RT Journal Article
SR Electronic
T1 Multi-dimensional predictions of psychotic symptoms via machine learning
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.03.02.974246
DO 10.1101/2020.03.02.974246
A1 Jeremy A Taylor
A1 Kit Melissa Larsen
A1 Marta I Garrido
YR 2020
UL http://biorxiv.org/content/early/2020/03/05/2020.03.02.974246.abstract
AB Background The diagnostic criteria for schizophrenia comprise a diverse range of heterogeneous symptoms. As a result, individuals each present a distinct set of symptoms despite having the same overall diagnosis.Methods Although machine learning techniques are considered a potential gateway to precision psychiatry, prior work has primarily focused on dichotomous patient-control classification. Instead, we predict the severity of each individual symptom on a continuum. We applied machine learning regression within a multi-modal fusion framework to fMRI and behavioural data acquired during an auditory oddball task in 80 schizophrenia patients.Results Brain activity was highly predictive of some, but not all symptoms, namely hallucinations, avolition, anhedonia and attention. Each of these symptoms was associated with alterations in specific functional networks encompassing the ventral and dorsal attention networks, the auditory network, amongst other cortical and subcortical regions. We found that an ensemble of subscale models yielded a two-fold increase in accuracy over single models which predict positive and negative compound scores directly.Conclusions Our results suggest that modelling symptoms as an ensemble of subscales is more accurate, specific, and informative than the compound-based approach. We provide functional brain maps of model contributions identifying the networks of regions which pertain to each individual symptom. This approach is transferrable to any other psychiatric condition and may also contribute to the development of precision psychiatry.