Interpretable Machine Learning Model for Characterizing Magnetic Susceptibility based Biomarkers in First Episode Psychosis

Simple item page
dc.article.number109067
dc.catalogadorgrr
dc.contributor.authorFranco, Pamela
dc.contributor.authorMontalba Zalaquett, Cristian Andres
dc.contributor.author Caulier-Cisterna, Raul
dc.contributor.authorMilovic Fabregat, Carlos Andrés
dc.contributor.authorGonzalez, Alfonso
dc.contributor.authorRamirez Mahaluf, Juan Pablo
dc.contributor.authorUndurraga, Juan
dc.contributor.authorSalas, Rodrigo
dc.contributor.authorCrossley, Nicolás
dc.contributor.authorTejos Núñez, Cristián Andrés
dc.contributor.authorUribe, Sergio
dc.date.accessioned2025-09-09T15:01:51Z
dc.date.available2025-09-09T15:01:51Z
dc.date.issued2025
dc.description.abstractAltered neurochemicals in deep-brain nuclei, especially dopamine dysfunction, arelinked to psychosis. Quantitative Susceptibility Mapping (QSM) measures brainmagnetic susceptibility changes, including iron concentration, which affects dopaminepathways. This study used machine learning (ML) to analyze MRI data and build aclassifier distinguishing healthy individuals from First-Episode Psychosis (FEP)patients while predicting their response to antipsychotic treatment. A random forestmodel was trained, with the SHAP framework assessing feature importance andinterpretability. Hierarchical clustering identified relationships among features. Themodel achieved performance, with 76.48 ± 10.73% accuracy for classifying FEPpatients (based on R2* values in the nucleus accumbens and amygdala, and QSM inthe thalamus) and 76.43 ± 12.57% accuracy for predicting treatment response (basedon R2* values in the hippocampus, caudate, and putamen, and QSM in the amygdala).MRI-based biomarkers and ML could help tailor personalized treatments for FEPpatients, especially those not responding to standard therapies.
dc.fechaingreso.objetodigital2025-09-09
dc.format.extent43 páginas
dc.fuente.origenSIPA
dc.identifier.doi10.1016/j.cmpb.2025.109067
dc.identifier.eissn1872-7565
dc.identifier.issn0169-2607
dc.identifier.urihttps://doi.org/10.1016/j.cmpb.2025.109067
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/105620
dc.information.autorucEscuela de Medicina; Montalba Zalaquett, Cristian Andres; 0000-0003-3370-0233; 1077325
dc.information.autorucEscuela de Ingeniería; Milovic Fabregat, Carlos Andrés; 0000-0002-1196-6703; 120377
dc.information.autorucEscuela de Medicina; Ramirez Mahaluf, Juan Pablo; 0000-0002-0821-1174; 17132
dc.information.autorucEscuela de Medicina; Crossley, Nicolás; 0000-0002-3060-656X; 11224
dc.information.autorucEscuela de Ingeniería; Tejos Núñez, Cristián Andrés; 0000-0002-8367-155X; 4027
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaComputer Methods and Programs in Biomedicine Update
dc.rightsacceso abierto
dc.rights.licenseCC BY 4.0 Attribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subject Interpretable Machine Learning
dc.subjectMagnetic Resonance Imaging
dc.subjectBiomarkers
dc.subjectArtificial Intelligence for Medical Imaging
dc.subjectQuantitative Susceptibility Mapping
dc.subject.ddc610
dc.subject.ods03 Good health and well-being
dc.subject.odspa03 Salud y bienestar
dc.titleInterpretable Machine Learning Model for Characterizing Magnetic Susceptibility based Biomarkers in First Episode Psychosis
dc.title.alternativeComputer Methods and Programs in Biomedicine Available online 6 September 2025, 109067
dc.typepreprint
sipa.codpersvinculados1077325
sipa.codpersvinculados120377
sipa.codpersvinculados17132
sipa.codpersvinculados11224
sipa.codpersvinculados4027
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S0169260725004845-main.pdf
Size:
2.08 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.98 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos de revistas