Systematic Review of Functional MRI Applications for Psychiatric Disease Subtyping

Abstract

Background: Psychiatric disorders have been historically classified using symptom information alone. Recently, there has been a dramatic increase in research interest not only in identifying the mechanisms underlying defined pathologies but also in redefining their etiology. This is particularly relevant for the field of personalized medicine, which searches for data-driven approaches to improve diagnosis, prognosis, and treatment selection for individual patients. Methods: This review aims to provide a high-level overview of the rapidly growing field of functional magnetic resonance imaging (fMRI) from the perspective of unsupervised machine learning applications for disease subtyping. Following the PRISMA guidelines for protocol reproducibility, we searched the PubMed database for articles describing functional MRI applications used to obtain, interpret, or validate psychiatric disease subtypes. We also employed the active learning framework ASReview to prioritize publications in a machine learning-guided way. Results: From the 20 studies that met the inclusion criteria, five used functional MRI data to interpret symptom-derived disease clusters, four used it to interpret clusters derived from biomarker data other than fMRI itself, and 11 applied clustering techniques involving fMRI directly. Major depression disorder and schizophrenia were the two most frequently studied pathologies (35% and 30% of the retrieved studies, respectively), followed by ADHD (15%), psychosis as a whole (10%), autism disorder (5%), and the consequences of early exposure to violence (5%). Conclusions: The increased interest in personalized medicine and data-driven disease subtyping also extends to psychiatric disorders. However, to date, this subfield is at an incipient exploratory stage, and all retrieved studies were mostly proofs of principle where further validation and increased sample sizes are craved for. Whereas results for all explored diseases are inconsistent, we believe this reflects the need for concerted, multisite data collection efforts with a strong focus on measuring the generalizability of results. Finally, whereas functional MRI is the best way of measuring brain function available to date, its low signal-to-noise ratio and elevated monetary cost make it a poor clinical alternative. Even with technology progressing and costs decreasing, this might incentivize the search for more accessible, clinically ready functional proxies in the future.

Keywords: biotypes; clustering; disease subtyping; functional MRI (fMRI); machine learning; personalized medicine; translational psychiatry; unsupervised learning.

Figure 1

Paper selection pipeline. PRISMA flowchart (represented as a ribbon plot, which flows from top to bottom) that schematizes the employed pipeline. A total of 144 articles were retrieved from PubMed using the string “(unsupervised learning OR clustering OR dimensionality reduction OR subtyping) AND functional MRI”. Two articles were included after the manual search, yielding a total of 146 input studies. After several systematic filters, which included the exclusion of reviews, duplicated articles, and relevance to the defined inclusion criteria, a total of 20 articles were included in the review.

Figure 2

Characteristics of retrieved studies. (A) Donut plot representing the number of selected studies for each of the three defined categories: (a) fMRI used for validation of subtypes obtained via unsupervised learning of symptom-related data, (b) fMRI used for validation of subtypes obtained via unsupervised learning of biomarkers other than fMRI (including structural MRI), and (c) fMRI used for brain disease subtyping directly. (B) Donut plot representing the most prevalent brain disorders that the included studies analyzed.