Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning Techniques

Brain connectivity represents the functional organization of the brain, which is an important indicator for evaluating neuropsychiatric disorders and treatment effects. Schizophrenia is associated with impaired functional connectivity but characterizing the complex abnormality patterns has been chal...

Full description

Saved in:
Bibliographic Details
Main Authors: Janerra D. Allen, Sravani Varanasi, Fei Han, L. Elliot Hong, Fow-Sen Choa
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7742
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060258532130816
author Janerra D. Allen
Sravani Varanasi
Fei Han
L. Elliot Hong
Fow-Sen Choa
author_facet Janerra D. Allen
Sravani Varanasi
Fei Han
L. Elliot Hong
Fow-Sen Choa
author_sort Janerra D. Allen
collection DOAJ
description Brain connectivity represents the functional organization of the brain, which is an important indicator for evaluating neuropsychiatric disorders and treatment effects. Schizophrenia is associated with impaired functional connectivity but characterizing the complex abnormality patterns has been challenging. In this work, we used resting-state functional magnetic resonance imaging (fMRI) data to measure functional connectivity between 55 schizophrenia patients and 63 healthy controls across 246 regions of interest (ROIs) and extracted the disease-related connectivity patterns using energy landscape (EL) analysis. EL analysis captures the complexity of brain function in schizophrenia by focusing on functional brain state stability and region-specific dynamics. Age, sex, and smoker demographics between patients and controls were not significantly different. However, significant patient and control differences were found for the brief psychiatric rating scale (BPRS), auditory perceptual trait and state (APTS), visual perceptual trait and state (VPTS), working memory score, and processing speed score. We found that the brains of individuals with schizophrenia have abnormal energy landscape patterns between the right and left rostral lingual gyrus, and between the left lateral and orbital area in 12/47 regions. The results demonstrate the potential of the proposed imaging analysis workflow to identify potential connectivity biomarkers by indexing specific clinical features in schizophrenia patients.
format Article
id doaj-art-c1e1bb2612de44da9102f5861d8dab4c
institution DOAJ
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c1e1bb2612de44da9102f5861d8dab4c2025-08-20T02:50:37ZengMDPI AGSensors1424-82202024-12-012423774210.3390/s24237742Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning TechniquesJanerra D. Allen0Sravani Varanasi1Fei Han2L. Elliot Hong3Fow-Sen Choa4Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, MD 21250, USADepartment of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, MD 21250, USAThe Hilltop Institute, University of Maryland, Baltimore County, Baltimore, MD 21250, USADepartment of Psychiatry, University of Texas Health Science Center, Houston, TX 77030, USADepartment of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, MD 21250, USABrain connectivity represents the functional organization of the brain, which is an important indicator for evaluating neuropsychiatric disorders and treatment effects. Schizophrenia is associated with impaired functional connectivity but characterizing the complex abnormality patterns has been challenging. In this work, we used resting-state functional magnetic resonance imaging (fMRI) data to measure functional connectivity between 55 schizophrenia patients and 63 healthy controls across 246 regions of interest (ROIs) and extracted the disease-related connectivity patterns using energy landscape (EL) analysis. EL analysis captures the complexity of brain function in schizophrenia by focusing on functional brain state stability and region-specific dynamics. Age, sex, and smoker demographics between patients and controls were not significantly different. However, significant patient and control differences were found for the brief psychiatric rating scale (BPRS), auditory perceptual trait and state (APTS), visual perceptual trait and state (VPTS), working memory score, and processing speed score. We found that the brains of individuals with schizophrenia have abnormal energy landscape patterns between the right and left rostral lingual gyrus, and between the left lateral and orbital area in 12/47 regions. The results demonstrate the potential of the proposed imaging analysis workflow to identify potential connectivity biomarkers by indexing specific clinical features in schizophrenia patients.https://www.mdpi.com/1424-8220/24/23/7742energy landscapefMRIfunctional connectivitybiomarkerschizophrenia
spellingShingle Janerra D. Allen
Sravani Varanasi
Fei Han
L. Elliot Hong
Fow-Sen Choa
Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning Techniques
Sensors
energy landscape
fMRI
functional connectivity
biomarker
schizophrenia
title Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning Techniques
title_full Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning Techniques
title_fullStr Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning Techniques
title_full_unstemmed Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning Techniques
title_short Functional Connectivity Biomarker Extraction for Schizophrenia Based on Energy Landscape Machine Learning Techniques
title_sort functional connectivity biomarker extraction for schizophrenia based on energy landscape machine learning techniques
topic energy landscape
fMRI
functional connectivity
biomarker
schizophrenia
url https://www.mdpi.com/1424-8220/24/23/7742
work_keys_str_mv AT janerradallen functionalconnectivitybiomarkerextractionforschizophreniabasedonenergylandscapemachinelearningtechniques
AT sravanivaranasi functionalconnectivitybiomarkerextractionforschizophreniabasedonenergylandscapemachinelearningtechniques
AT feihan functionalconnectivitybiomarkerextractionforschizophreniabasedonenergylandscapemachinelearningtechniques
AT lelliothong functionalconnectivitybiomarkerextractionforschizophreniabasedonenergylandscapemachinelearningtechniques
AT fowsenchoa functionalconnectivitybiomarkerextractionforschizophreniabasedonenergylandscapemachinelearningtechniques