Browsing by Author "Milovic, Carlos"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Interpretable machine learning model for characterizing magnetic susceptibility-based biomarkers in first episode psychosis
    (2025) Franco, Pamela; Montalba, Cristian; Caulier, Raúl; Milovic, Carlos; González, Alfonso; Ramirez, Juan; Undurraga, Juan; Salas, Rodrigo; Crossley, Nicolás; Tejos, Cristian; Uribe, Sergio
    Background 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.
  • Thumbnail Image
    Publication
    Quantitative Susceptibility Mapping MRI in Deep-Brain Nuclei in First-Episode Psychosis
    (2023) García Saborit, Marisleydis; Jara, Alejandro; Muñoz, Néstor; Milovic, Carlos; Tepper, Angeles; Alliende, Luz María; Mena, Carlos; Iruretagoyena, Bárbara; Ramírez-Mahaluf, Juan Pablo; Díaz, Camila; Nachar, Ruben; Castañeda, Carmen Paz; González, Alfonso; Undurraga, Juan; Crossley, Nicolás; Tejos, Cristian
    Background: Psychosis is related to neurochemical changes in deep-brain nuclei, particularly suggesting dopamine dysfunctions. We used an magnetic resonance imaging-based technique called quantitative susceptibility mapping (QSM) to study these regions in psychosis. QSM quantifies magnetic susceptibility in the brain, which is associated with iron concentrations. Since iron is a cofactor in dopamine pathways and co-localizes with inhibitory neurons, differences in QSM could reflect changes in these processes. Methods: We scanned 83 patients with first-episode psychosis and 64 healthy subjects. We reassessed 22 patients and 21 control subjects after 3 months. Mean susceptibility was measured in 6 deep-brain nuclei. Using linear mixed models, we analyzed the effect of case-control differences, region, age, gender, volume, framewise displacement (FD), treatment duration, dose, laterality, session, and psychotic symptoms on QSM. Results: Patients showed a significant susceptibility reduction in the putamen and globus pallidus externa (GPe). Patients also showed a significant R2* reduction in GPe. Age, gender, FD, session, group, and region are significant predictor variables for QSM. Dose, treatment duration, and volume were not predictor variables of QSM. Conclusions: Reduction in QSM and R2* suggests a decreased iron concentration in the GPe of patients. Susceptibility reduction in putamen cannot be associated with iron changes. Since changes observed in putamen and GPe were not associated with symptoms, dose, and treatment duration, we hypothesize that susceptibility may be a trait marker rather than a state marker, but this must be verified with long-term studies.

Implementado por OpenGeek Services