Considerations on brain age predictions from repeatedly sampled data across time

Abstract

AbstractIntroductionBrain age, the estimation of a person’s age from magnetic resonance imaging (MRI) parameters, has been used as a general indicator of health. The marker requires however further validation for application in clinical contexts. Here, we show how brain age predictions perform for for the same individual at various time points and validate our findings with age-matched healthy controls.MethodsWe used densly sampled T1-weighted MRI data from four individuals (from two datasets) to observe how brain age corresponds to age and is influenced by acquision and quality parameters. For validation, we used two cross-sectional datasets. Brain age was predicted by a pre-trained deep learning model.ResultsWe find small within-subject correlations between age and brain age. We also find evidence for the influence of field strength on brain age which replicated in the cross-sectional validation data, and inconclusive effects of scan quality.ConclusionThe absence of maturation effects for the age range in the presented sample, brain age model-bias (including training age distribution and field strength) and model error are potential reasons for small relationships between age and brain age in longitudinal data. Future brain age models should account for differences in field strength and intra-individual differences.