Brain-based graph-theoretical predictive modeling to map the trajectory of anhedonia, impulsivity, and hypomania from the human functional connectome

Abstract

Clinical assessments often fail to discriminate between unipolar and bipolar depression and identify individuals who will develop future (hypo)manic episodes. To address this challenge, we developed a brain-based graph-theoretical predictive model (GPM) to prospectively map symptoms of anhedonia, impulsivity, and (hypo)mania. Individuals seeking treatment for mood disorders (n = 80) underwent an fMRI scan, including (i) resting-state and (ii) a reinforcement-learning (RL) task. Symptoms were assessed at baseline as well as at 3- and 6-month follow-ups. A whole-brain functional connectome was computed for each fMRI task, and the GPM was applied for symptom prediction using cross-validation. Prediction performance was evaluated by comparing the GPM to a corresponding null model. In addition, the GPM was compared to the connectome-based predictive modeling (CPM). Cross-sectionally, the GPM predicted anhedonia from the global efficiency (a graph theory metric that quantifies information transfer across the connectome) during the RL task, and impulsivity from the centrality (a metric that captures the importance of a region) of the left anterior cingulate cortex during resting-state. At 6-month follow-up, the GPM predicted (hypo)manic symptoms from the local efficiency of the left nucleus accumbens during the RL task and anhedonia from the centrality of the left caudate during resting-state. Notably, the GPM outperformed the CPM, and GPM derived from individuals with unipolar disorders predicted anhedonia and impulsivity symptoms for individuals with bipolar disorders. Importantly, the generalizability of cross-sectional models was demonstrated in an external validation sample. Taken together, across DSM mood diagnoses, efficiency and centrality of the reward circuit predicted symptoms of anhedonia, impulsivity, and (hypo)mania, cross-sectionally and prospectively. The GPM is an innovative modeling approach that may ultimately inform clinical prediction at the individual level.

Fig. 1. Illustration of the brain-based graph-theoretical predictive modeling (GPM).

The GPM utilizes cross-validation and includes the following steps: (i) calculation of whole-brain functional connectomes for each individual; (ii) computation of graph-theoretical metrics from brain connectomes; (iii) feature selection: choosing the graph metric most strongly associated with the clinical symptom; (iv) model building: mapping between graph metric and clinical symptom; (v) model prediction: applying the model to previously unseen data. The model is built on the training set (steps i-iv) and prediction is done on the testing set (step v).

Fig. 2. Trajectories of anhedonia, impulsivity, and (hypo)mania symptoms.

The distributions (using violin plots), scatter plots, and boxplots of A anhedonia, B impulsivity, and C (hypo)mania symptoms are presented for baseline, 3-month (3M) and 6-month (6M) follow-ups. A demographically matched group of 32 healthy controls (HC) (age = 28.40 ± 7.72, 17 female) is included for comparison.

Fig. 3. The GPM predicted anhedonia and impulsivity at baseline.

Predicted clinical scores (y axis) are presented as a function of the observed clinical scores (x axis). For each symptom, the predictions of the GPM are presented on the left panel and the predictions of the corresponding null model (without the brain predictor) are presented on the right panel. A Anhedonia was predicted by the GPM from the global efficiency of the functional connectome during the reinforcement-learning task. B Impulsivity was predicted by the GPM from the centrality of the left anterior cingulate cortex during resting-state. All p values were computed using permutation testing. Prediction was done while controlling for other baseline symptoms and medication load.

Fig. 4. The GPM predicted (hypo)mania and anhedonia at 6-month follow-up.

Predicted clinical scores (y axis) are presented as a function of the observed clinical scores (x axis). A (Hypo)mania at 6-month (6M) follow-up was predicted by the GPM from the local efficiency of the left nucleus accumbens during the reinforcement-learning task. B Anhedonia at 6-month follow-up was predicted by the GPM from the centrality of the left caudate during resting-state. All p values were computed using permutation testing. Prediction was done while controlling for all baseline symptoms and medication load.