In disease, however, the brain‐ageing pattern may deviate from the chronological ageing trajectory. Previous studies have reported very high correlations between brain age predictions and chronological age in healthy people (e.g., r > .9, Franke, Ziegler, Klöppel, & Gaser, 2010). Recently, there has been great interest in measuring the ageing process of the brain through brain age prediction using machine learning methods, most commonly based on structural magnetic resonance imaging (MRI). It, therefore, is of critical importance to detect age‐related health issues in their early stages to prevent or slow down further deterioration.
On a societal level, the ageing population is linked to greater socioeconomic costs (United Nations, Department of Economic and Social Affairs, 2019) on an individual level, ageing is associated with a progressive decline in physical and cognitive abilities (Fjell & Walhovd, 2010). The world population is ageing rapidly, with one in four people in Europe and North America and one in six people globally predicted to be aged over 65 by 2050 (United Nations, Department of Economic and Social Affairs, 2019).
#Sandra model set 113 code
All code is provided online in the hope that this will aid future research. Overall, we observed little difference in performance between models trained on the same data type, indicating that the type of input data had greater impact on performance than model choice.
The models achieved mean absolute errors between 3.7 and 4.7 years, with those trained on voxel‐level data with principal component analysis performing best. Performance was assessed in the validation set through cross‐validation as well as an independent test set.
Therefore, we used the UK Biobank data set ( N = 10,824, age range 47–73) to compare the performance of the machine learning models support vector regression, relevance vector regression and Gaussian process regression on whole‐brain region‐based or voxel‐based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis. Existing studies on such “brain age prediction” vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach is unclear. Brain morphology varies across the ageing trajectory and the prediction of a person's age using brain features can aid the detection of abnormalities in the ageing process.
0 kommentar(er)
