Normative modelling of molecular-based functional circuits captures clinical heterogeneity transdiagnostically in psychiatric patients

Abstract

Advanced methods such as REACT have allowed the integration of fMRI with the brain's receptor landscape, providing novel insights transcending the multiscale organisation of the brain. Similarly, normative modelling has allowed translational neuroscience to move beyond group-average differences and characterise deviations from health at an individual level. Here, we bring these methods together for the first time. We used REACT to create functional networks enriched with the main modulatory, inhibitory, and excitatory neurotransmitter systems and generated normative models of these networks to capture functional connectivity deviations in patients with schizophrenia, bipolar disorder (BPD), and ADHD. Substantial overlap was seen in symptomatology and deviations from normality across groups, but these could be mapped into a common space linking constellations of symptoms through to underlying neurobiology transdiagnostically. This work provides impetus for developing novel biomarkers that characterise molecular- and systems-level dysfunction at the individual level, facilitating the transition towards mechanistically targeted treatments.

Fig. 1. Analysis overview.

a The data utilised is from two existing datasets: CamCAN ageing and UCLA phenomics, the latter including healthy individuals as well as data from three clinical cohorts (Schizophrenia - SCHZ, bipolar disorder - BPD, and ADHD). b 28 different symptom scores available transdiagnostically were used to examine within- and between-group similarity in terms of symptomatology (I) as well as derive composite symptom sub-domains using PCA (ii). c REACT was used to generate molecular-enriched functional networks (i) which were subsequently parcellated using a custom combination of cortical, subcortical, and cerebellar ROIs (ii). d These ROI-based molecular-enriched networks were then used to create normative models trained on 70% of the HC subjects from both CamCAN and UCLA (i), then used to characterise deviations from normality within the remaining 30% of HC as well as the three clinical cohorts (ii). e Deviation scores within each brain region and averaged across brain regions as summary metrics were compared using ANOVAs (i); the averaged summary metrics were also examined for classification value using binary logistic regression (ii); within- and between-group FC deviation similarity was also evaluated (iii). f Finally, deviation scores were analysed transdiagnostically, examining how transdiagnostic similarity relates to the extent of deviation and composite symptom sub-domains identified in B (i). Regional deviations were also correlated with symptom sub-domains (ii).

Fig. 2. Symptom similarity.

a Between-subject similarity matrix for normalised psychometric measures. Each position in the matrix represents the correlation coefficient across all psychometric scores for a pair of individuals. Grey bars separate the conventional diagnostic criteria, delineating matrix regions of within- (diagonal) and between-group (off-diagonal) similarity. b Plots of average similarity of each patient to those with the same diagnosis (within-group) and those with the other two diagnoses (between-group) for each diagnostic group.

Fig. 3. Symptom dimensionality reduction.

a Cross-correlations between each pair of psychometric measures. b Component selection. Four components were retained which explained 57.3% of the variance in the original symptom scores. c The scores for each component across individuals within the three different clinical cohorts. d The loadings of the different symptom scores onto these four components are shown as bar plots.

Fig. 4. Between-group differences in deviation scores.

a Only two molecular-enriched networks had significant (p_FDR) between-group differences (A; anterior view, L; left view, R; right view, S; superior view). SMA; supplementary motor area, STG; superior temporal gyrus. b Lower-level t-tests showed which between-group comparisons were driving the higher-level results. t statistic colour bars correspond to the order of the sub-box titles such that when the left group has greater deviations these are blue and when the right group has greater deviations these are red/yellow (A; anterior view, L; left view, R; right view, S; superior view).

Fig. 5. Deviation similarity within and between groups.

a Matrices of between-subject correlations of deviation scores across ROIs for each pair of individuals within and between groups. b The correlation coefficients for within-group similarity are displayed as density plots. c The relationship between patients’ similarity to the other patients across all diagnostic groups and the overall deviation burden categorised by mean deviation score across their whole brain (top row) as well as each symptom component. Asterisks denote relationships that are significant following Bonferroni correction (p < 0.05/30).

Fig. 6. Mass univariate relationships between deviation and symptom scores.

a Only two of these deviation-symptom relationships were significant. Significant p_FDR values are shown for the relationships between PC2 and deviations within the VAChT- and mGluR5-enriched networks (A; anterior view, L; left view, R; right view, S; superior view). SMA; supplementary motor area, STG; superior temporal gyrus. b The same relationships are shown in the brain plots, with Z values averaged across the significant clusters and correlated with PC2 symptom scores. The loadings for PC2 are shown again here for context. Of note, whilst the diagnostic groups are reported in different colours within the scatter plots, this is purely for visualisation purposes and these analyses were run transdiagnostically across all patient groups.