Data-Driven Clustering Reveals a Link Between Symptoms and Functional Brain Connectivity in Depression

Maglanoc, Luigi A.; Landrø, Nils Inge; Jonassen, Rune; Kaufmann, Tobias; Córdova‐Palomera, Aldo; Hilland, Eva; Westlye, Lars T.

doi:10.1016/j.bpsc.2018.05.005

Cited by 34 publications

(16 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…FIX substantially improved tSNR ( t = 20.89, p < .001, Cohen's d = 1.95), and no fMRI scans from healthy controls ( n = 72) nor from patients ( n = 178) were excluded. Group‐level ICA with model order fixed at 40 was performed on a balanced subset of healthy controls and patients ( N = 72 from each group), which has been used in a previous study (Maglanoc et al, ). Dual regression (Nickerson, Smith, Öngür, & Beckmann, ) was used to estimate spatial maps and corresponding time series of all components.…”

Section: Methodsmentioning

confidence: 99%

“…Resting-state fMRI data were processed using the FSL's FMRI Expert Analysis Tool. This included coregistration with T1 images, brain (N = 72 from each group), which has been used in a previous study (Maglanoc et al, 2019). Dual regression (Nickerson, Smith, Öngür, & Beckmann, 2017) was used to estimate spatial maps and corresponding time series of all components.…”

Section: Resting-state Fmri Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

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

Maglanoc

Kaufmann

Jonassen

et al. 2019

Human Brain Mapping

Self Cite

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: Methodsmentioning

confidence: 99%

Section: Resting-state Fmri Preprocessingmentioning

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Darüber hinaus gibt es ebenfalls Bemühungen im Bereich des nichtsupervidierten Lernens, die bisherigen diagnostischen Trennlinien zugunsten naturalistischer Einteilungen aufzulösen. Diese neuen Trennlinien werden basierend auf maschinellen Algorithmen unter anderem anhand klinischer [39,40], kognitiver [41,42], genetischer [43][44][45], hirnfunktioneller [46][47][48] oder hirnstruktureller Muster [49,50] entworfen. Des Weiteren wurden bereits auch Kindheitstraumata [51], Psychopathie [52], Suizidalität [53] oder Empathie [54] mithilfe nicht-supervidierter Algorithmen in verschiedene neurobiologische oder genetische Merkmalsräume dekonstruiert.…”

Section: Diagnostikunclassified

Präzisionspsychiatrie und der Beitrag von Brain Imaging und anderen Biomarkern

Popovic

Schiltz

Falkai

et al. 2020

Fortschr Neurol Psychiatr

View full text Add to dashboard Cite

ZusammenfassungDie Präzisionspsychiatrie stellt die psychiatrische Variante des übergeordneten Konzepts der Präzisionsmedizin dar. Hierbei soll eine auf Biomarkern basierte und auf die individuelle klinische, neurobiologische und genetische Konstitution des Patienten zugeschnittene Diagnostik und Behandlung angeboten werden. Die spezifische Eigenheit des Fachs Psychiatrie, in der die Krankheitsentitäten normativ anhand klinischer Erfahrungswerte definiert und damit auch maßgeblich durch zeitgeschichtliche, gesellschaftliche und philosophische Einflüsse geprägt sind, hat bisher die Suche nach psychobiologischen Zusammenhängen erschwert. Dennoch gibt es mittlerweile in allen Bereichen der psychiatrischen Forschung erhebliche Fortschritte, die vor allem durch die kritische Überprüfung und Erneuerung bisheriger Krankheits- und Psychopathologie-Konzepte, die vermehrte Ausrichtung hin zur Neurobiologie und Genetik und insbesondere die Verwendung maschineller Lernverfahren ermöglicht wurden. Vor allem letztere Analysemethoden erlauben es, hochdimensionale und multimodale Datensätze zu integrieren und Modelle zu entwickeln, die einerseits neue psychobiologische Erkenntnisse liefern und andererseits eine real anwendbare Prädiktion von Diagnose, Therapieansprechen und Prognose auf Einzelfallniveau zunehmend realistisch erscheinen lassen. Ziel der hier vorliegenden Übersichtsarbeit soll daher sein, dem interessierten Leser das Konzept der Präzisionspsychiatrie näherzubringen, die hierfür verwendeten maschinellen Lernverfahren darzustellen und sowohl den gegenwärtigen Entwicklungsstand als auch zukunftsnahe Entwicklungen in diesem neuen Feld übersichtlich darzustellen.

show abstract

“…7 Multiple data-driven approaches for identifying disease phenotypes with EHRs have been explored. 8,9 From a data-driven perspective, discovering phenotypes using EHRs can be seen as a "data clustering" problem. [9][10][11] The disease manifestations of patients in the same cluster (ie, subphenotype) usually tend to be more 12 can be performed on each cluster, which aim at finding discriminative variables across different clusters and providing interpretation for the computationally derived subphenotypes.…”

Section: Introductionmentioning

confidence: 99%

Subphenotyping depression using machine learning and electronic health records

Wang

Adekkanattu

et al. 2020

Learning Health Systems

View full text Add to dashboard Cite

Objective: To identify depression subphenotypes from Electronic Health Records (EHRs) using machine learning methods, and analyze their characteristics with respect to patient demographics, comorbidities, and medications. Materials and Methods: Using EHRs from the INSIGHT Clinical Research Network (CRN) database, multiple machine learning (ML) algorithms were applied to analyze 11 275 patients with depression to discern depression subphenotypes with distinct characteristics. Results: Using the computational approaches, we derived three depression subphenotypes: Phenotype_A (n = 2791; 31.35%) included patients who were the oldest (mean (SD) age, 72.55 (14.93) years), had the most comorbidities, and took the most medications. The most common comorbidities in this cluster of patients were hyperlipidemia, hypertension, and diabetes. Phenotype_B (mean (SD) age, 68.44 (19.09) years) was the largest cluster (n = 4687; 52.65%), and included patients suffering from moderate loss of body function. Asthma, fibromyalgia, and Chronic Pain and Fatigue (CPF) were common comorbidities in this subphenotype. Phenotype_C (n = 1452; 16.31%) included patients who were younger (mean (SD) age, 63.47 (18.81) years), had the fewest comorbidities, and took fewer medications. Anxiety and tobacco use were common comorbidities in this subphenotype. Conclusion: Computationally deriving depression subtypes can provide meaningful insights and improve understanding of depression as a heterogeneous disorder. Further investigation is needed to assess the utility of these derived phenotypes to inform clinical trial design and interpretation in routine patient care.

show abstract

Data-Driven Clustering Reveals a Link Between Symptoms and Functional Brain Connectivity in Depression

Abstract: Adding to the pursuit of individual-based treatment, subtyping based on a dimensional conceptualization and unique constellations of anxiety and depression symptoms is supported by distinct patterns of static functional connectivity in the brain.

Cited by 34 publications

References 78 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

Präzisionspsychiatrie und der Beitrag von Brain Imaging und anderen Biomarkern

Subphenotyping depression using machine learning and electronic health records

Contact Info

Product

Resources

About