Publication:
Interpretable machine learning model for characterizing magnetic susceptibility-based biomarkers in first episode psychosis

Simple item page
dc.contributor.authorFranco, Pamela
dc.contributor.authorMontalba, Cristian
dc.contributor.authorCaulier, Raúl
dc.contributor.authorMilovic, Carlos
dc.contributor.authorGonzález, Alfonso
dc.contributor.authorRamirez, Juan
dc.contributor.authorUndurraga, Juan
dc.contributor.authorSalas, Rodrigo
dc.contributor.authorCrossley, Nicolás
dc.contributor.authorTejos, Cristian
dc.contributor.authorUribe, Sergio
dc.date.accessioned2026-09-30T15:26:15Z
dc.date.available2026-09-30T15:26:15Z
dc.date.issued2025
dc.description.abstractBackground and purpose: Several studies have shown changes in neurochemicals within the deep-brain nuclei of patients with psychosis. These alterations indicate a dysfunction in dopamine within subcortical regions affected by fluctuations in iron concentrations. Quantitative Susceptibility Mapping (QSM) is a method employed to measure iron concentration, offering a potential means to identify dopamine dysfunction in these subcortical areas. This study employed a random forest algorithm to predict susceptibility features of the First-Episode Psychosis (FEP) and the response to antipsychotics using Shapley Additionality Explanation (SHAP) values. Methods: 3D multi-echo Gradient Echo (GRE) and T1-weighted GRE were obtained in 61 healthy-volunteers (HV) and 76 FEP patients (32 % Treatment-Resistant Schizophrenia (TRS) and 68 % treatment-Responsive Schizophrenia (RS)) using a 3T Philips Ingenia MRI scanner. QSM and R2* were reconstructed and averaged in twenty-two segmented regions of interest. We used a Sequential Forward Selection as a feature selection algorithm and a Random Forest as a model to predict FEP patients and their response to antipsychotics. We further applied the SHAP framework to identify informative features and their interpretations. Finally, multiple correlation patterns from magnetic susceptibility parameters were extracted using hierarchical clustering. Results: Our approach accurately classifies HV and FEP patients with 76.48 ± 10.73 % accuracy (using four features) and TRS vs RS patients with 76.43 ± 12.57 % accuracy (using four features), using 10-fold stratified cross-validation. The SHAP analyses indicated the top four nonlinear relationships between the selected features. Hierarchical clustering revealed two groups of correlated features for each study. Conclusions: Early prediction of treatment response enables tailored strategies for FEP patients with treatment resistance, ensuring timely and effective interventions.
dc.description.versionVersión Publicada
dc.identifier.citationFranco, P., Montalba, C., Caulier-Cisterna, R., Milovic, C., González, A., Ramirez-Mahaluf, J. P., Undurraga, J., Salas, R., Crossley, N., Tejos, C., & Uribe, S. (2025). Interpretable machine learning model for characterizing magnetic susceptibility-based biomarkers in first episode psychosis. Computer methods and programs in biomedicine, 272, 109067. https://doi.org/10.1016/j.cmpb.2025.109067
dc.identifier.doihttps://doi.org/10.1016/j.cmpb.2025.109067
dc.identifier.urihttps://hdl.handle.net/11447/11211
dc.language.isoen
dc.subjectBiomarkers
dc.subjectArtificial intelligence for medical imaging
dc.subjectInterpretable machine learning
dc.subjectMagnetic resonance imaging
dc.subjectQuantitative susceptibility mapping
dc.titleInterpretable machine learning model for characterizing magnetic susceptibility-based biomarkers in first episode psychosis
dc.typeArticle
dcterms.accessRightsAcceso Abierto
dcterms.sourceComputer methods and programs in biomedicine
dspace.entity.typePublication
relation.isAuthorOfPublication7a9f060d-7506-44d2-84ae-30bce0fea90a
relation.isAuthorOfPublication.latestForDiscovery7a9f060d-7506-44d2-84ae-30bce0fea90a

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Interpretable machine learning model for characterizing magnetic susceptibility-based biomarkers in first episode psychosis.pdf
Size:
4.37 MB
Format:
Adobe Portable Document Format
Description:
Texto Completo
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
347 B
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Artículos Medicina y Ciencias de la Salud

Implementado por OpenGeek Services