Towards improved specificity in mental health syndromes: projection-based clustering of depressive phenotypes

Quantitative attempts to improve syndrome specificity typically produce large heterogenous subgroupings, impacting the validity of treatment and research targets. Assessing barriers to the valid application of existing methods and examining improvements from an interpretable projection-based clustering alternative may improve the precision and reproducibility of our research targets and classification systems.

This exploratory, cross-sectional, study recruited 2820 participants aged 12-to-25 years, from primary-healthcare services in Australia, between November 2018 and July 2023. 1843 participants completed relevant self-reported measures of depression, anxiety and mania-like experiences, and were included for analysis. Principal Component Analysis (PCA) was used to examine the distribution of within-syndrome variance. Projection-based subtypes were compared to traditional quantitative phenotyping approaches: clustering paradigms (Model-Based, Centre-Based Partition, Hierarchical), LCA, and Exploratory Factor Analysis (FA).

Interpretable projection-based clustering improved homogeneity and qualitative distinctions between clusters were compared to all other methods. This identified 14 clusters organisable into six novel symptom profiles: sleep (n = 117; 11 %), mania (n = 125; 12 %), anxiety (n = 119; 11 %), weight/appetite gain (n = 138; 13 %), weight/appetite loss (n = 242; 23 %), and an undifferentiated type (n = 310; 29 %). The PCA identified a skewed power-law distribution underlying symptom variance, affecting standard LCA/clustering procedures. This interacted with optimisation algorithms, producing heterogenous subtypes. Within FA, it produced the nested hierarchical structure identified in HiTOP studies.

A skewed variance distribution underlying the depressive syndrome adversely impacts standard Clustering/LCA methods, and may contribute to past difficulties in identifying well-specified data-driven phenotypes. Consequently, future studies should consider the distribution's impact to their optimisation algorithms or use the better-specified projection-based clustering. Identified profiles reflect major trends in depressive symptom expression, potentially representing improved research targets.