Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning

Abstract Individuals with schizophrenia experience significant cognitive impairments and alterations in brain function. However, the shared and unique brain functional patterns underlying cognition deficits and symptom severity in schizophrenia remain poorly understood. We design an interpretable gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Xia, Yi Hao Chan, Deepank Girish, Qian Hui Chew, Kang Sim, Jagath C. Rajapakse
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Communications Biology
Online Access:https://doi.org/10.1038/s42003-025-08637-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332342051569664
author Jing Xia
Yi Hao Chan
Deepank Girish
Qian Hui Chew
Kang Sim
Jagath C. Rajapakse
author_facet Jing Xia
Yi Hao Chan
Deepank Girish
Qian Hui Chew
Kang Sim
Jagath C. Rajapakse
author_sort Jing Xia
collection DOAJ
description Abstract Individuals with schizophrenia experience significant cognitive impairments and alterations in brain function. However, the shared and unique brain functional patterns underlying cognition deficits and symptom severity in schizophrenia remain poorly understood. We design an interpretable graph-based multi-task deep learning framework to enhance the simultaneous prediction of schizophrenia illness severity and cognitive functioning measurements by using functional connectivity, and identify both shared and unique brain patterns associated with these phenotypes on 378 subjects from three datasets. Our framework outperforms both single-task and state-of-the-art multi-task learning methods in predicting four Positive and Negative Syndrome Scale (PANSS) subscales and four cognitive domain scores. The performance is replicable across three datasets, and the shared and unique functional changes are confirmed by meta-analysis at both regional and modular levels. Our study provides insights into the neural correlates of illness severity and cognitive implications, offering potential targets for further evaluations of treatment effects and longitudinal follow-up.
format Article
id doaj-art-e5f8c2b25d1b4fccbf8c0042696d543b
institution Kabale University
issn 2399-3642
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Communications Biology
spelling doaj-art-e5f8c2b25d1b4fccbf8c0042696d543b2025-08-20T03:46:13ZengNature PortfolioCommunications Biology2399-36422025-08-018111710.1038/s42003-025-08637-0Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learningJing Xia0Yi Hao Chan1Deepank Girish2Qian Hui Chew3Kang Sim4Jagath C. Rajapakse5College of Computing and Data Science, Nanyang Technological UniversityCollege of Computing and Data Science, Nanyang Technological UniversityCollege of Computing and Data Science, Nanyang Technological UniversityResearch Division, Institute of Mental Health (IMH)Research Division, Institute of Mental Health (IMH)College of Computing and Data Science, Nanyang Technological UniversityAbstract Individuals with schizophrenia experience significant cognitive impairments and alterations in brain function. However, the shared and unique brain functional patterns underlying cognition deficits and symptom severity in schizophrenia remain poorly understood. We design an interpretable graph-based multi-task deep learning framework to enhance the simultaneous prediction of schizophrenia illness severity and cognitive functioning measurements by using functional connectivity, and identify both shared and unique brain patterns associated with these phenotypes on 378 subjects from three datasets. Our framework outperforms both single-task and state-of-the-art multi-task learning methods in predicting four Positive and Negative Syndrome Scale (PANSS) subscales and four cognitive domain scores. The performance is replicable across three datasets, and the shared and unique functional changes are confirmed by meta-analysis at both regional and modular levels. Our study provides insights into the neural correlates of illness severity and cognitive implications, offering potential targets for further evaluations of treatment effects and longitudinal follow-up.https://doi.org/10.1038/s42003-025-08637-0
spellingShingle Jing Xia
Yi Hao Chan
Deepank Girish
Qian Hui Chew
Kang Sim
Jagath C. Rajapakse
Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning
Communications Biology
title Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning
title_full Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning
title_fullStr Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning
title_full_unstemmed Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning
title_short Disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning
title_sort disentangling shared and unique brain functional changes associated with clinical severity and cognitive phenotypes in schizophrenia via deep learning
url https://doi.org/10.1038/s42003-025-08637-0
work_keys_str_mv AT jingxia disentanglingsharedanduniquebrainfunctionalchangesassociatedwithclinicalseverityandcognitivephenotypesinschizophreniaviadeeplearning
AT yihaochan disentanglingsharedanduniquebrainfunctionalchangesassociatedwithclinicalseverityandcognitivephenotypesinschizophreniaviadeeplearning
AT deepankgirish disentanglingsharedanduniquebrainfunctionalchangesassociatedwithclinicalseverityandcognitivephenotypesinschizophreniaviadeeplearning
AT qianhuichew disentanglingsharedanduniquebrainfunctionalchangesassociatedwithclinicalseverityandcognitivephenotypesinschizophreniaviadeeplearning
AT kangsim disentanglingsharedanduniquebrainfunctionalchangesassociatedwithclinicalseverityandcognitivephenotypesinschizophreniaviadeeplearning
AT jagathcrajapakse disentanglingsharedanduniquebrainfunctionalchangesassociatedwithclinicalseverityandcognitivephenotypesinschizophreniaviadeeplearning