Forecasting violent behaviors for schizophrenic outpatients using their disease insights: Development of a binary logistic regression model and a support vector model

This study explored the predictive value of disease insight for violent behavior for a group of Taiwanese schizophrenic outpatients over a one-year period. The Schedule of Assessment of Insight in Psychosis and its expanded version were used to provide a baseline insight score for sixty-three schizophrenic outpatients considered to be in remission or to have minimal psychopathology. A psychiatrist reassessed subjects at the end of the period to determine the predictive value of initial insight rating on the presence of violent behaviors. The binary logistic regression model was built first, which could explain 65.2 percent of the variance of patients' violent behavior tendency. Then, a support vector machine (SVM) was developed. After the training with cross validation, no misclassifications were found in the training data, and the average percentage of misclassification for the testing data was 23.8 percent, resulting in a 76.2 percent predictive power. These findings showed that SVM is more robust than a binary logistic regression model due to the good learning capability of an SVM for the nonlinear dependency between the input and output (also called outcome) variables. This SVM might help to build an early-warning and advisory system guiding the medical care of schizophrenic patients living in the community.