Connectome-based prediction of eating disorder-associated symptomatology

Review of machine learning solutions for eating disorders

BACKGROUND

Eating Disorders (EDs) are one of the most complex psychiatric disorders, with significant impairment of psychological and physical health, and psychosocial functioning, and are associated with low rates of early detection, low recovery and high relapse rates. This underscores the need for better diagnostic and treatment methods.

OBJECTIVE

This narrative review explores current Machine Learning (ML) and Artificial Intelligence (AI) applications in the domain of EDs, with a specific emphasis on clinical management in treatment settings. The primary objective are to (i) decrease the knowledge gap between ED researchers and AI-practitioners, by presenting the current state-of-the-art AI applications (including models for causality) in different ED use-cases; (ii) identify limitations of these existing AI interventions and how to address them.

RESULTS

AI/ML methods have been applied in different ED use-cases, including ED risk factor identification and incidence prediction (including the analysis of social media content in the general population), diagnosis, monitoring patients and treatment response and prognosis in clinical populations. A comparative analysis of AI-techniques deployed in these use-cases have been performed, considering factors such as complexity, flexibility, functionality, explainability and adaptability to healthcare constraints.

CONCLUSION

Multiple restrictions have been identified in the existing methods in ML and Causality in terms of achieving actionable healthcare for ED, like lack of good quality and quantity of data for models to train on, while requiring models to be flexible, high-performing, yet being explainable and producing counterfactual explanations, for ensuring the fairness and trustworthiness of its decisions. We conclude that to overcome these limitations and for future AI research and application in clinical management of ED, (i) careful considerations are required with regards to AI-model selection, and (ii) joint efforts from ED researcher and patient community are essential in building better quality and quantity of dedicated ED datasets and secure AI-solution framework.

Functional Connectome Hierarchy in Schizotypy and Its Associations With Expression of Schizophrenia-Related Genes

BACKGROUND AND HYPOTHESIS

Schizotypy has been conceptualized as a continuum of symptoms with marked genetic, neurobiological, and sensory-cognitive overlaps to schizophrenia. Hierarchical organization represents a general organizing principle for both the cortical connectome supporting sensation-to-cognition continuum and gene expression variability across the cortex. However, a mapping of connectome hierarchy to schizotypy remains to be established. Importantly, the underlying changes of the cortical connectome hierarchy that mechanistically link gene expressions to schizotypy are unclear.

STUDY DESIGN

The present study applied novel connectome gradient on resting-state fMRI data from 1013 healthy young adults to investigate schizotypy-associated sensorimotor-to-transmodal connectome hierarchy and assessed its similarity with the connectome hierarchy of schizophrenia. Furthermore, normative and differential postmortem gene expression data were utilized to examine transcriptional profiles linked to schizotypy-associated connectome hierarchy.

STUDY RESULTS

We found that schizotypy was associated with a compressed functional connectome hierarchy. Moreover, the pattern of schizotypy-related hierarchy exhibited a positive correlation with the connectome hierarchy observed in schizophrenia. This pattern was closely colocated with the expression of schizophrenia-related genes, with the correlated genes being enriched in transsynaptic, receptor signaling and calcium ion binding.

CONCLUSIONS

The compressed connectome hierarchy suggests diminished functional system differentiation, providing a novel and holistic system-level basis for various sensory-cognition deficits in schizotypy. Importantly, its linkage with schizophrenia-altered hierarchy and schizophrenia-related gene expression yields new insights into the neurobiological continuum of psychosis. It also provides mechanistic insight into how gene variation may drive alterations in functional hierarchy, mediating biological vulnerability of schizotypy to schizophrenia.

Cerebellar morphological differences and associations with extrinsic factors in bipolar disorder type I

BACKGROUND

The neural underpinnings of bipolar disorder (BD) remain poorly understood. The cerebellum is ideally positioned to modulate emotional regulation circuitry yet has been understudied in BD. Literature suggests differences in cerebellar activity and metabolism in BD, however findings on structural differences remain contradictory. Potential reasons include combining BD subtypes, small sample sizes, and potential moderators such as genetics, adverse childhood experiences (ACEs), and pharmacotherapy.

METHODS

We collected 3 T MRI scans from participants with (N = 131) and without (N = 81) BD type I, as well as blood and questionnaires. We assessed differences in cerebellar volumes and explored potentially influential factors.

RESULTS

The cerebellar cortex was smaller bilaterally in participants with BD. Polygenic propensity score did not predict any cerebellar volumes, suggesting that non-genetic factors may have greater influence on the cerebellar volume difference we observed in BD. Proportionate cerebellar white matter volumes appeared larger with more ACEs, but this may result from reduced ICV. Time from onset and symptom burden were not associated with cerebellar volumes. Finally, taking sedatives was associated with larger cerebellar white matter and non-significantly larger cortical volume.

LIMITATIONS

This study was cross-sectional, limiting interpretation of possible mechanisms. Most of our participants were White, which could limit the generalizability. Additionally, we did not account for potential polypharmacy interactions.

CONCLUSIONS

These findings suggest that external factors, such as sedatives and childhood experiences, may influence cerebellum structure in BD and may mask underlying differences. Accounting for such variables may be critical for consistent findings in future studies.