Preprint Open Access

# Functional MRI applications for psychiatric disease subtyping: a review

Miranda, Lucas; Paul, Riya; Pütz, Benno; Müller-Myhsok, Bertram

### Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:creator>Miranda, Lucas</dc:creator>
<dc:creator>Paul, Riya</dc:creator>
<dc:creator>Pütz, Benno</dc:creator>
<dc:creator>Müller-Myhsok, Bertram</dc:creator>
<dc:date>2020-06-30</dc:date>
<dc:description>Background

Psychiatric disorders have historically been classified using symptom information alone. With the advent of new technologies that allowed researchers to investigate brain mechanisms in a more direct manner, interest in not only the mechanistic rationale behind defined pathologies but also aetiology redefinition has greatly increased. This is particularly appealing for the field of personalised medicine, which searches for data-driven approaches to improve diagnosis, prognosis and treatment selection on an individual basis.

Objective

In the present article, we intend to systematically analyse the usage of functional MRI on both the elucidation of psychiatric disease biotypes and the interpretation/validation of subtypes obtained via unsupervised learning techniques applied to symptom or biomarker data.

Methods

Using PubMed, we searched the existing literature for functional MRI applications to the obtention or interpretation/validation of psychiatric disease subtypes in humans. The PRISMA guidelines were applied to filter the retrieved studies, and the active learning framework ASReviews was applied for article prioritization.

Results

From the 20 studies that met the inclusion criteria, 5 used functional MRI data to interpret symptom-derived disease clusters, 4 used it for the interpretation of clusters derived from biomarker data other than fMRI itself, and 11 applied clustering techniques to fMRI directly. Major depression disorder and schizophrenia were the two most studied pathologies (35% and 30% of the retrieved studies, respectively), followed by ADHD (15%), psychosis (10%), autism disorder (5%), and the consequences of early violence (5%). No trans-diagnostic studies were retrieved.

Conclusions

While interest in personalised medicine and data-driven disease subtyping is on the rise and psychiatry is not the exception, unsupervised analyses of functional MRI data are inconsistent to date, and much remains to be done in terms of gathering and centralising data, standardising pipelines and model validation, and method refinement. The usage of fMRI in the field of trans-diagnostic psychiatry, of great importance for the aforementioned goals, remains vastly unexplored.</dc:description>
<dc:identifier>https://zenodo.org/record/3923919</dc:identifier>
<dc:identifier>10.5281/zenodo.3923919</dc:identifier>
<dc:identifier>oai:zenodo.org:3923919</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>info:eu-repo/grantAgreement/EC/H2020/813533/</dc:relation>
<dc:relation>doi:10.5281/zenodo.3923918</dc:relation>
<dc:relation>url:https://zenodo.org/communities/mlfpm</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:subject>functional MRI</dc:subject>
<dc:subject>unsupervised learning</dc:subject>
<dc:subject>clustering</dc:subject>
<dc:subject>subtypes</dc:subject>
<dc:subject>machine learning</dc:subject>
<dc:subject>personalised medicine</dc:subject>
<dc:subject>translational psychiatry</dc:subject>
<dc:subject>artificial intelligence</dc:subject>
<dc:subject>mental health</dc:subject>
<dc:subject>clinical psychology</dc:subject>
<dc:subject>psychiatry</dc:subject>
<dc:title>Functional MRI applications for psychiatric disease subtyping: a review</dc:title>
<dc:type>info:eu-repo/semantics/preprint</dc:type>
<dc:type>publication-preprint</dc:type>
</oai_dc:dc>

144
90
views