The Heterogeneity Problem: Approaches to Identify Psychiatric Subtypes

Feczko, Eric; Miranda-Domínguez, Óscar; Marr, Mollie; Graham, Alice M.; Nigg, Joel T.; Fair, Damien A.

doi:10.1016/j.tics.2019.03.009

Cited by 291 publications

(206 citation statements)

References 119 publications

Supporting

Mentioning

194

Contrasting

Order By: Relevance

“…As an example, Müller et al (2017) partially attribute the lack of convergence in their meta-analysis of activation-based fMRI experiments involving 1,058 MDD patients to clinical heterogeneity. As a result, future research probing the neurobiology of depression should aim for large sample sizes (Rutledge, Chekroud, & Huys, 2019), and more importantly, stratifying patients (Feczko et al, 2019) with depression at the individual level. Pursuant to this, there has been considerable interest in identifying clinically relevant subgroups based on brain imaging, with initially encouraging results (Drysdale et al, 2017).…”

Section: Discussionmentioning

confidence: 99%

Multimodal fusion of structural and functional brain imaging in depression using linked independent component analysis

Maglanoc

Kaufmann

Jonassen

et al. 2019

Human Brain Mapping

View full text Add to dashboard Cite

Previous structural and functional neuroimaging studies have implicated distributed brain regions and networks in depression. However, there are no robust imaging biomarkers that are specific to depression, which may be due to clinical heterogeneity and neurobiological complexity. A dimensional approach and fusion of imaging modalities may yield a more coherent view of the neuronal correlates of depression. We used linked independent component analysis to fuse cortical macrostructure (thickness, area, gray matter density), white matter diffusion properties and resting‐state functional magnetic resonance imaging default mode network amplitude in patients with a history of depression (n = 170) and controls (n = 71). We used univariate and machine learning approaches to assess the relationship between age, sex, case–control status, and symptom loads for depression and anxiety with the resulting brain components. Univariate analyses revealed strong associations between age and sex with mainly global but also regional specific brain components, with varying degrees of multimodal involvement. In contrast, there were no significant associations with case–control status, nor symptom loads for depression and anxiety with the brain components, nor any interaction effects with age and sex. Machine learning revealed low model performance for classifying patients from controls and predicting symptom loads for depression and anxiety, but high age prediction accuracy. Multimodal fusion of brain imaging data alone may not be sufficient for dissecting the clinical and neurobiological heterogeneity of depression. Precise clinical stratification and methods for brain phenotyping at the individual level based on large training samples may be needed to parse the neuroanatomy of depression.

show abstract

Section: Discussionmentioning

confidence: 99%

Multimodal fusion of structural and functional brain imaging in depression using linked independent component analysis

Maglanoc

Kaufmann

Jonassen

et al. 2019

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…Others have also reported on the absence of clear biological distinctions on structural or functional neuroimaging measures when comparing different NDD diagnostic groups [13][14][15][16][17][18] Data-driven clustering approaches offer a methodological alternative to conventional comparisons between clinically defined groups. This alternative approach may better disentangle heterogeneity within and across current diagnostic categories to identify participant subgroups that may be more similar to each other in brain or behavior [10]. Some of these approaches use data integration techniques to identify data-driven subgroups beyond using neuroimaging [19] or behavioral features alone [13].…”

Section: Introductionmentioning

confidence: 99%

Integration of Brain and Behavior Measures for Identification of Data-Driven Groups Cutting Across Children with ASD, ADHD, or OCD

