Meeting Banner
Abstract #4101

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

Pamela Franco1, Cristian Montalba2,3,4, Raúl Caulier-Cisterna5, Carlos Molovic6, Alfonso González7, Juan Pablo Ramirez-Mahaluf7, Juan Undurraga7, Nicolás Crossley8, and Cristian Tejos9
1Energy Transformation Center, Universidad Andrés Bello, Santiago, Chile, 2Biomedical Imaging Center, Pontificia Universidad Católica, Santiago, Chile, 3Radiology Department, Pontificia Universidad Católica de Chile, Santiago, Chile, 4Millennium Institute for Intelligent Healthcare Engineering, Santiago, Chile, 5Department of Informatics and Computing, Universidad Tecnológica Metropolitana, Santiago, Chile, 6School of Electrical Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile, 7Department of Psychiatry, Pontificia Universidad Católica de Chile, Santiago, Chile, 8Pontificia Universidad Católica de Chile, Santiago, Chile, 9Biomedical Imaging Center, Pontificia Universidad Católica de Chile, Santiago, Chile

Synopsis

Keywords: Psychiatric Disorders, Psychiatric Disorders, Machine learning

Motivation: The research aims to improve diagnostic accuracy and treatment strategies for First-Episode Psychosis by identifying critical brain iron biomarkers.

Goal(s): The present study aims to pinpoint potential predictive biomarkers derived from QSM and R2* for individuals experiencing first-episode-psychosis (FEP), along with their response to antipsychotic treatment.

Approach: The study used MRI to assess brain iron levels in psychosis patients, employing machine learning for classification and treatment response prediction.

Results: The study achieved 76.48% accuracy in classifying healthy individuals from First-Episode Psychosis patients and 76.43% accuracy in predicting treatment responses, identifying key biomarkers linked to dopamine pathways.

Impact: This study identifies key brain iron concentration biomarkers using QSM and R2* in FEP, achieving 76% classification accuracy. It highlights the potential for improved early detection and treatment response prediction, paving the way for enhanced clinical outcomes in schizophrenia management.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords