Escape and absconding among offenders with schizophrenia spectrum disorder – an explorative analysis of characteristics

Abstract Background Escape and absconding, especially in forensic settings, can have serious consequences for patients, staff institutions. Several characteristics of affected patients could be identified so far, albeit based on heterogeneous patient populations, a limited number possible factors basal statistical analyses. The aim this study was to determine the most important among large variables describe best model using machine learning homogeneous group offender with schizophrenia spectrum disorder. Methods A database 370 suffering from disorder 507 predictor explored by learning. To counteract overfitting, divided into training validation set nested procedure used set. tested were extracted. Results final resulted balanced accuracy 71.1% (95% CI = [58.5, 83.1]) an AUC 0.75 [0.63, 0.87]). as relevant related absconding/ escape listed least were: more frequent forbidden intake drugs during current hospitalization, index offences, higher neuroleptic medication, rule breaking behavior PANSS Score at discharge, lower age admission, dissocial shorter time spent hospitalization admission. Conclusions For first detailed built topic. results indicate presence particularly problematic subgroup within offenders schizophrenic who also tend or abscond. Early identification tailored treatment these clinical benefit.