Cognitive and MRI trajectories for prediction of Alzheimer’s disease

Abstract

The concept of Mild Cognitive Impairment (MCI) is used to describe the early stages of Alzheimer’s disease (AD), and identification and treatment before further decline is an important clinical task. We selected longitudinal data from the ADNI database to investigate how well normal function (HC, n= 134) vs. conversion to MCI (cMCI, n= 134) and stable MCI (sMCI, n=333) vs. conversion to AD (cAD, n= 333) could be predicted from cognitive tests, and whether the predictions improve by adding information from magnetic resonance imaging (MRI) examinations. Features representing trajectories of change in the selected cognitive and MRI measures were derived from mixed effects models and used to train ensemble machine learning models to classify the pairs of subgroups based on a subset of the data set. Evaluation in an independent test set showed that the predictions for HC vs. cMCI improved substantially when MRI features were added, with an increase in $$F_1$$ F 1 -score from 60 to 77%. The $$F_1$$ F 1 -scores for sMCI vs. cAD were 77% without and 78% with inclusion of MRI features. The results are in-line with findings showing that cognitive changes tend to manifest themselves several years after the Alzheimer’s disease is well-established in the brain.

Neuroscience from the comfort of your home: Repeated, self-administered wireless dry EEG measures brain function with high fidelity

“…In the context of drug clinical trials, recording across a week prior to a therapeutic intervention could establish a baseline of brain activity more robust to daily fluctuations (e.g., caused by lifestyle factors). Once identified, changes in baseline metrics over time could act as biomarkers for the detection and monitoring of neurodevelopmental, neuropsychiatric, or neurodegenerative disorders (74)(75)(76)(77). Brain changes associated with neurodegenerative disorders typically occur over years (64, 78), while neurodevelopmental disorders impact brain function across the lifespan (79,80).…”

At a Glance: An Update on Neuroimaging and Retinal Imaging in Alzheimer’s Disease and Related Research

“…The assessment of structural features using MRI also presents valuable opportunities for disease categorisation. For example, cognitive and MRI measures (alongside machine learning [ML] approaches [-covered in more detail below]), were used to aid the classification of participants with MCI, into AD subcategories (stable [sMCI] and converters to AD [cAD]) (17). The researchers successfully differentiated between sub-groups with the inclusion of MRI features, whereby additions to the models allowed for the measurement of changes in the entorhinal cortex and hippocampal volume.…”

The midpoint of cortical thinning between late childhood and early adulthood differs between individuals and brain regions: Evidence from longitudinal modelling in a 12-wave neuroimaging sample

“…The human cortex undergoes protracted microscopic and macroscopic structural changes between childhood and adulthood 1 . Individual differences in cortical structure have been associated with a range of phenotypic differences, including physical and mental health [2][3][4][5] , neurodevelopmental disorders as well as cognitive performance in childhood and adolescence 2,6 . Although other measures of brain structural development such as brain volume or white matter connectivity provide complementary insights into brain maturation, cortical thinning is one of the most widely used proxies of brain maturation [7][8][9] .…”