Employing Connectome-Based Models to Predict Working Memory in Multiple Sclerosis

Connectome‐based predictive modelling of cognitive reserve using task‐based functional connectivity

“…Critically, the network strength predicted CR measures did not generalize to resting-state data in an independent dataset. Other studies applying CPM to cognitive phenotypes have had similar results, where the phenotype could be accurately predicted within-sample (i.e., in the training set), but not when applied to independent test sets (Gbadeyan et al, 2022;Manglani et al, 2022). We undertook exploratory analyses that suggested the failure to develop generalizable and theoretically valid measures of CR was not due to differences in the age ranges of the datasets, overfitting the training set due to a strict edge selection threshold, nor due to the use of the CR residual as a target variable.…”

Predicting response time variability from task and resting-state functional connectivity in the aging brain

“…Using whole brain, task-based, or resting state functional connectivity, several recent studies have demonstrated the utility of the CPM technique in identifying individual differences in brain functional architecture. These have allowed for the construction of brain-based models capable of predicting fluid intelligence ( Finn et al, 2015 ), processing speed ( Gao et al, 2020 ), attention ( Rosenberg et al, 2016 ), reading ability ( Jangraw et al, 2018 ), working memory ( Avery et al, 2020 ; Manglani et al, 2021 ), loneliness ( Feng et al, 2019 ), mind-wandering ( Kucyi et al, 2021 ), or even diseased states such as Alzheimer’s disease ( Lin et al, 2018 ) and attention deficit hyperactivity disorder (ADHD; Barron et al, 2020 ). A recent fMRI study demonstrated the utility of CPM to build generalizable models of mind-wandering, as measured using an experience sampling method, in healthy young adults and adults with ADHD ( Kucyi et al, 2021 ).…”

Connectome-based predictive modeling of cognitive reserve using task-based functional connectivity

“…Other studies applying CPM to cognitive phenotypes have had similar results, where the phenotype could be accurately predicted within-sample (i.e. in the training set), but not when applied to independent test sets (Gbadeyan et al, 2022;Manglani et al, 2021). We undertook exploratory analyses that suggested the failure to develop generalizable and theoretically valid measures of CR was not due to differences in the age ranges of the datasets, overfitting the training set due to a strict edge selection threshold, nor due to the use of the CR residual as a target variable.…”