Identifying subgroups of eating behavior traits unrelated to obesity using functional connectivity and feature representation learning.

Eating behavior is highly heterogeneous across individuals and cannot be fully explained using only the degree of obesity. We utilized unsupervised machine learning and functional connectivity measures to explore the heterogeneity of eating behaviors measured by a self-assessment instrument using 424 healthy adults (mean ± standard deviation [SD] age = 47.07 ± 18.89 years; 67% female). We generated low-dimensional representations of functional connectivity using resting-state functional magnetic resonance imaging and estimated latent features using the feature representation capabilities of an autoencoder by nonlinearly compressing the functional connectivity information. The clustering approaches applied to latent features identified three distinct subgroups. The subgroups exhibited different levels of hunger traits, while their body mass indices were comparable. The results were replicated in an independent dataset consisting of 212 participants (mean ± SD age = 38.97 ± 19.80 years; 35% female). The model interpretation technique of integrated gradients revealed that the between-group differences in the integrated gradient maps were associated with functional reorganization in heteromodal association and limbic cortices and reward-related subcortical structures such as the accumbens, amygdala, and caudate. The cognitive decoding analysis revealed that these systems are associated with reward- and emotion-related systems. Our findings provide insights into the macroscopic brain organization of eating behavior-related subgroups independent of obesity.

Structural connectome alterations between individuals with autism and neurotypical controls using feature representation learning.

Autism spectrum disorder is one of the most common neurodevelopmental conditions associated with sensory and social communication impairments. Previous neuroimaging studies reported that atypical nodal- or network-level functional brain organization in individuals with autism was associated with autistic behaviors. Although dimensionality reduction techniques have the potential to uncover new biomarkers, the analysis of whole-brain structural connectome abnormalities in a low-dimensional latent space is underinvestigated. In this study, we utilized autoencoder-based feature representation learning for diffusion magnetic resonance imaging-based structural connectivity in 80 individuals with autism and 61 neurotypical controls that passed strict quality controls. We generated low-dimensional latent features using the autoencoder model for each group and adopted an integrated gradient approach to assess the contribution of the input data for predicting latent features during the encoding process. Subsequently, we compared the integrated gradient values between individuals with autism and neurotypical controls and observed differences within the transmodal regions and between the sensory and limbic systems. Finally, we identified significant associations between integrated gradient values and communication abilities in individuals with autism. Our findings provide insights into the whole-brain structural connectome in autism and may help identify potential biomarkers for autistic connectopathy.

Diagnosis-informed connectivity subtyping discovers subgroups of autism with reproducible symptom profiles.

Clinical heterogeneity has been one of the main barriers to develop effective biomarkers and therapeutic strategies in autism spectrum disorder (ASD). Recognizing this challenge, much effort has been made in recent neuroimaging studies to find biologically more homogeneous subgroups (called 'neurosubtypes') in autism. However, most approaches have rarely evaluated how much the employed features in subtyping represent the core anomalies of ASD, obscuring its utility in actual clinical diagnosis. To address this, we combined two data-driven methods, 'connectome-based gradient' and 'functional random forest', collectively allowing to discover reproducible neurosubtypes based on resting-state functional connectivity profiles that are specific to ASD. Indeed, the former technique provides the features (as input for subtyping) that effectively summarize whole-brain connectome variations in both normal and ASD conditions, while the latter leverages a supervised random forest algorithm to inform diagnostic labels to clustering, which makes neurosubtyping driven by the features of ASD core anomalies. Applying this framework to the open-sharing Autism Brain Imaging Data Exchange repository data (discovery, n = 103/108 for ASD/typically developing [TD]; replication, n = 44/42 for ASD/TD), we found three dominant subtypes of functional gradients in ASD and three subtypes in TD. The subtypes in ASD revealed distinct connectome profiles in multiple brain areas, which are associated with different Neurosynth-derived cognitive functions previously implicated in autism studies. Moreover, these subtypes showed different symptom severity, which degree co-varies with the extent of functional gradient changes observed across the groups. The subtypes in the discovery and replication datasets showed similar symptom profiles in social interaction and communication domains, confirming a largely reproducible brain-behavior relationship. Finally, the connectome gradients in ASD subtypes present both common and distinct patterns compared to those in TD, reflecting their potential overlap and divergence in terms of developmental mechanisms involved in the manifestation of large-scale functional networks. Our study demonstrated a potential of the diagnosis-informed subtyping approach in developing a clinically useful brain-based classification system for future ASD research.

Multiclassification of the symptom severity of social anxiety disorder using digital phenotypes and feature representation learning.

Objective: Social anxiety disorder (SAD) is characterized by heightened sensitivity to social interactions or settings, which disrupts daily activities and social relationships. This study aimed to explore the feasibility of utilizing digital phenotypes for predicting the severity of these symptoms and to elucidate how the main predictive digital phenotypes differed depending on the symptom severity. Method: We collected 511 behavioral and physiological data over 7 to 13 weeks from 27 SAD and 31 healthy individuals using smartphones and smartbands, from which we extracted 76 digital phenotype features. To reduce data dimensionality, we employed an autoencoder, an unsupervised machine learning model that transformed these features into low-dimensional latent representations. Symptom severity was assessed with three social anxiety-specific and nine additional psychological scales. For each symptom, we developed individual classifiers to predict the severity and applied integrated gradients to identify critical predictive features. Results: Classifiers targeting social anxiety symptoms outperformed baseline accuracy, achieving mean accuracy and F1 scores of 87% (with both metrics in the range 84-90%). For secondary psychological symptoms, classifiers demonstrated mean accuracy and F1 scores of 85%. Application of integrated gradients revealed key digital phenotypes with substantial influence on the predictive models, differentiated by symptom types and levels of severity. Conclusions: Leveraging digital phenotypes through feature representation learning could effectively classify symptom severities in SAD. It identifies distinct digital phenotypes associated with the cognitive, emotional, and behavioral dimensions of SAD, thereby advancing the understanding of SAD. These findings underscore the potential utility of digital phenotypes in informing clinical management.