Abstract:

The global rise in life expectancy has resulted in an increasing prevalence of age-related health conditions, with cognitive decline being one of the most critical concerns affecting older adults. Dietary habits and overall nutritional status have been identified as key modifiable factors that influence brain structure, function, and the rate of cognitive deterioration. Advances in data analytics, machine learning, and multi-omics technologies have enabled a more comprehensive evaluation of the complex relationships between diet, metabolism, genetic variation, and cognitive outcomes. This review synthesizes current knowledge on data-driven investigations into the association between dietary intake and cognitive decline in aging populations. An evidence from population-based cohort studies, dietary pattern modeling, metabolomic profiling, and artificial intelligence applications that aim to predict or monitor cognitive performance over time. The review also discusses the methodological and ethical challenges associated with the use of large-scale health and nutrition datasets, including issues of data quality, representativeness, and privacy. The integration of heterogeneous data sources through computational and statistical frameworks is expected to improve understanding of the mechanisms linking nutrition to brain aging and to facilitate the development of personalized dietary strategies for maintaining cognitive health in later life.