On the prediction of human intelligence from neuroimaging: A systematic review of methods and reporting

Abstract

Human intelligence is one of the main objects of study in cognitive neuroscience. Reviews and meta-analyses have proved to be fundamental to establish and cement neuroscientific theories on intelligence. The prediction of intelligence using in vivo neuroimaging data and machine learning has become a widely accepted and replicated result. Here, we present a systematic review of this growing area of research, based on studies that employ structural, functional, and/or diffusion MRI to predict human intelligence in cognitively normal subjects using machine-learning. We performed a systematic assessment of methodological and reporting quality, using the PROBAST and TRIPOD assessment forms and 30 studies identified through a systematic search. We observed that fMRI is the most employed modality, resting-state functional connectivity (RSFC) is the most studied predictor, and the Human Connectome Project is the most employed dataset. A meta-analysis revealed a significant difference between the performance obtained in the prediction of general and fluid intelligence from fMRI data, confirming that the quality of measurement moderates this association. The expected performance of studies predicting general intelligence from fMRI was estimated to be r = 0.42 (CI95% = [0.35, 0.50]) while for studies predicting fluid intelligence obtained from a single test, expected performance was estimated as r = 0.15 (CI95% = [0.13, 0.17]). We further enumerate some virtues and pitfalls we identified in the methods for the assessment of intelligence and machine learning. The lack of treatment of confounder variables, including kinship, and small sample sizes were two common occurrences in the literature which increased risk of bias. Reporting quality was fair across studies, although reporting of results and discussion could be vastly improved. We conclude that the current literature on the prediction of intelligence from neuroimaging data is reaching maturity. Performance has been reliably demonstrated, although extending findings to new populations is imperative. Current results could be used by future works to foment new theories on the biological basis of intelligence differences.

Intermediately Synchronised Brain States optimise trade-off between Subject Identifiability and Predictive Capacity

“…Moreover, there may be other machine learning models not applied here, which perform better on FC estimates obtained during HACF frames than on FC estimates obtained during intermediate or LACF bins. However, in order to minimise this risk, we applied CBPM 4,9 and kernel ridge regression, two models which are commonly used for FC-based prediction, and have been consistently found to yield competitive results in the prediction of cognitive and demographic variables 4,12,19,39,57 . Both models show results consistent with our conclusions here.…”

“…However, in order to minimise this risk, we applied CBPM 4,9 and kernel ridge regression, two models which are commonly used for FC-based prediction, and have been consistently found to yield competitive results in the prediction of cognitive and demographic variables 4,12,19,39,57 . Both models show results consistent with our conclusions here.…”

“…S12-S21). For this analysis we chose "Reading" and "Vocabulary", because they yielded best prediction accuracy scores as well as "Fluid Intelligence", because it is widely used for prediction in the literature 4,39 .…”

ANTsX neuroimaging-derived structural phenotypes of UK Biobank

“…Similarly, the association between brain structure and fluid intelligence has been well-studied [Vieira et al, 2022] despite potentially problematic philosophical and ethical issues [Eickhoff and Langner, 2019]. With intentions of furthering this research, the ABCD Neurocognitive Prediction Challenge (ABCD-NP-Challenge) was held in 2019 which concerned predicting fluid intelligence scores (using the NIH Toolbox Cognition Battery [Weintraub et al, 2013]) in a population of 9-10 year pediatric subjects using T1-weighted MRI.…”

The (Limited?) Utility of Brain Age as a Biomarker for Capturing Fluid Cognition in Older Individuals

“…Third and finally, can we further improve our ability to capture the decline in cognition fluid by using, not only Brain Age and chronological age, but also another biomarker, Brain Cognition? Analogous to Brain Age, Brain Cognition is defined as a predicted value from machine-learning models that predict cognition fluid based on a person’s brain data (Dubois et al, 2018; Pat, Wang, Anney, et al, 2022; Rasero et al, 2021; Sripada et al, 2020; Tetereva et al, 2022; for review, see Vieira et al, 2022). Age-related cognitive decline is not only related to the changes in age, but also to the changes in cognition.…”