Meeting Banner
Abstract #0353

Prediction of Genetic Risks in Schizophrenia: A DTI-Based Pattern Classification Study

Madhura Ingalhalikar1, Stathis Kanterakis1, Drew Parker1, Raquel E. Gur2, Ruben C. Gur2, Ragini Verma1

1Section of Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA; 2Brain Behavior Laboratory, Department of Psychiatry, University of Pennsylvania, Philadelphia, PA, USA


This study investigates the presence of endophenotypic brain patterns in first-degree family members of patients with schizophrenia via a diffusion tensor based classification study. High dimensional gender specific classifiers were constructed for patients diagnosed with schizophrenia or schizoaffective disorder and healthy controls. Superior cross-validated classification was obtained between patients with schizophrenia and healthy controls with 88.25% accuracy in males and 75.04% accuracy in females. The classifier associated a genetic pattern score to each of the asymptomatic FM. The female FM displayed scores that were closer to the patient spectrum than the male FM, indicating possibly enhanced genetic susceptibility of schizophrenia in females.