeneration,” said Dr. Kurt Farrell, co-author of the study. “Clinical scientists are increasingly using AI in research and diagnostic settings. It’s a tool that is revolutionizing medicine and we are excited to be leaders in this space, optimizing machine learning—not to replace our Health System’s commitment to compassionate care, but to improve diagnosis and treatment for all patients.”
Source: Interesting Engineering
Scientists find 10 ‘markers’ in blood that predict people’s chances of reaching 100
New AI model uncovers how and why the human brain ages