Purpose. The purpose of the present study is to explore whether the Addiction Severity Index (ASI) can be used to predict violent crime among drug-using inmates. The association between substance abuse and violent crime among drug-using inmates was also evaluated. Methods. The participants were male, drug-using inmates (N=178) of two Dutch penitentiaries. In a prospective study, discriminant analysis was applied to explore which variables distinguish between participants with and without violent crime during a two-year follow-up period after detention. Predictive validity of demographic variables, criminal history variables and ASI variables were assessed. DSM-III classifications, measured by the DIS, were compared with ASI variables on their predictive validity. Results. Overall correct classification of violent crime varied between 82% and 93%. Information from the ASI in addition to demographic variables and the criminal past ofa detainee clearly improved the overall correct classification of participants committing violent crime, and the percentage of variance explained. Compared to DIS diagnoses, ASI variables explained 19% more variance. Apart from the ASI severity rating for criminal past, the number of years of regular cocaine use, and the age at which cocaine use started, were major contributors of the ASI's predictive power. Conclusions. The ASI is a useful instrument for the prediction of violent crime among drug-using inmates. The ASI-based assessment of drug use can indicate a risk of violent crime. Further research is needed into the processes involved in this predictive power, as well as into the circumstances in which drug use induces violent crime. This may lead to the prevention of violent crime in this particular group of inmates.