Patients with schizophrenia have been shown to have an increased risk for physical violence. While certain features have been identified as risk factors, it has been difficult to integrate these variables to identify violent patients. The present study thus attempts to develop a clinically-relevant predictive tool. In a population of 275 schizophrenia patients, we identified 103 participants as violent and 172 as non-violent through electronic medical documentation, and conducted cross-sectional assessments to identify demographic, clinical, and sociocultural variables. Using these predictors, we utilized seven machine learning classification algorithms to predict for past instances of physical violence. Our classification algorithms predicted with significant accuracy compared to random discrimination alone, and had varying degrees of predictive power, as described by various performance measures. We determined that the random forest model performed marginally better than other algorithms, with an accuracy of 62% and an area under the receiver operator characteristic curve (AUROC) of 0.63. To summarize, machine learning classification algorithms are becoming increasingly valuable, though, optimization of these models is needed to better complement diagnostic decisions regarding early interventional measures to predict instances of physical violence.
Pubmed ID: 32361562 RIS Download
Publication data is provided by the National Library of Medicine ® and PubMed ®. Data is retrieved from PubMed ® on a weekly schedule. For terms and conditions see the National Library of Medicine Terms and Conditions.
scikit-learn: machine learning in Python
View all literature mentionsA web-based workbench to conveniently compare the classification performances of many different filter-based gene selection procedures. In addition to the commonly used filter metric-classifier combinations, user can test various additive methodological options by specification of only up- or down-regulated genes to select, applying feature discretization and adding feature vectors to make a new feature. Throughout the comprehensive comparisons, user can identify the best performing gene selection procedure and subsequent classification performance measured by .632+ bootstrap error estimation for the given binary (two-class) microarray data.
View all literature mentions