Jacobs

Voineskos

Hawco

et al. 2020

Preprint

View full text Add to dashboard Cite

Autism spectrum disorder (ASD), obsessive-compulsive disorder (OCD) and attentiondeficit/hyperactivity disorder (ADHD) are clinically and biologically heterogeneous neurodevelopmental disorders (NDDs). The objective of the present study was to integrate brain imaging and behavioral measures to identify new brain-behavior subgroups cutting across these disorders. A subset of the data from the Province of Ontario Neurodevelopmental Disorder (POND) Network including participants with different NDDs (aged 6-16 years) that underwent cross-sectional T1-weighted and diffusion-weighted magnetic resonance imaging (MRI) scanning on the same 3T scanner, and behavioral/cognitive assessments was used. Similarity Network Fusion was applied to integrate cortical thickness, subcortical volume, white matter fractional anisotropy (FA), and behavioral measures in 176 children with ASD, ADHD or OCD with complete data that passed quality control. Normalized mutual information (NMI) was used to determine top contributing model features. Bootstrapping, out-of-model outcome measures and supervised machine learning were each used to examine stability and evaluate the new groups. Cortical thickness in socio-emotional and attention/executive networks and inattention symptoms comprised the top ten features driving participant similarity and differences between four transdiagnostic groups. Subcortical volumes (pallidum, nucleus accumbens, thalamus) were also different among groups, although white matter FA showed limited differences. Features driving participant similarity remained stable across resampling, and the new groups showed significantly different scores on everyday adaptive functioning. Our findings open the possibility of studying new data-driven groups that represent children with NDDs more similar to each other than others within their own diagnostic group. Such new groups can be evaluated longitudinally for prognostic utility and could be stratified for clinical trials targeted toward each group's unique brain and behavioral profiles.

show abstract

“…Indeed, in the last decade, there has been an exponential increase in machine learning approaches in the field of posttraumatic stress, including both supervised and unsupervised approaches. Supervised analytic approaches make assumptions and are therefore limited by how much the assumptions are informed accurately by prior knowledge 42 . On the other hand, unsupervised approaches make few or no assumptions, but are limited in such that subpopulations revealed by the analysis are not tied to specific questions of interest 42 .…”

Section: Introductionmentioning

confidence: 99%

Potential Neurocognitive Biomarkers for Post Traumatic Stress Disorder (PTSD) Severity in Recent Trauma Survivors

Ben‐Zion

Zeevi

et al. 2019

Preprint

View full text Add to dashboard Cite

Contemporary symptom-based diagnosis of Post-traumatic Stress Disorder (PTSD) largely overlooks related neurobehavioral findings and rely entirely on subjective interpersonal reporting. Previous studies associating objective biomarkers with PTSD have mostly used the disorder's symptom-based diagnosis as main outcome measure, overlooking the actual clustering and richness of phenotypical features associated with PTSD. Here, we aimed to computationally derive potential neurocognitive biomarkers that could efficiently differentiate PTSD subtypes, based on an observational cohort study of recent trauma survivors. A three-staged semi-unsupervised method ("3C") was used to categorize trauma survivors based on current PTSD diagnostics, derive clusters of PTSD based on features related to symptom load, and to classify participants' cluster membership using objective features. A total of 256 features were extracted from psychometrics, cognitive, structural and functional neuroimaging data, obtained from 101 adult civilians (age=34.80±11.95, 51 females) evaluated within a month of trauma exposure. Multi-domain features that best differentiated cluster membership were indicated by using importance analysis, classification trees, and ANOVA. Results revealed that entorhinal and rostral anterior cingulate cortices volumes (structural 3 domain), in-task amygdala's functional connectivity with the insula and thalamus (functional domain), executive function and cognitive flexibility (cognitive domain) best differentiated between two clusters related to PTSD severity. Cross-validation established the results' robustness and consistency within this sample. Multi-domain biomarkers revealed by the 3C analytics offer objective classifiers of post-traumatic morbidityshortly following trauma. They also map onto previously documented neurobehavioral PTSD features, supporting the future use of standardized and objective measurements to more precisely identify psychopathology subgroups shortly after trauma.

show abstract

The Heterogeneity Problem: Approaches to Identify Psychiatric Subtypes

Cited by 291 publications

References 119 publications

Multimodal fusion of structural and functional brain imaging in depression using linked independent component analysis

Multimodal fusion of structural and functional brain imaging in depression using linked independent component analysis

Integration of Brain and Behavior Measures for Identification of Data-Driven Groups Cutting Across Children with ASD, ADHD, or OCD

Potential Neurocognitive Biomarkers for Post Traumatic Stress Disorder (PTSD) Severity in Recent Trauma Survivors

Contact Info

Product

Resources

About