A team from Duke University, Harvard University, and the University of Otago in New Zealand has published a paper in the latest issue of Nature Aging, revealing a new tool based on brain scan images that can not only determine whether a person is "accelerating aging" in middle age, but also predict their future risk of developing dementia, cardiovascular disease, lung disease, and even premature death. It is expected to become a new means of health risk warning and intervention. Scientists have been working hard to develop various "aging clocks" to more accurately measure the aging process. This time, the team utilized data from the Dunedin Study in New Zealand. This study tracked 1037 people born in Dunedin continuously from 1972 to 1973. Participants undergo health check ups every few years from birth, including evaluations of various indicators such as cardiovascular, metabolic, immune, cognitive, etc. On this basis, the team used brain MRI images collected by 860 participants at the age of 45 to train an artificial intelligence model called "DunedinPACNI" (Dunedin Image Age Model). This model only requires one brain scan image to estimate an individual's aging rate. To verify the universality of the model, the team applied it to 1737 brain image data from 42583 participants in the UK Biobank and the Alzheimer's Disease Neuroimaging Initiative (ADNI). The results showed that the model exhibited good predictive ability in different populations. According to Dunedin PACNI's standards, people who age faster perform worse on cognitive tests, and their hippocampus shrinks faster, making them more likely to develop dementia in the coming years and experience earlier symptoms of memory and cognitive decline. The study also found that "accelerated aging individuals" not only have significantly decreased brain function, but their overall health condition is also worse. Their probability of suffering from common elderly diseases such as heart disease, stroke, and chronic lung disease is significantly increased, with an 18% higher risk of being diagnosed with a chronic disease within a few years and an approximately 40% higher risk of death. The team stated that this tool still has some distance to go before it can be clinically applied. Further validation of the stability and accuracy of the model in different age groups, races, and device environments is needed in the future. (New Society)