Computational limits to the legibility of the imaged human brain

• Published in: NeuroImage (Orlando, Fla.) Vol. 291; p. 120600
• Main Authors: Ruffle, James K., Gray, Robert J, Mohinta, Samia, Pombo, Guilherme, Kaul, Chaitanya, Hyare, Harpreet, Rees, Geraint, Nachev, Parashkev
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01-05-2024; Elsevier Limited; Elsevier
• Subjects: Artificial intelligence; Biobanks; Brain - diagnostic imaging; Brain function; Brain structure; Child, Preschool; Chronic Disease; Chronic illnesses; Computational neuroscience; Deep learning; Emotions; Functional connectivity; Hemoglobin; High performance computing; Humans; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Neural networks; Neural Networks, Computer; Neuroimaging; Neuroimaging - methods; Prediction models; Serology; Structure-function relationships; Variables; United Kingdom > UK; Neuroimaging; Functional connectivity; CNN; MRI; FNN; Brain function; Brain structure; Deep learning; MAE; HDL; rsfMRI; Magnetic resonance imaging; High performance computing; FDR; LDL; Machine learning; DWI; FLAIR; Hb; Artificial intelligence; HbA1c
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2024.120600

•Individuals remain poorly predictable from population-level analyses of the brain.•The fidelity limits data scale, compute, and model flexibility impose are unknown.•We quantify these limits in multimodal, multitarget analyses across 23810 people.•We show a radical change in modelling regimes is needed for individual prediction.
Our knowledge of the organisation of the human brain at the population-level is yet to translate into power to predict functional differences at the individual-level, limiting clinical applications and casting doubt on the generalisability of inferred mechanisms. It remains unknown whether the difficulty arises from the absence of individuating biological patterns within the brain, or from limited power to access them with the models and compute at our disposal.
Here we comprehensively investigate the resolvability of such patterns with data and compute at unprecedented scale. Across 23 810 unique participants from UK Biobank, we systematically evaluate the predictability of 25 individual biological characteristics, from all available combinations of structural and functional neuroimaging data. Over 4526 GPU*hours of computation, we train, optimize, and evaluate out-of-sample 700 individual predictive models, including fully-connected feed-forward neural networks of demographic, psychological, serological, chronic disease, and functional connectivity characteristics, and both uni- and multi-modal 3D convolutional neural network models of macro- and micro-structural brain imaging.
We find a marked discrepancy between the high predictability of sex (balanced accuracy 99.7%), age (mean absolute error 2.048 years, R2 0.859), and weight (mean absolute error 2.609Kg, R2 0.625), for which we set new state-of-the-art performance, and the surprisingly low predictability of other characteristics. Neither structural nor functional imaging predicted an individual's psychology better than the coincidence of common chronic disease (p < 0.05). Serology predicted chronic disease (p < 0.05) and was best predicted by it (p < 0.001), followed by structural neuroimaging (p < 0.05).
Our findings suggest either more informative imaging or more powerful models will be needed to decipher individual level characteristics from the human brain. We make our models and code openly available.