Investigating data-driven biological subtypes of psychiatric disorders using specification-curve analysis

The Transition From Homogeneous to Heterogeneous Machine Learning in Neuropsychiatric Research

Despite the advantage of neuroimaging-based machine learning (ML) models as pivotal tools for investigating brain-behavior relationships in neuropsychiatric studies, these data-driven predictive approaches have yet to yield substantial, clinically actionable insights for mental health care. A notable impediment lies in the inadequate accommodation of most ML research to the natural heterogeneity within large samples. Although commonly thought of as individual-level analyses, many ML algorithms are unimodal and homogeneous and thus incapable of capturing the potentially heterogeneous relationships between biology and psychopathology. We review the current landscape of computational research targeting population heterogeneity and argue that there is a need to expand from brain subtyping and behavioral phenotyping to analyses that focus on heterogeneity at the relational level. To this end, we review and suggest several existing ML models with the capacity to discern how external environmental and sociodemographic factors moderate the brain-behavior mapping function in a data-driven fashion. These heterogeneous ML models hold promise for enhancing the discovery of individualized brain-behavior associations and advancing precision psychiatry.

Dissection of depression heterogeneity using proteomic clusters

BACKGROUND

The search for relevant biomarkers of major depressive disorder (MDD) is challenged by heterogeneity; biological alterations may vary in patients expressing different symptom profiles. Moreover, most research considers a limited number of biomarkers, which may not be adequate for tagging complex network-level mechanisms. Here we studied clusters of proteins and examined their relation with MDD and individual depressive symptoms.

METHODS

The sample consisted of 1621 subjects from the Netherlands Study of Depression and Anxiety (NESDA). MDD diagnoses were based on DSM-IV criteria and the Inventory of Depressive Symptomatology questionnaire measured endorsement of 30 symptoms. Serum protein levels were detected using a multi-analyte platform (171 analytes, immunoassay, Myriad RBM DiscoveryMAP 250+). Proteomic clusters were computed using weighted correlation network analysis (WGCNA).

RESULTS

Six proteomic clusters were identified, of which one was nominally significantly associated with current MDD (p = 9.62E-03, Bonferroni adj. p = 0.057). This cluster contained 21 analytes and was enriched with pathways involved in inflammation and metabolism [including C-reactive protein (CRP), leptin and insulin]. At the individual symptom level, this proteomic cluster was associated with ten symptoms, among which were five atypical, energy-related symptoms. After correcting for several health and lifestyle covariates, hypersomnia, increased appetite, panic and weight gain remained significantly associated with the cluster.

CONCLUSIONS

Our findings support the idea that alterations in a network of proteins involved in inflammatory and metabolic processes are present in MDD, but these alterations map predominantly to clinical symptoms reflecting an imbalance between energy intake and expenditure.

Transdiagnostic connectome signatures from resting-state fMRI predict individual-level intellectual capacity

Medication and other therapies for psychiatric disorders show unsatisfying efficacy, in part due to the significant clinical/ biological heterogeneity within each disorder and our over-reliance on categorical clinical diagnoses. Alternatively, dimensional transdiagnostic studies have provided a promising pathway toward realizing personalized medicine and improved treatment outcomes. One factor that may influence response to psychiatric treatments is cognitive function, which is reflected in one's intellectual capacity. Intellectual capacity is also reflected in the organization and structure of intrinsic brain networks. Using a large transdiagnostic cohort (n = 1721), we sought to discover neuroimaging biomarkers by developing a resting-state functional connectome-based prediction model for a key intellectual capacity measure, Full-Scale Intelligence Quotient (FSIQ), across the diagnostic spectrum. Our cross-validated model yielded an excellent prediction accuracy (r = 0.5573, p < 0.001). The robustness and generalizability of our model was further validated on three independent cohorts (n = 2641). We identified key transdiagnostic connectome signatures underlying FSIQ capacity involving the dorsal-attention, frontoparietal and default-mode networks. Meanwhile, diagnosis groups showed disorder-specific biomarker patterns. Our findings advance the neurobiological understanding of cognitive functioning across traditional diagnostic categories and provide a new avenue for neuropathological classification of psychiatric disorders.