PREDICTORS OF TREATMENT NON-ADHERENCE IN AN INPATIENT SUBSTANCE ABUSE REHABILITATION PROGRAMME

The research study aimed to identify the factors contributing to premature termination of treatment for substance addiction. The investigation took the form of a differential research design based on archival data obtained from patient files at an inpatient drug rehabilitation centre in Gauteng. One independent variable (treatment adherence) and five dependent variables (past and present patterns of scheduled medication use, legal history and DSM-IV-TR Axis I and II co-morbidity) were chosen. Eighty-five patient files were drawn, constituting 41 treatment adherent and 44 treatment non-adherent addicts. Extraneous variables of age, age of onset, duration of addiction, previous treatment history, drug of choice, current physical health status, gender, race, and level of education were equivalent in both samples. Univariate analysis indicated that treatment adherent and drop-out groups differed significantly in terms of legal history (Fisher's exact test = 12.369; p = 0.002) and past patterns of use of scheduled medication (Fisher's exact test = 29.131; p = 0.000). A logistic regression indicated that a history of abusing a combination of scheduled psychiatric and other medication prior to treatment is the single most accurate predictor of treatment non-adherence (Wald statistic = 11.1035, p = 0.0009). Although certain combinations of past medication patterns and legal history increase predicted probabilities of treatment non-adherence, legal history on its own failed to explain any further variance that past medication could not explain on its own.